1,153 Hits in 4.0 sec

Investigating Resistance of Deep Learning-based IDS against Adversaries using min-max Optimization [article]

Rana Abou Khamis, Omair Shafiq, Ashraf Matrawy
2019 arXiv   pre-print
In this paper, we study the resilience of deep learning-based intrusion detection systems against adversarial attacks.  ...  With the growth of adversarial attacks against machine learning models, several concerns have emerged about potential vulnerabilities in designing deep neural network-based intrusion detection systems  ...  BACKGROUND An intrusion detection system (IDS) is a key component in network systems to monitor and analyze real-time network activities for any symptoms of suspicious, anomalous activities and issue alerts  ... 
arXiv:1910.14107v1 fatcat:evhwk4ismvazfkj565ocatciuy

Adversarial Machine Learning In Network Intrusion Detection Domain: A Systematic Review [article]

Huda Ali Alatwi, Charles Morisset
2021 arXiv   pre-print
models against such attacks.  ...  Due to their massive success in various domains, deep learning techniques are increasingly used to design network intrusion detection solutions that detect and mitigate unknown and known attacks with high  ...  [61] proposed Evaluating Network Intrusion Detection System (ENIDS) framework to assess the robustness of ML-based NIDS against AEs.  ... 
arXiv:2112.03315v1 fatcat:3j2jwdsh6zfy7bwoudfutqp2u4

IDSGAN: Generative Adversarial Networks for Attack Generation against Intrusion Detection [article]

Zilong Lin, Yong Shi, Zhi Xue
2021 arXiv   pre-print
Given that the internal structure of the detection system is unknown to attackers, the adversarial attack examples perform the black-box attacks against the detection system.  ...  In this paper, a framework of the generative adversarial networks, called IDSGAN, is proposed to generate the adversarial malicious traffic records aiming to attack intrusion detection systems by deceiving  ...  Introduction With the spread of security threats in the internet, the intrusion detection system (IDS) becomes the essential tools to detect and defend network attacks which are performed in the form of  ... 
arXiv:1809.02077v4 fatcat:dzk23tpr7jexjgzlrgh5y5lipe

Fooling intrusion detection systems using adversarially autoencoder

Junjun Chen, Di Wu, Ying Zhao, Nabin Sharma, Michael Blumenstein, Shui Yu
2020 Digital Communications and Networks  
Consequently, various Intrusion Detection Systems (IDSs) and network traffic classification systems based on Machine Learning (ML) or Deep Learning (DL) techniques have been proposed to detect anomaly  ...  In our future work, we have a significant interest in defending against this type of attack. Moreover, we will research the evasion attacks based on the semantical level information.  ... 
doi:10.1016/j.dcan.2020.11.001 fatcat:xp6tctcxqrhstk7ptymxee46cu

The Threat of Adversarial Attacks on Machine Learning in Network Security – A Survey [article]

Olakunle Ibitoye, Rana Abou-Khamis, Ashraf Matrawy, M. Omair Shafiq
2020 arXiv   pre-print
This is because machine learning applications in network security such as malware detection, intrusion detection, and spam filtering are by themselves adversarial in nature.  ...  In what could be considered an arms race between attackers and defenders, adversaries constantly probe machine learning systems with inputs which are explicitly designed to bypass the system and induce  ...  Adversarial attacks against Network Anomaly Detection 1) IDSGAN: IDSGAN was proposed by Lin et al. [114] for generating adversarial attacks targeted towards intrusion detection systems.  ... 
arXiv:1911.02621v2 fatcat:p7mgj65wavee3op6as5lufwj3q

Adversarial attacks against intrusion detection systems: Taxonomy, solutions and open issues

Igino Corona, Giorgio Giacinto, Fabio Roli
2013 Information Sciences  
Intrusion Detection Systems (IDSs) are one of the key components for securing computing infrastructures. Their objective is to protect against attempts to violate defense mechanisms.  ...  To the best of our knowledge, this survey is the first work to present an overview on adversarial attacks against IDSs.  ...  module of the network sensor (this may be due to an evasion attack against the network sensor).  ... 
doi:10.1016/j.ins.2013.03.022 fatcat:gjmx55wlkbhq5cfmjcx5nh523e

Adversarial Machine Learning for Cybersecurity and Computer Vision: Current Developments and Challenges [article]

Bowei Xi
2021 arXiv   pre-print
against machine learning techniques -- poisoning attacks, evasion attacks, and privacy attacks.  ...  For example, deep neural networks fail to correctly classify adversarial images, which are generated by adding imperceptible perturbations to clean images.We first discuss three main categories of attacks  ...  Poisoning attack is one of the six attack categories against intrusion detection systems, as discussed in (Corona et al., 2013) .  ... 
arXiv:2107.02894v1 fatcat:ir7vzxh3wfaddcmgezqtyxu7iy

Fixed Points in Cyber Space: Rethinking Optimal Evasion Attacks in the Age of AI-NIDS [article]

Christian Schroeder de Witt, Yongchao Huang, Philip H.S. Torr, Martin Strohmeier
2021 arXiv   pre-print
Working within the threat model of Locked Shields, Europe's largest cyberdefense exercise, we study blackbox adversarial attacks on network classifiers.  ...  Given already existing attack capabilities, we question the utility of optimal evasion attack frameworks based on minimal evasion distances.  ...  The use of semi-automated network intrusion detection systems using machine learning technology (ML-NIDS) reduces the workload on human network operators.  ... 
arXiv:2111.12197v1 fatcat:gqo27ytqizcdrfsbiicfsba37m

