aiqbench analysis
This research introduces MalEval, a diagnostic framework that exposes critical limitations in current Large Language Models when tasked with fine-grained malware behavior auditing. The study reveals that existing models often rely on surface-level cues rather than verifiable code evidence and struggle to construct coherent attack chains within limited context windows. These findings underscore the urgent need for agentic workflows grounded in structured, human-interpretable proof before LLMs can be trusted for high-stakes security analysis.
Is "Knowing It's Malicious Enough?" Evaluating LLMs for Fine-Grained Malware Behavior Auditing
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. Traditional signature-based methods and learning-based XAI often fail to provide such support in a human-interpretable form. Large Language Models (LLMs) appear promising, yet their reliability for malware auditing remains unclear. Evaluation faces three challenges: (1) the lack of human-written behavioral ground truth; (2) real-world codebases that exceed current context limits; and (3) the lack of reliable mechanisms to verify whether generated claims are grounded in code evidence. These obstacles make benchmarking difficult and leave model capabilities and failure modes opaque. We introduce MalEval, a diagnostic framework for measuring the capability boundaries of LLMs in malware auditing. MalEval pairs real-world application codebases with expert-written audit reports to provide fine-grained behavior-level ground truth. It compresses large codebases into behavior-relevant program contexts through a context-driven intermediate representation that preserves call relations. Expert reports and model outputs are mapped, via constrained reasoning, into structured evidence chains linking code-level facts to high-level behaviors in a shared space. MalEval decomposes auditing into four stage-wise tasks, enabling each intermediate judgment to be verified under limited context windows. We evaluate seven LLMs and find that they rely on surface cues rather than verifiable evidence, struggle to compose dispersed facts into coherent attack chains, and are highly sensitive to context formulation. These findings shift attention from isolated outputs to reliable LLM and agentic workflows for malware auditing. MalEval is publicly available at https://github.com/ZhengXR930/MalEval.git
Title:Is "Knowing It's Malicious Enough?" Evaluating LLMs for Fine-Grained Malware Behavior Auditing
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. Traditional signature-based methods and learning-based XAI often fail to provide such support in a human-interpretable form. Large Language Models (LLMs) appear promising, yet their reliability for malware auditing remains unclear. Evaluation faces three challenges: (1) the lack of human-written behavioral ground truth; (2) real-world codebases that exceed current context limits; and (3) the lack of reliable mechanisms to verify whether generated claims are grounded in code evidence. These obstacles make benchmarking difficult and leave model capabilities and failure modes opaque. We introduce MalEval, a diagnostic framework for measuring the capability boundaries of LLMs in malware auditing. MalEval pairs real-world application codebases with expert-written audit reports to provide fine-grained behavior-level ground truth. It compresses large codebases into behavior-relevant program contexts through a context-driven intermediate representation that preserves call relations. Expert reports and model outputs are mapped, via constrained reasoning, into structured evidence chains linking code-level facts to high-level behaviors in a shared space. MalEval decomposes auditing into four stage-wise tasks, enabling each intermediate judgment to be verified under limited context windows. We evaluate seven LLMs and find that they rely on surface cues rather than verifiable evidence, struggle to compose dispersed facts into coherent attack chains, and are highly sensitive to context formulation. These findings shift attention from isolated outputs to reliable LLM and agentic workflows for malware auditing. MalEval is publicly available at this https URL
Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Software Engineering (cs.SE)
arXiv:2509.14335 [cs.CR]
(or arXiv:2509.14335v2 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2509.14335 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 363 words
