Search papers, labs, and topics across Lattice.
This paper introduces a hybrid malware detection framework combining concolic execution with LLM-augmented path prioritization and deep learning-based vulnerability classification to combat AI-generated malware. The framework uses an LLM to guide concolic execution, reducing explored paths by 73.2% while maintaining coverage, and employs a transformer-based classifier trained on symbolic execution traces. Evaluated on multiple datasets including a novel AI-Gen-Malware benchmark, the framework achieves 97.5% accuracy on AI-generated threats, significantly outperforming existing methods.
LLMs can now help you catch AI-generated malware: a hybrid analysis framework uses LLMs to guide concolic execution and deep learning to classify vulnerabilities, achieving state-of-the-art detection rates.
The weaponization of LLMs for automated malware generation poses an existential threat to conventional detection paradigms. AI-generated malware exhibits polymorphic, metamorphic, and context-aware evasion capabilities that render signature-based and shallow heuristic defenses obsolete. This paper introduces a novel hybrid analysis framework that synergistically combines \emph{concolic execution} with \emph{LLM-augmented path prioritization} and \emph{deep-learning-based vulnerability classification} to detect zero-day AI-generated malware with provable guarantees. We formalize the detection problem within a first-order temporal logic over program execution traces, define a lattice-theoretic abstraction for path constraint spaces, and prove both the \emph{soundness} and \emph{relative completeness} of our detection algorithm, assuming classifier correctness. The framework introduces three novel algorithms: (i) an LLM-guided concolic exploration strategy that reduces the average number of explored paths by 73.2\% compared to depth-first search while maintaining equivalent malicious-path coverage; (ii) a transformer-based path-constraint classifier trained on symbolic execution traces; and (iii) a feedback loop that iteratively refines the LLM's prioritization policy using reinforcement learning from detection outcomes. We provide a comprehensive implementation built upon \texttt{angr} 9.2, \texttt{Z3} 4.12, Hugging Face Transformers 4.38, and PyTorch 2.2, with configuration details enabling reproducibility. Experimental evaluation on the EMBER, Malimg, SOREL-20M, and a novel AI-Gen-Malware benchmark comprising 2{,}500 LLM-synthesized samples demonstrates that achieves 98.7\% accuracy on conventional malware and 97.5\% accuracy on AI-generated threats, outperforming ClamAV, YARA, MalConv, and EMBER-GBDT baselines by margins of 8.4--52.2 percentage points on AI-generated samples.