A Study on Advanced Persistent Threats [chapter]

Ping Chen, Lieven Desmet, Christophe Huygens
2014 Lecture Notes in Computer Science  
APTs are cyber attacks executed by sophisticated and well-resourced adversaries targeting specific information in high-profile companies and governments, usually in a long term campaign involving different  ...  In this paper, we present the results of a comprehensive study on APT, characterizing its distinguishing characteristics and attack model, and analyzing techniques commonly seen in APT attacks.  ...  With the financial support from the Prevention of and Fight against Crime Programme of the European Union (B-CCENTRE).  ... 
doi:10.1007/978-3-662-44885-4_5 fatcat:f3jws7xf2vhi5omqoiy5hp3jf4

Omni: Automated Ensemble with Unexpected Models against Adversarial Evasion Attack [article]

Rui Shu, Tianpei Xia, Laurie Williams, Tim Menzies
2021 arXiv   pre-print
Machine learning-based security detection models have become prevalent in modern malware and intrusion detection systems.  ...  Once the attackers can fool a classifier to think that a malicious input is actually benign, they can render a machine learning-based malware or intrusion detection system ineffective.  ...  Here we conclude: A well-designed weighted ensemble system is a promising approach to defend against adversarial evasion attack. and When using ensemble learning as a defense method against adversarial  ... 
arXiv:2011.12720v2 fatcat:g755b3q2lnem7irwin5o2kh67i

Machine learning in adversarial environments

Pavel Laskov, Richard Lippmann
2010 Machine Learning  
or or corrupted features, demonstrate the ability of modern polymorphic engines to rewrite malware so it evades detection by current intrusion detection and antivirus systems, and provide approaches to  ...  This special issue highlights papers that span many disciplines including email spam detection, computer intrusion detection, and detection of web pages deliberately designed to manipulate the priorities  ...  modeled by the simple generative approach (i.e. attack signatures) used in many common intrusion detection and antivirus tools.  ... 
doi:10.1007/s10994-010-5207-6 fatcat:653z5mltdffnjf6kumh6ss4g4a

Adversarial machine learning

Ling Huang, Anthony D. Joseph, Blaine Nelson, Benjamin I.P. Rubinstein, J. D. Tygar
2011 Proceedings of the 4th ACM workshop on Security and artificial intelligence - AISec '11  
attacks; introduce the evasion challenge; and discuss privacy-preserving learning techniques.  ...  In this paper (expanded from an invited talk at AISEC 2010), we discuss an emerging field of study: adversarial machine learning-the study of effective machine learning techniques against an adversarial  ...  Shing-hon Lau, Steven Lee, Satish Rao, Udam Saini, Russell Sears, Charles Sutton, Nina Taft, Anthony Tran, and Kai Xia for many fruitful discussions and collaborations that have influenced our thinking about adversarial  ... 
doi:10.1145/2046684.2046692 dblp:conf/ccs/HuangJNRT11 fatcat:d6wcto4tmvbbrec35cjdengxby

Adversarial Machine Learning

J.D. Tygar
2011 IEEE Internet Computing  
attacks; introduce the evasion challenge; and discuss privacy-preserving learning techniques.  ...  In this paper (expanded from an invited talk at AISEC 2010), we discuss an emerging field of study: adversarial machine learning-the study of effective machine learning techniques against an adversarial  ...  Shing-hon Lau, Steven Lee, Satish Rao, Udam Saini, Russell Sears, Charles Sutton, Nina Taft, Anthony Tran, and Kai Xia for many fruitful discussions and collaborations that have influenced our thinking about adversarial  ... 
doi:10.1109/mic.2011.112 fatcat:wb3bt4r67zd4teikanwo6nfzba

Adversarial Machine Learning applied to Intrusion and Malware Scenarios: a systematic review

Nuno Martins, Jose Magalhaes Cruz, Tiago Cruz, Pedro Henriques Abreu
2020 IEEE Access  
Cyber-security is the practice of protecting computing systems and networks from digital attacks, which are a rising concern in the Information Age.  ...  INDEX TERMS Cybersecurity, adversarial machine learning, intrusion detection, malware detection.  ...  The growth of IoT environments in the recent years poses as a potential source for generating new test beds for intrusion detection; • Performing live attacks against time based intrusion detection systems  ... 
doi:10.1109/access.2020.2974752 fatcat:fbw4gbtyqrf7pgwduqunakxrx4

Adversarial Training Against Adversarial Attacks for Machine Learning-Based Intrusion Detection Systems

Muhammad Shahzad Haroon, Husnain Mansoor Ali
2022 Computers Materials & Continua  
Intrusion detection system plays an important role in defending networks from security breaches.  ...  End-to-end machine learning-based intrusion detection systems are being used to achieve high detection accuracy.  ...  Standardized Euclidean distance and information entropy is used to assess generative adversarial network (GAN) The authors in [13] demonstrated the adversarial attack and two defence methods.  ... 
doi:10.32604/cmc.2022.029858 fatcat:obzu3jvfqrfmtnnoxrownuwape
« Previous Showing results 1 — 15 out of 1,153 results