2 citations · 5 across the 33 of their papers we have counts for
5 papers · 1 filter
Defending Jailbreak Attacks on Large Language Models via Manifold Trajectory Kinetics
Hangtao Zhang, Yucheng Zhao, Sishun Liu +8
Jailbreak prompts can bypass alignment guardrails in large language models (LLMs) and elicit unsafe outputs, making reliable deployment-time detection critical. Prior detection app…
UnlearnShield: Shielding Forgotten Privacy against Unlearning Inversion
Lulu Xue, Shengshan Hu, Wei Lu +6
Machine unlearning is an emerging technique that aims to remove the influence of specific data from trained models, thereby enhancing privacy protection. However, recent research h…
MARS: A Malignity-Aware Backdoor Defense in Federated Learning
Wei Wan, Yuxuan Ning, Zhicong Huang +7
Federated Learning (FL) is a distributed paradigm aimed at protecting participant data privacy by exchanging model parameters to achieve high-quality model training. However, this…
Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM
Lei Yu, Yechao Zhang, Ziqi Zhou +6
With the rapid development of the Vision-Language Model (VLM), significant progress has been made in Visual Question Answering (VQA) tasks. However, existing VLM often generate ina…
Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks
Lulu Xue, Shengshan Hu, Ruizhi Zhao +4
Collaborative learning (CL) is a distributed learning framework that aims to protect user privacy by allowing users to jointly train a model by sharing their gradient updates only.…