4 papers
MMAligner: Safeguarding Multimodal Large Language Models through Representation Calibration
Shenyi Zhang, Keyan Guo, Zihao Wang +5
Multimodal large language models (MLLMs) often refuse unsafe text prompts yet generate harmful responses to semantically equivalent multimodal inputs. Existing defenses either rely…
Amulet: Fast TEE-Shielded Inference for On-Device Model Protection
Zikai Mao, Lingchen Zhao, Lei Xu +4
On-device machine learning (ML) introduces new security concerns about model privacy. Storing valuable trained ML models on user devices exposes them to potential extraction by adv…
Metadata-private Messaging without Coordination
Peipei Jiang, Yihao Wu, Lei Xu +6
For those seeking end-to-end private communication free from pervasive metadata tracking and censorship, the Tor network has been the de-facto choice in practice, despite its susce…
JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation
Shenyi Zhang, Yuchen Zhai, Keyan Guo +7
Despite the implementation of safety alignment strategies, large language models (LLMs) remain vulnerable to jailbreak attacks, which undermine these safety guardrails and pose sig…