Search results for: inference attack

Authors: Manas Tripathi, Arunabha Mukhopadhyay

Abstract:

In Cloud computing environment, cloud servers, sometimes may crash after receiving huge amount of request and cloud services may stop which can create huge loss to users of that cloud services. This situation is called Denial of Service (DoS) attack. In Distributed Denial of Service (DDoS) attack, an attacker targets multiple network paths by compromising various vulnerable systems (zombies) and floods the victim with huge amount of request through these zombies. There are many solutions to mitigate this challenge but most of the methods allows the attack traffic to arrive at Cloud Service Provider (CSP) and then only takes actions against mitigation. Here in this paper we are rather focusing on preventive mechanism to deal with these attacks. We analyze network topology and find most vulnerable paths beforehand without waiting for the traffic to arrive at CSP. We have used Dijkstra's and Yen’s algorithm. Finally, risk assessment of these paths can be done by multiplying the probabilities of attack for these paths with the potential loss.

Keywords: cloud computing, DDoS, Dijkstra, Yen’s k-shortest path, network security

Procedia PDF Downloads 257

Authors: Haonan Hu, Shuge Lei, Dasheng Sun, Huabin Zhang, Kehong Yuan, Jian Dai, Jijun Tang

Abstract:

This paper focuses on the classification task of breast ultrasound images and conducts research on the reliability measurement of classification results. A dual-channel evaluation framework was developed based on the proposed inference reliability and predictive reliability scores. For the inference reliability evaluation, human-aligned and doctor-agreed inference rationals based on the improved feature attribution algorithm SP-RISA are gracefully applied. Uncertainty quantification is used to evaluate the predictive reliability via the test time enhancement. The effectiveness of this reliability evaluation framework has been verified on the breast ultrasound clinical dataset YBUS, and its robustness is verified on the public dataset BUSI. The expected calibration errors on both datasets are significantly lower than traditional evaluation methods, which proves the effectiveness of the proposed reliability measurement.

Keywords: medical imaging, ultrasound imaging, XAI, uncertainty measurement, trustworthy AI

Procedia PDF Downloads 57

Authors: Jonathan Sohn

Abstract:

Deep neural networks (DNNs) have shown state-of-the-art performance for many applications, including computer vision, natural language processing, and speech recognition. Recently, adversarial attacks have been studied in the context of deep neural networks, which aim to alter the results of deep neural networks by modifying the inputs slightly. For example, an adversarial attack on a DNN used for object detection can cause the DNN to miss certain objects. As a result, the reliability of DNNs is undermined by their lack of robustness against adversarial attacks, raising concerns about their use in safety-critical applications such as autonomous driving. In this paper, we focus on studying the adversarial attacks and defenses on DNNs for image classification. There are two types of adversarial attacks studied which are fast gradient sign method (FGSM) attack and projected gradient descent (PGD) attack. A DNN forms decision boundaries that separate the input images into different categories. The adversarial attack slightly alters the image to move over the decision boundary, causing the DNN to misclassify the image. FGSM attack obtains the gradient with respect to the image and updates the image once based on the gradients to cross the decision boundary. PGD attack, instead of taking one big step, repeatedly modifies the input image with multiple small steps. There is also another type of attack called the target attack. This adversarial attack is designed to make the machine classify an image to a class chosen by the attacker. We can defend against adversarial attacks by incorporating adversarial examples in training. Specifically, instead of training the neural network with clean examples, we can explicitly let the neural network learn from the adversarial examples. In our experiments, the digit recognition accuracy on the MNIST dataset drops from 97.81% to 39.50% and 34.01% when the DNN is attacked by FGSM and PGD attacks, respectively. If we utilize FGSM training as a defense method, the classification accuracy greatly improves from 39.50% to 92.31% for FGSM attacks and from 34.01% to 75.63% for PGD attacks. To further improve the classification accuracy under adversarial attacks, we can also use a stronger PGD training method. PGD training improves the accuracy by 2.7% under FGSM attacks and 18.4% under PGD attacks over FGSM training. It is worth mentioning that both FGSM and PGD training do not affect the accuracy of clean images. In summary, we find that PGD attacks can greatly degrade the performance of DNNs, and PGD training is a very effective way to defend against such attacks. PGD attacks and defence are overall significantly more effective than FGSM methods.

