4 papers
Rethinking Forgery Attacks on Semantic Watermarks in Black-Box Settings: A Geometric Distortion Perspective
Cheng-Yi Lee, Yichi Zhang, Yuchen Yang +2
Recent studies have shown that semantic watermarks, which embed information into the initial noise of latent diffusion models (LDMs), are vulnerable to black-box forgery attacks. H…
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…
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…
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…