6 papers
DP-SelFT: Differentially Private Selective Fine-Tuning for Large Language Models
Haichao Sha, Zihao Wang, Yuncheng Wu +2
Large language models (LLMs) are commonly adapted to downstream tasks through fine-tuning, but fine-tuning data often contains sensitive information that may be leaked by the resul…
Rethinking Side-Channel Analysis: Automated Discovery and Analysis of Side-Channel Leakage with LLM-Assisted Agents
Zhen Xu, Zihao Wang, Yuhua Sun +1
Side-channel attacks exploit unintended information leakage from system behavior and continue to pose serious privacy risks in modern platforms. Despite extensive prior work, side-…
Misrouter: Exploiting Routing Mechanisms for Input-Only Attacks on Mixture-of-Experts LLMs
Zekun Fei, Zihao Wang, Weijie Liu +4
Mixture-of-Experts (MoE) architectures have emerged as a leading paradigm for scaling large language models through sparse, routing-based computation. However, this design introduc…
Hey, That's My Data! Token-Only Dataset Inference in Large Language Models
Chen Xiong, Zihao Wang, Rui Zhu +4
Large Language Models (LLMs) rely on massive training datasets, often including proprietary data, which raises concerns about unauthorized usage and copyright infringement. Existin…
LocalAlign: Enabling Generalizable Prompt Injection Defense via Generation of Near-Target Adversarial Examples for Alignment Training
Yuyang Gong, Zihao Wang, Jiawei Liu +1
Large language models are increasingly embedded into systems that interact with user data, retrieved web content, and external tools, creating a new attack surface: prompt injectio…
Trojans in Artificial Intelligence (TrojAI) Final Report
Kristopher W. Reese, Taylor Kulp-McDowall, Michael Majurski +68
The Intelligence Advanced Research Projects Activity (IARPA) launched the TrojAI program to confront an emerging vulnerability in modern artificial intelligence: the threat of AI T…