9 papers
Environment Steering: Using Data Flow Control to Improve Agent Utility and Safety
Charlie Summers, Prajwal Raghunath, Aaditya Pai +4
LLM agents can make unsafe tool calls even when instructed to behave safely. Existing defenses constrain agents before execution, modify tool inputs/outputs, or rely on LLM judges;…
FlowCheck: Helping End-Users Specify and Verify Intent in Vibe-Coded Web Apps
Reya Vir, Lydia Chilton, Zhuo Zhang +1
Vibe-coded applications often contain silent behavioral failures in which the interface appears functional even though user-visible information does not flow to the expected state…
The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark
Jeremy Spence, Nicholas Assaderaghi, Jinhao Zhu +9
AI agents are rapidly improving in cybersecurity when source code is available, yet much of the software most consequential to security, including malware, firmware, and proprietar…
LogicEnvGen: Task-Logic Driven Generation of Diverse Simulated Environments for Embodied AI
Jianan Wang, Siyang Zhang, Bin Li +4
Simulated environments play an essential role in embodied AI, functionally analogous to test cases in software engineering. However, existing environment generation methods often e…
TRUST: A Decentralized Framework for Auditing Large Language Model Reasoning
Morris Yu-Chao Huang, Zhen Tan, Mohan Zhang +3
Large Language Models generate complex reasoning chains that reveal their decision-making, yet verifying the faithfulness and harmlessness of these intermediate steps remains a cri…
From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs
Guangyu Shen, Siyuan Cheng, Xiangzhe Xu +4
Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Exi…
ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants
Xiangzhe Xu, Guangyu Shen, Zian Su +9
AI coding assistants like GitHub Copilot are rapidly transforming software development, but their safety remains deeply uncertain-especially in high-stakes domains like cybersecuri…
MGC: A Compiler Framework Exploiting Compositional Blindness in Aligned LLMs for Malware Generation
Lu Yan, Zhuo Zhang, Xiangzhe Xu +5
Large language models (LLMs) have democratized software development, reducing the expertise barrier for programming complex applications. This accessibility extends to malicious so…
BugScope: Learn to Find Bugs Like Human
Jinyao Guo, Chengpeng Wang, Dominic Deluca +3
Software auditing is an increasingly critical task in the era of rapid code generation. While LLM-based auditors have demonstrated strong potential, their effectiveness remains lim…