Showing cs.CRShow all
3 papers · 1 filter
cs.CR2026
Intent-Hiding Jailbreaks: An Information-Theoretic Framework for Compositional Attacks
Fengwei Tian, Ravi Tandon
Recent work has shown that large language models (LLMs) can be vulnerable to jailbreak attacks in which harmful intent is obscured through composition with benign tasks. A harmful…
cs.CR2025
Learning to Diagnose Privately: DP-Powered LLMs for Radiology Report Classification
Payel Bhattacharjee, Fengwei Tian, Geoffrey D. Rubin +5
Large Language Models (LLMs) are increasingly adopted across domains such as education, healthcare, and finance. In healthcare, LLMs support tasks including disease diagnosis, abno…
cs.CR2024
Inference Privacy: Properties and Mechanisms
Fengwei Tian, Ravi Tandon
Ensuring privacy during inference stage is crucial to prevent malicious third parties from reconstructing users' private inputs from outputs of public models. Despite a large body…