Dive into the world of reinforcement learning and model extraction within the cybersecurity realm,

Explore how the MEME algorithm compares with state-of-the-art techniques in generating evasive malware across diverse detection systems.

Discover how minimal knowledge PT-AE attacks redefine black-box speaker recognition

Discover how minimal knowledge PT-AE attacks redefine black-box speaker recognition

Dive into the realm of audio attacks, from white-box to black-box strategies, exploring query-based and transfer-based approaches

Explore the effectiveness of PT-AE attacks in real-world settings through comprehensive experimental evaluations of digital-line and over-the-air methods.

Discover optimized PT-AE attacks on black-box models using advanced environmental sound carriers and feature-twisting techniques for higher TPR.

Analyzing the effectiveness of PT-AEs compared to GT-AEs in audio attacks, focusing on transferability, human perception, and TPR.

Evaluate parrot speech synthesis methods, including one-shot VC, for effective parrot training and compare performance with ground-truth models.

Explore how parrot training enhances black-box audio adversarial attacks on speaker recognition systems with minimal knowledge and no probing required.

Innovative parrot training boosts black-box attack success on speaker recognition systems.