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

Machine learning-based malware detectors are increasingly vulnerable to adversarial examples. Traditional defenses, such as one-shot adversarial training, often fail against adaptive attackers who use reinforcement learning to bypass detection. This paper proposes a robust defense framework based...

Malicious code in test-mlw2-ceorl-mokes (npm)

The package test-mlw2-ceorl-mokes was found to contain malicious code...

Mokes and Buerak distributed under the guise of security certificates

The technique of distributing malware under the guise of legitimate software updates is not new. As a rule, cybercriminals invite potential victims to install a new version of a browser or Adobe Flash Player. However, we recently discovered a new approach to this well-known method: visitors to...