From the 1 of 5 linked papers with an AI index.
6 papers
PVDetector: Detecting Prompt Injection Attacks on Purpose-Specific LLM Agents through Policy-Violation Concept Analysis
Junhui Wang, Hangtao Zhang, Zhirun Zheng +5
The paper introduces PVDetector, a training‑free method that detects prompt injection attacks on purpose‑specific LLM agents by measuring alignment of hidden states with policy‑vio…
A Large-Scale Comprehensive Measurement of AI-Generated Code in Real-World Repositories
Tianhao Mao, Dongfang Zhao, Haixu Tang +2
Large language models (LLMs) are rapidly transforming software engineering by enabling developers to generate code ranging from small snippets to entire projects. As AI-assisted co…
The Hitchhiker's Guide to Program Analysis, Part III: Mostly Harmless LLMs
Haonan Li, Tianyang Zhou, Manu Sridharan +2
LLMs are increasingly used in bug analysis to reason about code and judge whether a potential bug can be triggered in realistic execution contexts, with recent work showing promisi…
Defending Jailbreak Attacks on Large Language Models via Manifold Trajectory Kinetics
Hangtao Zhang, Yucheng Zhao, Sishun Liu +8
Jailbreak prompts can bypass alignment guardrails in large language models (LLMs) and elicit unsafe outputs, making reliable deployment-time detection critical. Prior detection app…
LineBreaker: Finding Token-Inconsistency Bugs with Large Language Models
Hongbo Chen, Yifan Zhang, Xing Han +7
Token-inconsistency bugs (TIBs) involve the misuse of syntactically valid yet incorrect code tokens, such as misused variables and erroneous function invocations, which can often l…
Disassembling Obfuscated Executables with LLM
Huanyao Rong, Yue Duan, Hang Zhang +4
Disassembly is a challenging task, particularly for obfuscated executables containing junk bytes, which is designed to induce disassembly errors. Existing solutions rely on heurist…