Keywords: deep neural network, adversarial attack, adversarial defense, adversarial machine learning

Procedia PDF Downloads 158

Authors: Akash Amalan, Rui Wang, Yanqi Qiao, Emmanouil Panaousis, Kaitai Liang

Abstract:

Federated learning is an emerging concept in the domain of distributed machine learning. This concept has enabled General Adversarial Networks (GANs) to benefit from the rich distributed training data while preserving privacy. However, in a non-IID setting, current federated GAN architectures are unstable, struggling to learn the distinct features, and vulnerable to mode collapse. In this paper, we propose an architecture MULTI-FLGAN to solve the problem of low-quality images, mode collapse, and instability for non-IID datasets. Our results show that MULTI-FLGAN is four times as stable and performant (i.e., high inception score) on average over 20 clients compared to baseline FLGAN.

Keywords: federated learning, generative adversarial network, inference attack, non-IID data distribution

Procedia PDF Downloads 118

Authors: Zhen Cheng, Xinyu Dai, Shujian Huang, Jiajun Chen

Abstract:

Recently, explanatory natural language inference has attracted much attention for the interpretability of logic relationship prediction, which is also known as explanation generation for Natural Language Inference (NLI). Existing explanation generators based on discriminative Encoder-Decoder architecture have achieved noticeable results. However, we find that these discriminative generators usually generate explanations with correct evidence but incorrect logic semantic. It is due to that logic information is implicitly encoded in the premise-hypothesis pairs and difficult to model. Actually, logic information identically exists between premise-hypothesis pair and explanation. And it is easy to extract logic information that is explicitly contained in the target explanation. Hence we assume that there exists a latent space of logic information while generating explanations. Specifically, we propose a generative model called Variational Explanation Generator (VariationalEG) with a latent variable to model this space. Training with the guide of explicit logic information in target explanations, latent variable in VariationalEG could capture the implicit logic information in premise-hypothesis pairs effectively. Additionally, to tackle the problem of posterior collapse while training VariaztionalEG, we propose a simple yet effective approach called Logic Supervision on the latent variable to force it to encode logic information. Experiments on explanation generation benchmark—explanation-Stanford Natural Language Inference (e-SNLI) demonstrate that the proposed VariationalEG achieves significant improvement compared to previous studies and yields a state-of-the-art result. Furthermore, we perform the analysis of generated explanations to demonstrate the effect of the latent variable.

Keywords: natural language inference, explanation generation, variational auto-encoder, generative model

Procedia PDF Downloads 122

Authors: G. Usha, S. Kannimuthu, K. Mahalakshmi

Abstract:

Mobile Adhoc Network (MANET) is one of the most promising technologies that have applications ranging from various portable devices to military networks. MANET has no fixed infrastructure and the security of such network is a big concern. Therefore, in order to operate MANET’s securely, the misbehavior and intrusions should be detected before the attackers affect the network communication. In this article, we make a comprehensive survey against black hole attack that is a serious threat against MANET that exploits the routing behavior of the MANET. We have given broad survey solutions that detect black hole attacks in MANET. This is achieved by analyzing the techniques involved in detecting the attacks in each scheme. Furthermore, we examine about the challenges to the researchers for constructing an in-depth solution against black hole attack.

Keywords: AODV, cross layer security, mobile Adhoc network (MANET), packet delivery ratio, single layer security

Procedia PDF Downloads 380

Authors: Rakesh Kumar, A. K. Ghosh

Abstract:

The paper presents the modeling of linear and nonlinear longitudinal aerodynamics using real flight data of Hansa-3 aircraft gathered at low and high angles of attack. The Neural-Gauss-Newton (NGN) method has been applied to model the linear and nonlinear longitudinal dynamics and estimate parameters from flight data. Unsteady aerodynamics due to flow separation at high angles of attack near stall has been included in the aerodynamic model using Kirchhoff’s quasi-steady stall model. NGN method is an algorithm that utilizes Feed Forward Neural Network (FFNN) and Gauss-Newton optimization to estimate the parameters and it does not require any a priori postulation of mathematical model or solving of equations of motion. NGN method was validated on real flight data generated at moderate angles of attack before application to the data at high angles of attack. The estimates obtained from compatible flight data using NGN method were validated by comparing with wind tunnel values and the maximum likelihood estimates. Validation was also carried out by comparing the response of measured motion variables with the response generated by using estimates a different control input. Next, NGN method was applied to real flight data generated by executing a well-designed quasi-steady stall maneuver. The results obtained in terms of stall characteristics and aerodynamic parameters were encouraging and reasonably accurate to establish NGN as a method for modeling nonlinear aerodynamics from real flight data at high angles of attack.

