8 papers
Cordyceps: Covert Control Attacks on LLMs via Data Poisoning
Zedian Shao, Charles Fleming, Teodora Baluta
Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison. Existing poisoning attacks primarily rely on fixed trigger phrases that de…
Context-Fractured Decomposition Attacks on Tool-Using LLM Agents: Exploiting Artifact Provenance Gaps
Xiaofeng Lin, Yukai Yang, Daniel Guo +3
Tool-using LLM agents interact with the world through actions that persist state in artifacts (e.g., workspace files or logs). Consequently, jailbreak defenses must reason about cr…
REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent Traces
Xiaofeng Lin, Yingxu Wang, Tung Sum Thomas Kwok +4
Large language model (LLM) agents now solve complex tasks through long plan-and-execution traces, yet the ability to locate errors in a completed traces still lags far behind, espe…
ReTabSyn: Realistic Tabular Data Synthesis via Reinforcement Learning
Xiaofeng Lin, Seungbae Kim, Zhuoya Li +3
Deep generative models can help with data scarcity and privacy by producing synthetic training data, but they struggle in low-data, imbalanced tabular settings to fully learn the c…
SARA: Stress Test Reasoning in Audio Deepfake Detection
Binh Nguyen, Charles Fleming, Thai Le
Audio Language Models (ALMs) offer a promising shift towards explainable audio deepfake detections (ADD), moving beyond \textit{black-box} classifiers by providing transparency to…
Retracing the Past: LLMs Emit Training Data When They Get Lost
Myeongseob Ko, Nikhil Reddy Billa, Adam Nguyen +3
The memorization of training data in large language models (LLMs) poses significant privacy and copyright concerns. Existing data extraction methods, particularly heuristic-based d…