Showing cs.CRShow all
2 papers · 1 filter
cs.CR2025
Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift
Shuai Yuan, Zhibo Zhang, Yuxi Li +2
The widespread distribution of Large Language Models (LLMs) through public platforms like Hugging Face introduces significant security challenges. While these platforms perform bas…
cs.CR2025
Where the Devil Hides: Deepfake Detectors Can No Longer Be Trusted
Shuaiwei Yuan, Junyu Dong, Yuezun Li
With the advancement of AI generative techniques, Deepfake faces have become incredibly realistic and nearly indistinguishable to the human eye. To counter this, Deepfake detectors…