4 papers
Model Poisoning Attacks to Federated Learning via Multi-Round Consistency
Yueqi Xie, Minghong Fang, Neil Zhenqiang Gong
Model poisoning attacks are critical security threats to Federated Learning (FL). Existing model poisoning attacks suffer from two key limitations: 1) they achieve suboptimal effec…
Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models
Jingwei Yi, Yueqi Xie, Bin Zhu +4
The integration of large language models with external content has enabled applications such as Microsoft Copilot but also introduced vulnerabilities to indirect prompt injection a…
MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance
Renjie Pi, Tianyang Han, Jianshu Zhang +6
The deployment of multimodal large language models (MLLMs) has brought forth a unique vulnerability: susceptibility to malicious attacks through visual inputs. This paper investiga…
GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis
Yueqi Xie, Minghong Fang, Renjie Pi +1
Large Language Models (LLMs) face threats from jailbreak prompts. Existing methods for detecting jailbreak prompts are primarily online moderation APIs or finetuned LLMs. These str…