aiqbench analysis
This paper provides the first comprehensive taxonomy for AI-augmented binary reversing, synthesizing 246 research papers into a unified framework that bridges traditional analysis techniques with modern LLM and agentic systems. By establishing a common vocabulary across diverse inference tasks, it clarifies persistent evaluation gaps and offers a structured foundation for developing more robust, evidence-grounded security tools. The work is essential for researchers aiming to navigate the fragmented landscape of automated reverse engineering and leverage AI effectively in vulnerability discovery and malware investigation.
SoK: AI-Augmented Binary Reversing
arXiv:2606.17398v2 Announce Type: replace-cross Abstract: Binary reversing is fundamental to software understanding, vulnerability discovery, malware investigation, and firmware auditing. However, it remains inherently challenging due to the lossy transformation of semantic information during compilation. Recent advances in machine learning, large language models (LLMs), and agentic AI systems have accelerated the adoption of AI-augmented binary reversing. Yet, the resulting body of work has become increasingly fragmented across reversing domains, artifact representations, learning approaches, and evaluation practices. This paper presents the first comprehensive systematization of knowledge on AI-augmented binary reversing. We collect 246 research papers published since 2015, and organize them into 22 binary reversing domains according to the inference tasks. We further introduce a unified taxonomy spanning conventional and AI-augmented reversing pipelines. Our taxonomy connects traditional analysis techniques, binary-derived artifacts, representation strategies, learning paradigms, and downstream inference tasks, while clarifying the emerging roles of LLMs and agentic AI systems. By establishing a common vocabulary and structured framework, we offer a holistic view of the field's evolution over the past decade. Our study reveals common structures underlying seemingly disparate approaches, highlights persistent technical challenges and evaluation gaps, and identifies promising opportunities for future research. Collectively, these insights clarify the current state of the field and provide a foundation for the next generation of evidence-grounded and practically deployable AI-augmented binary reversing systems.
Abstract:Binary reversing is fundamental to software understanding, vulnerability discovery, malware investigation, and firmware auditing. However, it remains inherently challenging due to the lossy transformation of semantic information during compilation. Recent advances in machine learning, large language models (LLMs), and agentic AI systems have accelerated the adoption of AI-augmented binary reversing. Yet, the resulting body of work has become increasingly fragmented across reversing domains, artifact representations, learning approaches, and evaluation practices. This paper presents the first comprehensive systematization of knowledge on AI-augmented binary reversing. We collect 246 research papers published since 2015, and organize them into 22 binary reversing domains according to the inference tasks. We further introduce a unified taxonomy spanning conventional and AI-augmented reversing pipelines. Our taxonomy connects traditional analysis techniques, binary-derived artifacts, representation strategies, learning paradigms, and downstream inference tasks, while clarifying the emerging roles of LLMs and agentic AI systems. By establishing a common vocabulary and structured framework, we offer a holistic view of the field's evolution over the past decade. Our study reveals common structures underlying seemingly disparate approaches, highlights persistent technical challenges and evaluation gaps, and identifies promising opportunities for future research. Collectively, these insights clarify the current state of the field and provide a foundation for the next generation of evidence-grounded and practically deployable AI-augmented binary reversing systems.
Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Software Engineering (cs.SE)
arXiv:2606.17398 [cs.CR]
(or arXiv:2606.17398v2 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2606.17398 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 · 313 words
Related coverage
SoK: AI-Augmented Binary Reversing
arXiv · Jun 17, 2026
Symbolic Augmentation Closes a Canonical-Equivalence Blind Spot in Neural Fact-Checkers
arXiv · Jul 21, 2026
Correcting Connectivity in Arc-Based QUBO Models for Fixed-Fleet Vehicle Routing
arXiv · Aug 28, 2026
Article: The AI Productivity Paradox in Test Automation: Moving beyond Structural Validation to Perception and Intent
InfoQ · Jun 1, 2026