Chronic Poisoning against Machine Learning Based IDSs Using Edge Pattern Detection

Pan, Li; Liu, Qiang; Zhao, Wentao; Wang, Dongxu; Wang, Siqi

doi:10.1109/icc.2018.8422328

Cited by 13 publications

(16 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The dataset can also be periodically updated to better resemble the modifications of the network environment, or to include malicious samples of novel attack variants. The updated version will then be used to re-train the model accordingly [54].…”

Section: Analysis and Classificationmentioning

confidence: 99%

Modeling Realistic Adversarial Attacks against Network Intrusion Detection Systems

et al. 2022

View full text Add to dashboard Cite

The incremental diffusion of machine learning algorithms in supporting cybersecurity is creating novel defensive opportunities but also new types of risks. Multiple researches have shown that machine learning methods are vulnerable to adversarial attacks that create tiny perturbations aimed at decreasing the effectiveness of detecting threats. We observe that existing literature assumes threat models that are inappropriate for realistic cybersecurity scenarios because they consider opponents with complete knowledge about the cyber detector or that can freely interact with the target systems. By focusing on Network Intrusion Detection Systems based on machine learning methods, we identify and model the real capabilities and circumstances that are necessary for an attacker to carry out a feasible and successful adversarial attack. We then apply our model to several adversarial attacks proposed in literature and highlight the limits and merits that can result in actual adversarial attacks. The contributions of this paper can help hardening defensive systems by letting cyber defenders address the most critical and real issues, and can benefit researchers by allowing them to devise novel forms of adversarial attacks based on realistic threat models.

show abstract

Section: Analysis and Classificationmentioning

confidence: 99%

Modeling Realistic Adversarial Attacks against Network Intrusion Detection Systems

et al. 2022

View full text Add to dashboard Cite

show abstract

“…This method is simple and effective [14], however, it focus on binary classification problems, which is not generic to other learning algorithms. Li et al [15] use the Edge Pattern Detection (EPD) algorithm to design poisoning attack, named chronic poisoning attack, on machine learning based intrusion detection systems (IDS). The method can poison several learning algorithms including SVM, LR and NB [15].…”

Section: ) Poisoning Attacks Targeting Non-nn Modelsmentioning

confidence: 99%

“…Li et al [15] use the Edge Pattern Detection (EPD) algorithm to design poisoning attack, named chronic poisoning attack, on machine learning based intrusion detection systems (IDS). The method can poison several learning algorithms including SVM, LR and NB [15]. However, the method in [15] uses a long-term slow poisoning procedure and is complicated to implement.…”

Section: ) Poisoning Attacks Targeting Non-nn Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Security: Threats, Countermeasures, and Evaluations

Xue

Yuan

Wu³

et al. 2020

IEEE Access

126

View full text Add to dashboard Cite

Machine learning has been pervasively used in a wide range of applications due to its technical breakthroughs in recent years. It has demonstrated significant success in dealing with various complex problems, and shows capabilities close to humans or even beyond humans. However, recent studies show that machine learning models are vulnerable to various attacks, which will compromise the security of the models themselves and the application systems. Moreover, such attacks are stealthy due to the unexplained nature of the deep learning models. In this survey, we systematically analyze the security issues of machine learning, focusing on existing attacks on machine learning systems, corresponding defenses or secure learning techniques, and security evaluation methods. Instead of focusing on one stage or one type of attack, this paper covers all the aspects of machine learning security from the training phase to the test phase. First, the machine learning model in the presence of adversaries is presented, and the reasons why machine learning can be attacked are analyzed. Then, the machine learning security-related issues are classified into five categories: training set poisoning; backdoors in the training set; adversarial example attacks; model theft; recovery of sensitive training data. The threat models, attack approaches, and defense techniques are analyzed systematically. To demonstrate that these threats are real concerns in the physical world, we also reviewed the attacks in real-world conditions. Several suggestions on security evaluations of machine learning systems are also provided. Last, future directions for machine learning security are also presented. INDEX TERMS Artificial intelligence security, poisoning attacks, backdoor attacks, adversarial examples, privacy-preserving machine learning.

show abstract

“…As artificial intelligence is becoming a national strategy in more and more countries, machine learning, which can be divided into supervised learning [1], Semi-supervised learning [2] and unsupervised learning [3], is concerned as the most important method in data science. But machine learning methods are vulnerable to a variety of disturbances [4], such as poisoning [5]- [7], evasion [8], and impersonation [9]. Most of these disturbances introduce adversarial samples, which leverage the vulnerability of machine learning models to achieve malicious goals.…”

Section: Introductionmentioning

confidence: 99%

Model Capacity Vulnerability in Hyper-Parameters Estimation

Zhao

Liu

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Machine learning models are vulnerable to a variety of data perturbation. Recent research mainly focuses on the vulnerability of model training and proposes various model-oriented defense methods to achieve robust machine learning. However, most of the existing research overlooks the vulnerability of model capacity, which is more fundamental for model performance. In this paper, we study an adversarial vulnerability of model capacity caused by the poisoning on the estimation of model hyper-parameters. We further implement this vulnerability catering for the polynomial regression model, on which the evading of model-oriented detection is challenging, to illustrate the effectiveness of the adversarial vulnerability. Extensive experiments on one synthetic and three real-world data sets demonstrate that the vulnerability can effectively mislead the hyper-parameter estimation of the polynomial regression model by poisoning a few numbers of camouflage samples that cannot be detected by model-oriented defense methods. INDEX TERMS Adversarial vulnerability, model capacity, hyper-parameter poisoning, gradient-based optimization.

show abstract

Chronic Poisoning against Machine Learning Based IDSs Using Edge Pattern Detection

Cited by 13 publications

References 11 publications

Modeling Realistic Adversarial Attacks against Network Intrusion Detection Systems

Modeling Realistic Adversarial Attacks against Network Intrusion Detection Systems

Machine Learning Security: Threats, Countermeasures, and Evaluations

Model Capacity Vulnerability in Hyper-Parameters Estimation

Contact Info

Product

Resources

About