3 papers
cs.CV2026
VidDoS: Universal Denial-of-Service Attack on Video-based Large Language Models
Duoxun Tang, Dasen Dai, Jiyao Wang +3
Video-LLMs are increasingly deployed in safety-critical applications but are vulnerable to Energy-Latency Attacks (ELAs) that exhaust computational resources. Current image-centric…
cs.CL2025
Heaven-Sent or Hell-Bent? Benchmarking the Intelligence and Defectiveness of LLM Hallucinations
Chengxu Yang, Jingling Yuan, Siqi Cai +2
Hallucinations in large language models (LLMs) are commonly regarded as errors to be minimized. However, recent perspectives suggest that some hallucinations may encode creative or…
cs.LG2025
Mjolnir: Breaking the Shield of Perturbation-Protected Gradients via Adaptive Diffusion
Xuan Liu, Siqi Cai, Qihua Zhou +3
Perturbation-based mechanisms, such as differential privacy, mitigate gradient leakage attacks by introducing noise into the gradients, thereby preventing attackers from reconstruc…