Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs
Yifei Wang, Tianlin Li, Xiaohan Zhang +3
Inference optimization aims to minimize the latency and resource consumption of LLM inference while preserving output quality, making large-scale deployment practical and cost-effe…
cs.CR2025
TokenProber: Jailbreaking Text-to-image Models via Fine-grained Word Impact Analysis
Longtian Wang, Xiaofei Xie, Tianlin Li +2
Text-to-image (T2I) models have significantly advanced in producing high-quality images. However, such models have the ability to generate images containing not-safe-for-work (NSFW…