Keywords: parameter estimation, NGN method, linear and nonlinear, aerodynamic modeling

Procedia PDF Downloads 414

Authors: Jaimin Patel

Abstract:

Cloud computing is one of the most sharp and important movement in various computing technologies. It provides flexibility to users, cost effectiveness, location independence, easy maintenance, enables multitenancy, drastic performance improvements, and increased productivity. On the other hand, there are also major issues like security. Being a common server, security for a cloud is a major issue; it is important to provide security to protect user’s private data, and it is especially important in e-commerce and social networks. In this paper, encryption algorithms such as Advanced Encryption Standard algorithms, their vulnerabilities, risk of attacks, optimal time and complexity management and comparison with other algorithms based on software implementation is proposed. Encryption techniques to improve the performance of AES algorithms and to reduce risk management are given. Secure Hash Algorithms, their vulnerabilities, software implementations, risk of attacks and comparison with other hashing algorithms as well as the advantages and disadvantages between hashing techniques and encryption are given.

Keywords: Cloud computing, encryption algorithm, secure hashing algorithm, brute force attack, birthday attack, plaintext attack, man in middle attack

Procedia PDF Downloads 251

Authors: Nasser S. Shebka

Abstract:

Fuzzy logic is used in complex adaptive systems where classical tools of representing knowledge are unproductive. Nevertheless, the incorporation of fuzzy logic, as it’s the case with all artificial intelligence tools, raised some inconsistencies and limitations in dealing with increased complexity systems and rules that apply to real-life situations and hinders the ability of the inference process of such systems, but it also faces some inconsistencies between inferences generated fuzzy rules of complex or imprecise knowledge-based systems. The use of fuzzy logic enhanced the capability of knowledge representation in such applications that requires fuzzy representation of truth values or similar multi-value constant parameters derived from multi-valued logic, which set the basis for the three t-norms and their based connectives which are actually continuous functions and any other continuous t-norm can be described as an ordinal sum of these three basic ones. However, some of the attempts to solve this dilemma were an alteration to fuzzy logic by means of non-monotonic logic, which is used to deal with the defeasible inference of expert systems reasoning, for example, to allow for inference retraction upon additional data. However, even the introduction of non-monotonic fuzzy reasoning faces a major issue of conflict resolution for which many principles were introduced, such as; the specificity principle and the weakest link principle. The aim of our work is to improve the logical representation and functional modelling of AI systems by presenting a method of resolving existing and potential rule conflicts by representing temporal modalities within defeasible inference rule-based systems. Our paper investigates the possibility of resolving fuzzy rules conflict in a non-monotonic fuzzy reasoning-based system by introducing temporal modalities and Kripke's general weak modal logic operators in order to expand its knowledge representation capabilities by means of flexibility in classifying newly generated rules, and hence, resolving potential conflicts between these fuzzy rules. We were able to address the aforementioned problem of our investigation by restructuring the inference process of the fuzzy rule-based system. This is achieved by using time-branching temporal logic in combination with restricted first-order logic quantifiers, as well as propositional logic to represent classical temporal modality operators. The resulting findings not only enhance the flexibility of complex rule-base systems inference process but contributes to the fundamental methods of building rule bases in such a manner that will allow for a wider range of applicable real-life situations derived from a quantitative and qualitative knowledge representational perspective.

Keywords: fuzzy rule-based systems, fuzzy tense inference, intelligent systems, temporal modalities

Procedia PDF Downloads 63

Authors: Zhan Chen, Wenquan Bi, Xiaoyun Wang

Abstract:

The Midori family of light weight block cipher is proposed in ASIACRYPT2015. It has attracted the attention of numerous cryptanalysts. There are two versions of Midori: Midori64 which takes a 64-bit block size and Midori128 the size of which is 128-bit. In this paper an improved 10-round impossible differential attack on Midori64 is proposed. Pre-whitening keys are considered in this attack. A better impossible differential path is used to reduce time complexity by decreasing the number of key bits guessed. A hash table is built in the pre-computation phase to reduce computational complexity. Partial abort technique is used in the key seiving phase. The attack requires 259 chosen plaintexts, 214.58 blocks of memory and 268.83 10-round Midori64 encryptions.

Keywords: cryptanalysis, impossible differential, light weight block cipher, Midori

Procedia PDF Downloads 325

Authors: Asma Ben Yaghlane, Mohamed Naceur Azaiez, Mehdi Mrad

Abstract:

We investigate the large scale of networks in the context of network survivability under attack. We use appropriate techniques to evaluate and the attacker-based- and the defender-based-network survivability. The attacker is unaware of the operated links by the defender. Each attacked link has some pre-specified probability to be disconnected. The defender choice is so that to maximize the chance of successfully sending the flow to the destination node. The attacker however will select the cut-set with the highest chance to be disabled in order to partition the network. Moreover, we extend the problem to the case of selecting the best p paths to operate by the defender and the best k cut-sets to target by the attacker, for arbitrary integers p,k > 1. We investigate some variations of the problem and suggest polynomial-time solutions.

