6 papers
Defending Unauthorized Model Merging via Dual-Stage Weight Protection
Wei-Jia Chen, Min-Yen Tsai, Cheng-Yi Lee +1
The rapid proliferation of pretrained models and open repositories has made model merging a convenient yet risky practice, allowing free-riders to combine fine-tuned models into a…
IU: Imperceptible Universal Backdoor Attack
Hsin Lin, Yan-Lun Chen, Ren-Hung Hwang +1
Backdoor attacks pose a critical threat to the security of deep neural networks, yet existing efforts on universal backdoors often rely on visually salient patterns, making them ea…
BadVim: Unveiling Backdoor Threats in Visual State Space Model
Cheng-Yi Lee, Yu-Hsuan Chiang, Zhong-You Wu +2
Visual State Space Models (VSSM) have shown remarkable performance in various computer vision tasks. However, backdoor attacks pose significant security challenges, causing comprom…
Safety Alignment Depth in Large Language Models: A Markov Chain Perspective
Ching-Chia Kao, Chia-Mu Yu, Chun-Shien Lu +1
Large Language Models (LLMs) are increasingly adopted in high-stakes scenarios, yet their safety mechanisms often remain fragile. Simple jailbreak prompts or even benign fine-tunin…
The Great Contradiction Showdown: How Jailbreak and Stealth Wrestle in Vision-Language Models?
Ching-Chia Kao, Chia-Mu Yu, Chun-Shien Lu +1
Vision-Language Models (VLMs) have achieved remarkable performance on a variety of tasks, yet they remain vulnerable to jailbreak attacks that compromise safety and reliability. In…
Defending Against Repetitive Backdoor Attacks on Semi-supervised Learning through Lens of Rate-Distortion-Perception Trade-off
Cheng-Yi Lee, Ching-Chia Kao, Cheng-Han Yeh +3
Semi-supervised learning (SSL) has achieved remarkable performance with a small fraction of labeled data by leveraging vast amounts of unlabeled data from the Internet. However, th…