5 papers · 1 filter
Can LLM Infer Risk Information From MCP Server System Logs?
Jiayi Fu, Yuansen Zhang, Yinggui Wang
Large Language Models (LLMs) demonstrate strong capabilities in solving complex tasks when integrated with external tools. The Model Context Protocol (MCP) has become a standard in…
CEE: An Inference-Time Jailbreak Defense for Embodied Intelligence via Subspace Concept Rotation
Jirui Yang, Zheyu Lin, Zhihui Lu +6
Large language models (LLMs) are widely used for task understanding and action planning in embodied intelligence (EI) systems, but their adoption substantially increases vulnerabil…
Ditto: Quantization-aware Secure Inference of Transformers upon MPC
Haoqi Wu, Wenjing Fang, Yancheng Zheng +4
Due to the rising privacy concerns on sensitive client data and trained models like Transformers, secure multi-party computation (MPC) techniques are employed to enable secure infe…
StegGuard: Fingerprinting Self-supervised Pre-trained Encoders via Secrets Embeder and Extractor
Xingdong Ren, Tianxing Zhang, Hanzhou Wu +3
In this work, we propose StegGuard, a novel fingerprinting mechanism to verify the ownership of the suspect pre-trained encoder using steganography. A critical perspective in StegG…
You Can Backdoor Personalized Federated Learning
Tiandi Ye, Cen Chen, Yinggui Wang +2
Existing research primarily focuses on backdoor attacks and defenses within the generic federated learning scenario, where all clients collaborate to train a single global model. A…