mlsanityData to 14 Oct 2026

SoK: AI-Augmented Binary Reversing

arXiv 2606.17398 ↗First posted 16 Jun 2026cs.CR cs.AI cs.SEcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 61 of its 216 references that are in the map. First posted on arXiv 16 Jun 2026.

Builds on

61 of 216 references.

References · 61

  1. 2023Code Llama: Open Foundation Models for Codecited by 2,139
  2. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,181
  3. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 906
  4. 2019Graph Matching Networks for Learning the Similarity of Graph Structured Objectscited by 205
  5. 2020Dos and Don'ts of Machine Learning in Computer Securitycited by 102
  6. 2017Neural Network-based Graph Embedding for Cross-Platform Binary Code Similarity Detectioncited by 65
  7. 2020Transcending Transcend: Revisiting Malware Classification in the Presence of Concept Driftcited by 53
  8. 2021PalmTree: Learning an Assembly Language Model for Instruction Embeddingcited by 49
  9. 2022jTrans: Jump-Aware Transformer for Binary Code Similaritycited by 44
  10. 2024LLM4Decompile: Decompiling Binary Code with Large Language Modelscited by 39
  11. 2019DIRE: A Neural Approach to Decompiled Identifier Namingcited by 36
  12. 2018SAFE: Self-Attentive Function Embeddings for Binary Similaritycited by 33
38 more
  1. 2019Explaining Vulnerabilities of Deep Learning to Adversarial Malware Binariescited by 31
  2. 2023Extending Source Code Pre-Trained Language Models to Summarise Decompiled Binariescited by 26
  3. 2018Neural Machine Translation Inspired Binary Code Similarity Comparison beyond Function Pairscited by 25
  4. 2020Classifying Sequences of Extreme Length with Constant Memory Applied to Malware Detectioncited by 24
  5. 2019Dynamic Malware Analysis with Feature Engineering and Feature Learningcited by 23
  6. 2021Augmenting Decompiler Output with Learned Variable Names and Typescited by 23
  7. 2015Novel Feature Extraction, Selection and Fusion for Effective Malware Family Classificationcited by 21
  8. 2020XDA: Accurate, Robust Disassembly with Transfer Learningcited by 21
  9. 2018NEUZZ: Efficient Fuzzing with Neural Program Smoothingcited by 19
  10. 2019A Survey of Binary Code Similaritycited by 19
  11. 2024CLAP: Learning Transferable Binary Code Representations with Natural Language Supervisioncited by 17
  12. 2022Out of Distribution Data Detection Using Dropout Bayesian Neural Networkscited by 15
  13. 2020Revisiting Binary Code Similarity Analysis using Interpretable Feature Engineering and Lessons Learnedcited by 14
  14. 2023Harnessing the Power of LLM to Support Binary Taint Analysiscited by 13
  15. 2025Chasing Shadows: Pitfalls in LLM Security Researchcited by 13
  16. 2023FINER: Enhancing State-of-the-art Classifiers with Feature Attribution to Facilitate Security Analysiscited by 12
  17. 2023Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learningcited by 12
  18. 2015When Coding Style Survives Compilation: De-anonymizing Programmers from Executable Binariescited by 11
  19. 2023CP-BCS: Binary Code Summarization Guided by Control Flow Graph and Pseudo Codecited by 11
  20. 2024Revisiting Concept Drift in Windows Malware Detection: Adaptation to Real Drifted Malware with Minimal Samplescited by 11
  21. 2024BinaryAI: Binary Software Composition Analysis via Intelligent Binary Source Code Matchingcited by 9
  22. 2021Asteria: Deep Learning-based AST-Encoding for Cross-platform Binary Code Similarity Detectioncited by 8
  23. 2022BinBert: Binary Code Understanding with a Fine-tunable and Execution-aware Transformercited by 8
  24. 2024Source Code Foundation Models are Transferable Binary Analysis Knowledge Basescited by 8
  25. 2025MalCL: Leveraging GAN-Based Generative Replay to Combat Catastrophic Forgetting in Malware Classificationcited by 8
  26. 2019Neutaint: Efficient Dynamic Taint Analysis with Neural Networkscited by 7
  27. 2022Decompiling x86 Deep Neural Network Executablescited by 7
  28. 2024CodeArt: Better Code Models by Attention Regularization When Symbols Are Lackingcited by 7
  29. 2025SK2Decompile: LLM-based Two-Phase Binary Decompilation from Skeleton to Skincited by 7
  30. 2020MTFuzz: Fuzzing with a Multi-Task Neural Networkcited by 6
  31. 2022Pre-Training Representations of Binary Code Using Contrastive Learningcited by 6
  32. 2023EMBERSim: A Large-Scale Databank for Boosting Similarity Search in Malware Analysiscited by 6
  33. 2024Can LLMs Obfuscate Code? A Systematic Analysis of Large Language Models into Assembly Code Obfuscationcited by 6
  34. 2021XFL: Naming Functions in Binaries with Extreme Multi-label Learningcited by 5
  35. 2023GraphMoco:a Graph Momentum Contrast Model that Using Multimodel Structure Information for Large-scale Binary Function Representation Learningcited by 5
  36. 2019Pangolin: An Efficient and Flexible Graph Pattern Mining System on CPU and GPUcited by 4
  37. 2023Feature-Space Bayesian Adversarial Learning Improved Malware Detector Robustnesscited by 4
  38. 2024Cross-Inlining Binary Function Similarity Detectioncited by 4

50 most cited of 61 All 61 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Reversa: A Reverse Documentation Engineering Framework for Converting Legacy Software into Operational Specifications for AI Agents
  2. 2025ReCopilot: Reverse Engineering Copilot in Binary Analysis
  3. 2026Revelio: Cost-Efficient Agentic Memory Safety Vulnerability Detection For Repository-Scale Codebases
  4. 2026Challenges and Future Directions in Agentic Reverse Engineering Systems
  5. 2026CrackMeBench: Binary Reverse Engineering for Agents
  6. 2026The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark
  7. 2026Verify Before You Fix: Agentic Execution Grounding for Trustworthy Cross-Language Code Analysis
  8. 2026Reveree: Diagnosing LLM Reverse-Engineering Agents