← Back to all news
arXiv AI By Xinran Zheng, Xingzhi Qian, Yiling He, Shuo Yang, Lorenzo Cavallaro

Is "Knowing It's Malicious Enough?" Evaluating LLMs for Fine-Grained Malware Behavior Auditing

Read the original on arXiv AI →

arXiv:2509. 14335v2 Announce Type: replace-cross Abstract: Automated malware classifiers achieve strong detection performance, but auditing requires more than flagging a sample: analysts must explain malicious behaviors and justify them with code evidence.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Sep 18

ALIBI: Adversarial Legitimacy Injection in Binary Input against LLM Malware Analyzers

The paper introduces ALIBI, a semantic cover story attack that injects a small, non-executed read‑only section into compiled binaries to mislead large language model (LLM) malware analyzers. By embedding a coherent but false security narrative, ALIBI can cause LLMs such as Gemini 2.5 Pro, GPT‑5.5 Pro, and Claude Opus 4.7 to downgrade or flip the verdicts of malicious samples. The attack also transfers to ELF binaries, and even a verification‑guided defense prompt only partially mitigates the effect, leaving a significant portion of malicious samples classified as benign.

By Hyeongjun Choi, Wonyoung Jung, Haehoon Seo, Sungyup Nam
llmssafety
More like this →
arXiv AI
Sep 25

Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning

The paper introduces CodeScan, a black-box, vulnerability-oriented scanning framework designed to detect data poisoning and backdoor attacks in code generation large language models (LLMs). CodeScan operates by analyzing structural similarities across multiple code generations, normalizing them with abstract syntax tree (AST) techniques, and then applying LLM-based vulnerability analysis to identify recurring insecure patterns. Evaluations on 117 models across three architectures and multiple sizes show over 97% detection accuracy with fewer false positives compared to prior methods.

By Shenao Yan, Shan Jin, Shimaa Ahmed, Sunpreet Singh Arora, Yiwei Cai, Yizhen Wang, Yuan Hong
llms
More like this →