paper-with-me

Papers

Security Theater: On the Vulnerability of Classifiers to Exploratory Attacks

2018-03-24 · Tegjyot Singh Sethi, Mehmed Kantardzic, Joung Woo Ryu

The increasing scale and sophistication of cyberattacks has led to the adoption of machine learning based classification techniques, at the core of cybersecurity systems. These techniques promise scale and accuracy, which traditional rule or signature based methods cannot. However, classifiers operating in adversarial domains are vulnerable to evasion attacks by an adversary, who is capable of learning the behavior of the system by employing intelligently crafted probes. Classification accuracy in such domains provides a false sense of security, as detection can easily be evaded by carefully perturbing the input samples. In this paper, a generic data driven framework is presented, to analyze the vulnerability of classification systems to black box probing based attacks. The framework uses an exploration exploitation based strategy, to understand an adversary's point of view of the attack defense cycle. The adversary assumes a black box model of the defender's classifier and can launch indiscriminate attacks on it, without information of the defender's model type, training data or the domain of application. Experimental evaluation on 10 real world datasets demonstrates that even models having high perceived accuracy (>90%), by a defender, can be effectively circumvented with a high evasion rate (>95%, on average). The detailed attack algorithms, adversarial model and empirical evaluation, serve.

📄 PDF Abstract BibTeX arXiv:1803.09163

Code (0)

등록된 구현이 없습니다.

Tasks

General Classification

Similar Papers 제목 키워드 기반

Data Driven Exploratory Attacks on Black Box Classifiers in Adversarial Domains

2017-03-23 · Tegjyot Singh Sethi, Mehmed Kantardzic

While modern day web applications aim to create impact at the civilization level, they have become vulnerable to adversarial activity, where the next cyber-attack can take any shape and can originate from anywhere. The i…

BIG-bench Machine Learning

On Security and Sparsity of Linear Classifiers for Adversarial Settings

2017-08-31 · Ambra Demontis, Paolo Russu, Battista Biggio, Giorgio Fumera 외

Machine-learning techniques are widely used in security-related applications, like spam and malware detection. However, in such settings, they have been shown to be vulnerable to adversarial attacks, including the delibe…

Malware Detection

Beyond Gradient-Based Attacks: Adversarial Robustness and Explainability Stability in Cybersecurity Classifiers

2026-07-02 · Mona Rajhans, Vishal Khawarey arxiv

Adversarial attacks on cybersecurity classifiers pose a dual threat: degrading predictions and destabilising the SHAP-based explanations that security analysts rely on to understand and triage alerts. We extend our prior…

Adversarial Robustness

A Dynamic-Adversarial Mining Approach to the Security of Machine Learning

2018-03-24 · Tegjyot Singh Sethi, Mehmed Kantardzic, Lingyu Lyua, Jiashun Chen

Operating in a dynamic real world environment requires a forward thinking and adversarial aware design for classifiers, beyond fitting the model to the training data. In such scenarios, it is necessary to make classifier…

BIG-bench Machine LearningDrift DetectionFeature ImportanceOne-class classifier

Targeted Bit-Flip Attacks on LLM-Based Agents

2026-03-07 · Jialai Wang, Ya Wen, Zhongmou Liu, Yuxiao Wu 외 arxiv

Targeted bit-flip attacks (BFAs) exploit hardware faults to manipulate model parameters, posing a significant security threat. While prior work targets single-step inference models (e.g., image classifiers), LLM-based ag…