IU: Imperceptible Universal Backdoor Attack

Backdoor attacks pose a critical threat to the security of deep neural networks, yet existing efforts on universal backdoors often rely on visually salient patterns, making them easier to detect and less practical at scale. In this work, we introduce a novel imperceptible universal backdoor attac...

EUVD-2005-4782

Malware in sbrugna...

Identifying and Understanding Cross-Class Features in Adversarial Training

Adversarial training AT has been considered one of the most effective methods for making deep neural networks robust against adversarial attacks, while the training mechanisms and dynamics of AT remain open research problems. In this paper, we present a novel perspective on studying AT through th...

SUSE CVE-2005-4789

resmgr in SUSE Linux 9.2 and 9.3, and possibly other distributions, does not properly enforce class-specific exclude rules in some situations, which allows local users to bypass intended access restrictions for USB devices that set their class ID at the interface level...

CVE-2005-4789

resmgr in SUSE Linux 9.2 and 9.3, and possibly other distributions, does not properly enforce class-specific exclude rules in some situations, which allows local users to bypass intended access restrictions for USB devices that set their class ID at the interface level...