7 papers
One Framework for All: Cross-Modal Membership Inference for Generative Models
Dayong Ye, Tainqing Zhu, Kun Gao +6
Large generative models across text-to-text, text-to-image, and image-to-text modalities have been shown to pose significant privacy risks. One fundamental threat is membership inf…
CSC: Turning the Adversary's Poison against Itself
Yuchen Shi, Xin Guo, Huajie Chen +3
Poisoning-based backdoor attacks pose significant threats to deep neural networks by embedding triggers in training data, causing models to misclassify triggered inputs as adversar…
Secure Forgetting: A Framework for Privacy-Driven Unlearning in Large Language Model (LLM)-Based Agents
Dayong Ye, Tainqing Zhu, Congcong Zhu +5
Large language model (LLM)-based agents have recently gained considerable attention due to the powerful reasoning capabilities of LLMs. Existing research predominantly focuses on e…
Poisoning the Pixels: Revisiting Backdoor Attacks on Semantic Segmentation
Guangsheng Zhang, Huan Tian, Leo Zhang +4
Semantic segmentation models are widely deployed in safety-critical applications such as autonomous driving, yet their vulnerability to backdoor attacks remains largely underexplor…
Character-Level Perturbations Disrupt LLM Watermarks
Zhaoxi Zhang, Xiaomei Zhang, Yanjun Zhang +5
Large Language Model (LLM) watermarking embeds detectable signals into generated text for copyright protection, misuse prevention, and content detection. While prior studies evalua…
Data Duplication: A Novel Multi-Purpose Attack Paradigm in Machine Unlearning
Dayong Ye, Tianqing Zhu, Jiayang Li +5
Duplication is a prevalent issue within datasets. Existing research has demonstrated that the presence of duplicated data in training datasets can significantly influence both mode…