相关论文: Extending the Metasploit Framework to Implement an…

Identifying threats in a network traffic flow which is encrypted is uniquely challenging. On one hand it is extremely difficult to simply decrypt the traffic due to modern encryption algorithms. On the other hand, passing such an encrypted…

Semantic segmentation models are widely deployed in safety-critical applications such as autonomous driving, yet their vulnerability to backdoor attacks remains largely underexplored. Prior segmentation backdoor studies transfer threat…

This paper presents ESCAPE, an informed moving target defense mechanism for cloud containers. ESCAPE models the interaction between attackers and their target containers as a "predator searching for a prey" search game. Live migration of…

Research has proven that end-to-end malware detectors are vulnerable to adversarial attacks. In response, the research community has proposed defenses based on randomized and (de)randomized smoothing. However, these techniques remain…

A system vulnerability analysis technique (SVAT) for complex mission critical systems (CMCS) was developed in response to the need to be able to conduct penetration testing on large industrial systems which cannot be taken offline or risk…

Malicious Python packages make software supply chains vulnerable by exploiting trust in open-source repositories like Python Package Index (PyPI). Lack of real-time behavioral monitoring makes metadata inspection and static code analysis…

We propose a symbolic execution method for analyzing the safety of software under fault attacks both accurately and efficiently. Fault attacks leverage physically injected hardware faults in an embedded system to break the safety of a…

The creation of a vulnerable node has been demonstrated through the analysis and implementation of the MS17-010 (CVE-2017-0144) vulnerability, affecting the SMBv1 protocol on various Windows operating systems. The principle and methodology…

Randomized smoothing is a powerful tool for certifying robustness to adversarial perturbations, including poisoning attacks via randomized training and evasion attacks via randomized inference. Extending these guarantees to backdoor…

Symbolic Execution is a formal method that can be used to verify the behavior of computer programs and detect software vulnerabilities. Compared to other testing methods such as fuzzing, Symbolic Execution has the advantage of providing…

Machine learning malware detectors are vulnerable to adversarial EXEmples, i.e., carefully-crafted Windows programs tailored to evade detection. Unlike other adversarial problems, attacks in this context must be functionality-preserving, a…

Malware analysis involves analyzing suspicious software to detect malicious payloads. Static malware analysis, which does not require software execution, relies increasingly on machine learning techniques to achieve scalability. Although…

Denial of service attacks (DoS) can cause significant financial damages. Flooding and Malicious packets are two kinds of DoS attacks. This paper presents a new security approach which stops malicious packets and prevents flooding in the…

Software vulnerabilities are commonly exploited as attack vectors in cyberattacks. Hence, it is crucial to identify vulnerable software configurations early to apply preventive measures. Effective vulnerability detection relies on…

Machine learning (ML) has demonstrated significant advancements in Android malware detection (AMD); however, the resilience of ML against realistic evasion attacks remains a major obstacle for AMD. One of the primary factors contributing to…

Public resources and services (e.g., datasets, training platforms, pre-trained models) have been widely adopted to ease the development of Deep Learning-based applications. However, if the third-party providers are untrusted, they can…

Vision-Language Models (VLMs) face significant safety vulnerabilities from malicious prompt attacks due to weakened alignment during visual integration. Existing defenses suffer from efficiency and robustness. To address these challenges,…

Emerging vulnerabilities in machine learning (ML) models due to adversarial attacks raise concerns about their reliability. Specifically, evasion attacks manipulate models by introducing precise perturbations to input data, causing…

Despite of the pervasive existence of multi-label evasion attack, it is an open yet essential problem to characterize the origin of the adversarial vulnerability of a multi-label learning system and assess its attackability. In this study,…

As machine learning models become increasingly deployed across the edge of internet of things environments, a partitioned deep learning paradigm in which models are split across multiple computational nodes introduces a new dimension of…