Keywords: defense/attack strategies, large scale, networks, partitioning a network

Procedia PDF Downloads 246

Authors: Said Abdul Ahad Ahadi, Elyas Baray, Nitin Rakesh, Sudeep Varshney

Abstract:

Wi-Fi is a widely used internet source that is used to provide internet access in many areas such as Stores, Cafes, University campuses, Restaurants and so on. This technology brought more facilities in communication and networking. On the other hand, due to the transmission of data over the air, which makes the network vulnerable, so it becomes prone to various threats such as Evil Twin and etc. The Evil Twin is a kind of adversary which impersonates a legitimate access point (LAP) as it can happen by spoofing the name (SSID) and MAC address (BSSID) of a legitimate access point (LAP). And this attack can cause many threats such as MITM, Service Interruption, Access point service blocking. Various Evil Twin Attack Detection Techniques are proposed, but they require additional hardware, or they require protocol modification. In this paper, we proposed a new technique based on Access Point’s two fingerprints, Received Signal Strength Indicator (RSSI) and Hop Count, that is hard to copy by an adversary. And we implemented the technique in a system called “ETDetector,” which can detect and prevent the attack.

Keywords: evil twin, LAP, SSID, Wi-Fi security, signal variation, ETAD, kali linux, scapy, python

Procedia PDF Downloads 119

Authors: Yas Barzegar, Atrin Barzegar

Abstract:

Drinking water quality assessment is a major issue today; technology and practices are continuously improving; Artificial Intelligence (AI) methods prove their efficiency in this domain. The current research seeks a hierarchical fuzzy model for predicting drinking water quality in Rome (Italy). The Mamdani fuzzy inference system (FIS) is applied with different defuzzification methods. The Proposed Model includes three fuzzy intermediate models and one fuzzy final model. Each fuzzy model consists of three input parameters and 27 fuzzy rules. The model is developed for water quality assessment with a dataset considering nine parameters (Alkalinity, Hardness, pH, Ca, Mg, Fluoride, Sulphate, Nitrates, and Iron). Fuzzy-logic-based methods have been demonstrated to be appropriate to address uncertainty and subjectivity in drinking water quality assessment; it is an effective method for managing complicated, uncertain water systems and predicting drinking water quality. The FIS method can provide an effective solution to complex systems; this method can be modified easily to improve performance.

Keywords: water quality, fuzzy logic, smart cities, water attribute, fuzzy inference system, membership function

Procedia PDF Downloads 43

Authors: Noureddine Mohtaram, Jeremy Patrix, Jerome Verny

Abstract:

As an enormous number of online services have been developed into web applications, security problems based on web applications are becoming more serious now. Most intrusion detection systems rely on each request to find the cyber-attack rather than on user behavior, and these systems can only protect web applications against known vulnerabilities rather than certain zero-day attacks. In order to detect new attacks, we analyze the HTTP protocols of web servers to divide them into two categories: normal attacks and malicious attacks. On the other hand, the quality of the results obtained by deep learning (DL) in various areas of big data has given an important motivation to apply it to cybersecurity. Deep learning for attack detection in cybersecurity has the potential to be a robust tool from small transformations to new attacks due to its capability to extract more high-level features. This research aims to take a new approach, deep learning to cybersecurity, to classify these two categories to eliminate attacks and protect web servers of the defense sector which encounters different web traffic compared to other sectors (such as e-commerce, web app, etc.). The result shows that by using a machine learning method, a higher accuracy rate, and a lower false alarm detection rate can be achieved.

Keywords: anomaly detection, HTTP protocol, logs, cyber attack, deep learning

Procedia PDF Downloads 178

Authors: Yuri Boiko, Iluju Kiringa, Tet Yeap

Abstract:

