7 papers
ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety
Kun Wang, Cheng Qian, Miao Yu +6
Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threatened by critical safety vulnera…
SafeSeek: Universal Attribution of Safety Circuits in Language Models
Miao Yu, Siyuan Fu, Moayad Aloqaily +6
Mechanistic interpretability reveals that safety-critical behaviors (e.g., alignment, jailbreak, backdoor) in Large Language Models (LLMs) are grounded in specialized functional co…
STEP: Detecting Audio Backdoor Attacks via Stability-based Trigger Exposure Profiling
Kun Wang, Meng Chen, Junhao Wang +6
With the widespread deployment of deep-learning-based speech models in security-critical applications, backdoor attacks have emerged as a serious threat: an adversary who poisons a…
TINA: Text-Free Inversion Attack for Unlearned Text-to-Image Diffusion Models
Qianlong Xiang, Miao Zhang, Haoyu Zhang +3
Although text-to-image diffusion models exhibit remarkable generative power, concept erasure techniques are essential for their safe deployment to prevent the creation of harmful c…
HearSay Benchmark: Do Audio LLMs Leak What They Hear?
Jin Wang, Liang Lin, Kaiwen Luo +8
While Audio Large Language Models (ALLMs) have achieved remarkable progress in understanding and generation, their potential privacy implications remain largely unexplored. This pa…
Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models
Miao Yu, Zhenhong Zhou, Moayad Aloqaily +5
Fine-tuned Large Language Models (LLMs) are vulnerable to backdoor attacks through data poisoning, yet the internal mechanisms governing these attacks remain a black box. Previous…