6 papers
ICL-EVADER: Zero-Query Black-Box Evasion Attacks on In-Context Learning and Their Defenses
Ningyuan He, Ronghong Huang, Qianqian Tang +3
In-context learning (ICL) has become a powerful, data-efficient paradigm for text classification using large language models. However, its robustness against realistic adversarial…
VidLeaks: Membership Inference Attacks Against Text-to-Video Models
Li Wang, Wenyu Chen, Ning Yu +2
The proliferation of powerful Text-to-Video (T2V) models, trained on massive web-scale datasets, raises urgent concerns about copyright and privacy violations. Membership inference…
DCMI: A Differential Calibration Membership Inference Attack Against Retrieval-Augmented Generation
Xinyu Gao, Xiangtao Meng, Yingkai Dong +2
While Retrieval-Augmented Generation (RAG) effectively reduces hallucinations by integrating external knowledge bases, it introduces vulnerabilities to membership inference attacks…
Beyond the Safety Tax: Mitigating Unsafe Text-to-Image Generation via External Safety Rectification
Xiangtao Meng, Yingkai Dong, Ning Yu +3
Text-to-image (T2I) generative models have achieved remarkable visual fidelity, yet remain vulnerable to generating unsafe content. Existing safety defenses typically intervene int…
FaceSwapGuard: Safeguarding Facial Privacy from DeepFake Threats through Identity Obfuscation
Li Wang, Zheng Li, Xuhong Zhang +2
DeepFakes pose a significant threat to our society. One representative DeepFake application is face-swapping, which replaces the identity in a facial image with that of a victim. A…
Beyond Known Fakes: Generalized Detection of AI-Generated Images via Post-hoc Distribution Alignment
Li Wang, Wenyu Chen, Xiangtao Meng +2
The rapid proliferation of highly realistic AI-generated images poses serious security threats such as misinformation and identity fraud. Detecting generated images in open-world s…