Current drainage attack suggested previously is further studied in regular settings of closed-loop controlled Brushless DC (BLDC) motor with Kalman filter in the feedback loop. Modeling and simulation experiments are conducted in a Matlab environment, implementing the closed-loop control model of BLDC motor operation in position sensorless mode under Kalman filter drive. The current increase in the motor windings is caused by the controller (p-controller in our case) affected by false data injection of substitution of the angular velocity estimates with distorted values. Operation of multiplication to distortion coefficient, values of which are taken from the distortion function synchronized in its periodicity with the rotor’s position change. A saw function with a triangular tooth shape is studied herewith for the purpose of carrying out the bias injection with current drainage consequences. The specific focus here is on how the asymmetry of the tooth in the saw function affects the flow of current drainage. The purpose is two-fold: (i) to produce and collect the signature of an asymmetric saw in the attack for further pattern recognition process, and (ii) to determine conditions of improving stealthiness of such attack via regulating asymmetry in saw function used. It is found that modification of the symmetry in the saw tooth affects the periodicity of current drainage modulation. Specifically, the modulation frequency of the drained current for a fully asymmetric tooth shape coincides with the saw function modulation frequency itself. Increasing the symmetry parameter for the triangle tooth shape leads to an increase in the modulation frequency for the drained current. Moreover, such frequency reaches the switching frequency of the motor windings for fully symmetric triangular shapes, thus becoming undetectable and improving the stealthiness of the attack. Therefore, the collected signatures of the attack can serve for attack parameter identification via the pattern recognition route.

Keywords: bias injection attack, Kalman filter, BLDC motor, control system, closed loop, P-controller, PID-controller, current drainage, saw-function, asymmetry

Procedia PDF Downloads 51

Authors: Gigih Supriyatno

Abstract:

SQL injection is one of the most common types of attacks and has a very critical impact on web servers. In the worst case, an attacker can perform post-exploitation after a successful SQL injection attack. In the case of forensics web servers, web server analysis is closely related to log file analysis. But sometimes large file sizes and different log types make it difficult for investigators to look for traces of attackers on the server. The purpose of this paper is to help investigator take appropriate steps to investigate when the web server gets attacked. We use attack scenarios using SQL injection attacks including PHP backdoor injection as post-exploitation. We perform post-mortem analysis of web server logs based on Hypertext Transfer Protocol (HTTP) POST and HTTP GET method approaches that are characteristic of SQL injection attacks. In addition, we also propose structured analysis method between the web server application log file, database application, and other additional logs that exist on the webserver. This method makes the investigator more structured to analyze the log file so as to produce evidence of attack with acceptable time. There is also the possibility that other attack techniques can be detected with this method. On the other side, it can help web administrators to prepare their systems for the forensic readiness.

Keywords: web forensic, SQL injection, investigation, web shell

Procedia PDF Downloads 120

Authors: Amir B. Khoshnevis, Morteza Mirhosseini

Abstract:

The paper deals with a sub-part of an extensive research program on the wake survey method in various Reynolds numbers and angles of attack. This research experimentally investigates the wake flow characteristics behind S823 and S822 airfoils in which designed for small wind turbines. Velocity measurements determined by using hot-wire anemometer. Data acquired in the wake of the airfoil at locations(c is the chord length): 0.01c - 3c. Reynolds number increased due to increase of free stream velocity. Results showed that mean velocity profiles depend on the angle of attack and location of data collections. Data acquired at the low Reynolds numbers (smaller than 10^5). Effects of Reynolds numbers on the mean velocity profiles are more significant in near locations the trailing edge and these effects decrease by taking distance from trailing edge toward downstream. Mean velocity profiles region increased by increasing the angle of attack, except for 7°, and also the maximum velocity deficit (velocity defect) increased. The difference of mean velocity in and out of the wake decreased by taking distance from trailing edge, and mean velocity profile become wider and more uniform.

Keywords: angle of attack, Reynolds number, velocity deficit, separation

Procedia PDF Downloads 350

Authors: Karima Djebaili, Lamine Melkemi

Abstract:

Elgamal encryption is a fundamental public-key encryption in cryptography, which is based on the difficulty of discrete logarithm problem and the Diffie-Hellman problem. Supposing the Diffie–Hellman problem is computationally infeasible then Elgamal is secure under a chosen plaintext attack, where security indicates it is difficult for the attacker, given the ciphertext, to restore the whole of the plaintext. However, although it is secure against chosen plaintext attack, Elgamal is absolutely malleable i.e. is not secure against an adaptive chosen ciphertext attack, where the attacker can recover the plaintext. We present a extension on Elgamal encryption which result in non-malleability against adaptive chosen plaintext attack using concatenation and a cryptographic hash function, our evidence utilizes the device of plaintext aware. The algorithm proposed can be used in cryptography voting protocol given its level security. Our protocol protects the confidentiality of voters because each voter encrypts their choice before casting their vote, offers public verifiability using a signing algorithm, the final result is correctly computed using homomorphic property, and works even in the presence of an adversary due to the propriety of non-malleability. Moreover, the protocol prevents some parties colluding to fix the vote results.

