2 papers
cs.CR2026
CacheTrap: Unveiling a Stealthier Gray-Box Trojan against LLMs
Mohaiminul Al Nahian, Abeer Matar A. Almalky, Gamana Aragonda +6
The rapid advancement of large language models (LLMs) has sparked growing interest in understanding their security vulnerabilities, particularly Trojan attacks that enable stealthy…
cs.CR2025
ShadowScope: GPU Monitoring and Validation via Composable Side Channel Signals
Ghadeer Almusaddar, Yicheng Zhang, Saber Ganjisaffar +4
As modern systems increasingly rely on GPUs for computationally intensive tasks such as machine learning acceleration, ensuring the integrity of GPU computation has become critical…