collaborators

5 papers

cs.CR2026

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…

cs.CR2026

Adversarial Co-Evolution of Malware and Detection Models: A Bilevel Optimization Perspective

Olha Jurečková, Martin Jureček, Matouš 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…

cs.AI2025

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…

cs.CR2025

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…

cs.CR2025

Effectiveness of Adversarial Benign and Malware Examples in Evasion and Poisoning Attacks

Matouš Kozák, Martin Jureček

Adversarial attacks present significant challenges for malware detection systems. This research investigates the effectiveness of benign and malicious adversarial examples (AEs) in…