Keywords: Elgamal encryption, non-malleability, plaintext aware, e-voting

Procedia PDF Downloads 422

Authors: Gennady P. Ginkul, Sergey Yu. Soloviov

Abstract:

The article proposes to use so-called "quotation-based algorithm" for simulation of decision making process in distributed expert systems and multi-agent systems. The idea was adopted from the techniques for group decision-making. It is based on the assumption that one expert system to perform its logical inference may use rules from another expert system. The application of the algorithm was demonstrated on the example in which the consolidated decision is the decision that requires minimal quotation.

Keywords: backward chaining inference, distributed expert systems, group decision making, multi-agent systems

Procedia PDF Downloads 345

Authors: B. Yanıktepe, C. Özalp, B. Şahin

Abstract:

Delta wing planform is an essential aerodynamic configuration, which could be effectively used at relatively high angles of attack than conventional wings in subsonic flow conditions. The flow over delta wings can be characterized by a pair of leading edge vortices emanating from wing apex. Boundary layer separation causes these vortical structures formed by rolling up of viscous flow sheet. This flow separation mechanism is occurred due to angle of attack and sharp leading edges of the delta wing. Therefore, complexity and variety in planform designs rise to catch the best under abnormal flow conditions. The present experimental study investigates the near surface flow structure and aerodynamic flow characteristics of X-45 type non-slender delta wing planform using dye visualization, Stereoscopic Particle Image Velocimetry (stereo-PIV). The instantaneous images are acquired on the plan-view plane within 5o≤α≤20o to calculate the time-averaged flow data. It can be concluded that vortical flow with a pair of well-defined LEVs over X-45 develop at very low angles of attack, secondary vortex are also evident and form close to the wing surface similar to delta and lambda planforms. The stall occurs at an angle of attack α=32o.

Keywords: aerodynamic, delta wing, PIV, vortex breakdown

Procedia PDF Downloads 387

Authors: V. S. S. Kumar, V. Ramya

Abstract:

In the modern electronic warfare, the signal scenario is changing at a rapid pace with the introduction of Low Probability of Intercept (LPI) radars. In the modern battlefield, radar system faces serious threats from passive intercept receivers such as Electronic Attack (EA) and Anti-Radiation Missiles (ARMs). To perform necessary target detection and tracking and simultaneously hide themselves from enemy attack, radar systems should be LPI. These LPI radars use a variety of complex signal modulation schemes together with pulse compression with the aid of advancement in signal processing capabilities of the radar such that the radar performs target detection and tracking while simultaneously hiding enemy from attack such as EA etc., thus posing a major challenge to the ES/ELINT receivers. Today an increasing number of LPI radars are being introduced into the modern platforms and weapon systems so these LPI radars created a requirement for the armed forces to develop new techniques, strategies and equipment to counter them. This paper presents various modulation techniques used in generation of LPI signals and development of Time Frequency Algorithms to analyse those signals.

Keywords: anti-radiation missiles, cross terms, electronic attack, electronic intelligence, electronic warfare, intercept receiver, low probability of intercept

Procedia PDF Downloads 410

Authors: İbrahi̇m Kara, Seher Arslankaya

Abstract:

Frequently preferred in the field of engineering in particular, data mining has now begun to be used in the field of health as well since the data in the health sector have reached great dimensions. With data mining, it is aimed to reveal models from the great amounts of raw data in agreement with the purpose and to search for the rules and relationships which will enable one to make predictions about the future from the large amount of data set. It helps the decision-maker to find the relationships among the data which form at the stage of decision-making. In this study, it is aimed to determine the risk of heart attack at the first stage, to control it, and to make its resource planning with the method of data mining. Through the early and correct diagnosis of heart attacks, it is aimed to reveal the factors which affect the diseases, to protect health and choose the right treatment methods, to reduce the costs in health expenditures, and to shorten the durations of patients’ stay at hospitals. In this way, the diagnosis and treatment costs of a heart attack will be scrutinized, which will be useful to determine the risk of the disease at the first stage, to control it, and to make its resource planning.

