5 papers
EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability
Andrea Ponte, Daniel Gibert, Matous Kozak +5
Due to the lack of systematic evaluations, we are not yet able to determine which AI-based Windows malware detector to deploy in production, since existing evaluations (i) differ i…
Adversarial Co-Evolution of Malware and Detection Models: A Bilevel Optimization Perspective
Olha JureÄková, Martin JureÄek, MatouÅ¡ Kozák +1
Machine learning-based malware detectors are increasingly vulnerable to adversarial examples. Traditional defenses, such as one-shot adversarial training, often fail against adapti…
When Developer Aid Becomes Security Debt: A Systematic Analysis of Insecure Behaviors in LLM Coding Agents
Matous Kozak, Roshanak Zilouchian Moghaddam, Siva Sivaraman
LLM-based coding agents are rapidly being deployed in software development, yet their safety implications remain poorly understood. These agents, while capable of accelerating soft…
Updating Windows Malware Detectors: Balancing Robustness and Regression against Adversarial EXEmples
Matous Kozak, Luca Demetrio, Dmitrijs Trizna +1
Adversarial EXEmples are carefully-perturbed programs tailored to evade machine learning Windows malware detectors, with an ongoing effort to develop robust models able to address…
Effectiveness of Adversarial Benign and Malware Examples in Evasion and Poisoning Attacks
MatouÅ¡ Kozák, Martin JureÄek
Adversarial attacks present significant challenges for malware detection systems. This research investigates the effectiveness of benign and malicious adversarial examples (AEs) in…