Keywords: data mining, decision support systems, heart attack, health sector

Procedia PDF Downloads 330

Authors: Marine Segui, Ruxandra Mihaela Botez

Abstract:

OpenVSP is an aerodynamic solver developed by National Aeronautics and Space Administration (NASA) that allows building a reliable model of an aircraft. This software performs an aerodynamic simulation according to the angle of attack of the aircraft makes between the incoming airstream, and its speed. A reliable aerodynamic model of the Cessna Citation X was designed but it required a lot of computation time. As a consequence, a prediction method was established that allowed predicting lift and drag coefficients for all Mach numbers and for all angles of attack, exclusively for stall conditions, from a computation of three angles of attack and only one Mach number. Aerodynamic coefficients given by the prediction method for a Cessna Citation X model were finally compared with aerodynamics coefficients obtained using a complete OpenVSP study.

Keywords: aerodynamic, coefficient, cruise, improving, longitudinal, openVSP, solver, time

Procedia PDF Downloads 202

Authors: Esther Chiramal, Kelvin Soh Boon Kai

Abstract:

Explainable AI is a strong strategy implemented to understand complex black-box model predictions in a human-interpretable language. It provides the evidence required to execute the use of trustworthy and reliable AI systems. On the other hand, however, it also opens the door to locating possible vulnerabilities in an AI model. Traditional adversarial text attack uses word substitution, data augmentation techniques, and gradient-based attacks on powerful pre-trained Bidirectional Encoder Representations from Transformers (BERT) variants to generate adversarial sentences. These attacks are generally white-box in nature and not practical as they can be easily detected by humans e.g., Changing the word from “Poor” to “Rich”. We proposed a simple yet effective Grey-box cum Black-box approach that does not require the knowledge of the model while using a set of surrogate Transformer/BERT models to perform the attack using Explainable AI techniques. As Transformers are the current state-of-the-art models for almost all Natural Language Processing (NLP) tasks, an attack generated from BERT1 is transferable to BERT2. This transferability is made possible due to the attention mechanism in the transformer that allows the model to capture long-range dependencies in a sequence. Using the power of BERT generalisation via attention, we attempt to exploit how transformers learn by attacking a few surrogate transformer variants which are all based on a different architecture. We demonstrate that this approach is highly effective to generate semantically good sentences by changing as little as one word that is not detectable by humans while still fooling other BERT models.

Keywords: BERT, explainable AI, Grey-box text attack, transformer

Procedia PDF Downloads 112

Authors: Farheen Tabassum, Shoab Ahmed Khan

Abstract:

The brutality of attacks on networks and decisive infrastructures are on the climb over recent years and appears to continue to do so. Distributed Denial of service attack is the most prevalent and easy attack on the availability of a service due to the easy availability of large botnet computers at cheap price and the general lack of protection against these attacks. Application layer DDoS attack is DDoS attack that is targeted on wed server, application server or database server. These types of attacks are much more sophisticated and challenging as they get around most conventional network security devices because attack traffic often impersonate normal traffic and cannot be recognized by network layer anomalies. Conventional techniques of single-hosted security systems are becoming gradually less effective in the face of such complicated and synchronized multi-front attacks. In order to protect from such attacks and intrusion, corporation among all network devices is essential. To overcome this issue, a collaborative intrusion detection system (CIDS) is proposed in which multiple network devices share valuable information to identify attacks, as a single device might not be capable to sense any malevolent action on its own. So it helps us to take decision after analyzing the information collected from different sources. This novel attack detection technique helps to detect seemingly benign packets that target the availability of the critical infrastructure, and the proposed solution methodology shall enable the incident response teams to detect and react to DDoS attacks at the earliest stage to ensure that the uptime of the service remain unaffected. Experimental evaluation shows that the proposed collaborative detection approach is much more effective and efficient than the previous approaches.

Keywords: Distributed Denial-of-Service (DDoS), Collaborative Intrusion Detection System (CIDS), Slowloris, OSSIM (Open Source Security Information Management tool), OSSEC HIDS

Procedia PDF Downloads 335

Authors: Omar Al Denali, Abdelaziz Badi

Abstract:

The ASTM A516 Grade 70 steel is a suitable material used for the fabrication of boiler pressure vessels working in moderate and lower temperature services, and it has good weldability and excellent notch toughness. The post-weld heat treatment (PWHT) or stress-relieving heat treatment has significant effects on avoiding the martensite transformation and resulting in high hardness, which can lead to cracking in the heat-affected zone (HAZ). An adaptive neuro-fuzzy inference system (ANFIS) was implemented to predict the material tensile strength of post-weld heat treatment (PWHT) experiments. The ANFIS models presented excellent predictions, and the comparison was carried out based on the mean absolute percentage error between the predicted values and the experimental values. The ANFIS model gave a Mean Absolute Percentage Error of 0.556 %, which confirms the high accuracy of the model.

Keywords: prediction, post-weld heat treatment, adaptive neuro-fuzzy inference system, mean absolute percentage error

Procedia PDF Downloads 118

Authors: Hesham A. El Zouka, Mustafa M. Hosni ka

Abstract:

The Radio Frequency Identification (RFID) technology has a diverse base of applications, but it is also prone to security threats. There are different types of security attacks that limit the range of the RFID applications. For example, deploying the RFID networks in insecure environments could make the RFID system vulnerable to many types of attacks such as spoofing attack, location traceability attack, physical attack and many more. Therefore, security is often an important requirement for RFID systems. In this paper, RFID mutual authentication protocol is implemented based on mobile agent technology and timestamp, which are used to provide strong authentication and integrity assurances to both the RFID readers and their corresponding RFID tags. The integration of mobile agent technology and timestamp provides promising results towards achieving this goal and towards reducing the security threats in RFID systems.

Keywords: RFID, security, authentication protocols, privacy, agent-based architecture, time-stamp, digital signature

Procedia PDF Downloads 229

Authors: Xiaobin Liang, Wei Liang, Laibin Zhang, Xiaoyan Guo

Abstract:

Pipelines pass through coal mined gobs inevitably in the mining area, the stability of which has great influence on the safety of pipelines. After extensive literature study and field research, it was found that there are a few risk assessment methods for coal mined gob pipelines, and there is a lack of data on the gob sites. Therefore, the fuzzy comprehensive evaluation method is widely used based on expert opinions. However, the subjective opinions or lack of experience of individual experts may lead to inaccurate evaluation results. Hence the accuracy of the results needs to be further improved. This paper presents a comprehensive approach to achieve this purpose by combining bow-tie model and cloud inference. The specific evaluation process is as follows: First, a bow-tie model composed of a fault tree and an event tree is established to graphically illustrate the probability and consequence indicators of pipeline failure. Second, the interval estimation method can be scored in the form of intervals to improve the accuracy of the results, and the censored mean algorithm is used to remove the maximum and minimum values of the score to improve the stability of the results. The golden section method is used to determine the weight of the indicators and reduce the subjectivity of index weights. Third, the failure probability and failure consequence scores of the pipeline are converted into three numerical features by using cloud inference. The cloud inference can better describe the ambiguity and volatility of the results which can better describe the volatility of the risk level. Finally, the cloud drop graphs of failure probability and failure consequences can be expressed, which intuitively and accurately illustrate the ambiguity and randomness of the results. A case study of a coal mine gob pipeline carrying natural gas has been investigated to validate the utility of the proposed method. The evaluation results of this case show that the probability of failure of the pipeline is very low, the consequences of failure are more serious, which is consistent with the reality.

Keywords: bow-tie model, natural gas pipeline, coal mine gob, cloud inference

Procedia PDF Downloads 221

Authors: Mehrzad Mohabbi Yadollahi, Ramazan Demirboğa, Majid Atashafrazeh

Abstract:

Geopolymers are highly complex materials which involve many variables which makes modeling its properties very difficult. There is no systematic approach in mix design for Geopolymers. Since the amounts of silica modulus, Na2O content, w/b ratios and curing time have a great influence on the compressive strength an ANFIS (Adaptive neuro fuzzy inference system) method has been established for predicting compressive strength of ground pumice based Geopolymers and the possibilities of ANFIS for predicting the compressive strength has been studied. Consequently, ANFIS can be used for geopolymer compressive strength prediction with acceptable accuracy.

Keywords: geopolymer, ANFIS, compressive strength, mix design

Procedia PDF Downloads 805

Authors: Emmy Pratiwi, Ketut B. Artana, A. A. B. Dinariyana

Abstract:

Madura Strait is considered as one of the busiest shipping channels in Indonesia. High vessel traffic density in Madura Strait gives serious threat due to navigational safety in this area, i.e. ship collision. This study is necessary as an attempt to enhance the safety of marine traffic. Fuzzy inference system (FIS) is proposed to calculate risk collision of ships. Collision risk is evaluated based on ship domain, Distance to Closest Point of Approach (DCPA), and Time to Closest Point of Approach (TCPA). Data were collected by utilizing Automatic Identification System (AIS). This study considers several ships’ domain models to give the characteristic of marine traffic in the waterways. Each encounter in the ship domain is analyzed to obtain the level of collision risk. Risk level of ships, as the result in this study, can be used as guidance to avoid the accident, providing brief description about safety traffic in Madura Strait and improving the navigational safety in the area.

Keywords: automatic identification system, collision risk, DCPA, fuzzy inference system, TCPA

Procedia PDF Downloads 517