mlsanityData to 14 Oct 2026

Cybersecurity is the True Frontier for Generative AI Success or Failure

arXiv 2606.28929 ↗First posted 27 Jun 2026cs.CR cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Cybersecurity is a real-life test-bed for many machine learning problems at once, especially when considering modern strides in using Large Language Models (LLMs) to automate processes as ``agents.'' Cybersecurity workflows require orchestrating hundreds of standard and bespoke tools through various formats. The scale of cybersecurity data is enormous; for example, a single malware sample can be viewed as a sequence of billions of tokens. The cost of labeling any file by experts is enormous and labor-intensive, in part because an adversary (possibly a well-funded nation state actor) is attempting to subvert your detection methods. Even skilled experts may disagree on the correct label, creating ambiguity in what constitutes ground truth. When deployed, models must run quickly on billions of items a day, where low-latency is critical for operational success, in a continuously changing environment. In addition, explainability is not optional: analysts demand clear reasoning for model decisions to cope with the large number of false-positive alerts they face daily, and to quickly develop remediation and understand how something went wrong. In short, the amount of complexity cybersecurity is greater than that of natural language and computer vision, and thus we posit that cybersecurity is the better test-case for general AI progress than other, well-studied fields.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 51 of its 109 references that are in the map. First posted on arXiv 27 Jun 2026.

Builds on

51 of 109 references.

References · 51

  1. 2020Rethinking Attention with Performerscited by 1,601
  2. 2020Linformer: Self-Attention with Linear Complexitycited by 1,474
  3. 2023Tree of Attacks: Jailbreaking Black-Box LLMs Automaticallycited by 672
  4. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 411
  5. 2023Grammar-Constrained Decoding for Structured NLP Tasks without Finetuningcited by 197
  6. 2017Malware Detection by Eating a Whole EXEcited by 115
  7. 2018TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Timecited by 108
  8. 2024SynCode: LLM Generation with Grammar Augmentationcited by 69
  9. 2024EasyJailbreak: A Unified Framework for Jailbreaking Large Language Modelscited by 60
  10. 2020SOREL-20M: A Large Scale Benchmark Dataset for Malicious PE Detectioncited by 49
  11. 2015Deep Neural Network Based Malware Detection Using Two Dimensional Binary Program Featurescited by 48
  12. 2024Automated Red Teaming with GOAT: the Generative Offensive Agent Testercited by 45
38 more
  1. 2020Misplaced Trust: Measuring the Interference of Machine Learning in Human Decision-Makingcited by 25
  2. 2020Classifying Sequences of Extreme Length with Constant Memory Applied to Malware Detectioncited by 24
  3. 2019An Observational Investigation of Reverse Engineers' Processescited by 21
  4. 2020XDA: Accurate, Robust Disassembly with Transfer Learningcited by 21
  5. 2025Frontier AI's Impact on the Cybersecurity Landscapecited by 21
  6. 2025EMBER2024 -- A Benchmark Dataset for Holistic Evaluation of Malware Classifierscited by 19
  7. 2018Benchmarking datasets for Anomaly-based Network Intrusion Detection: KDD CUP 99 alternativescited by 18
  8. 2023Bytes Are All You Need: Transformers Operating Directly On File Bytescited by 18
  9. 2020Automatic Yara Rule Generation Using Biclusteringcited by 17
  10. 2020Magma: A Ground-Truth Fuzzing Benchmarkcited by 16
  11. 2021A Framework for Cluster and Classifier Evaluation in the Absence of Reference Labelscited by 16
  12. 2022SoK: The Impact of Unlabelled Data in Cyberthreat Detectioncited by 15
  13. 2025ELFuzz: Efficient Input Generation via LLM-driven Synthesis Over Fuzzer Spacecited by 15
  14. 2023Illuminati: Towards Explaining Graph Neural Networks for Cybersecurity Analysiscited by 14
  15. 2023Recasting Self-Attention with Holographic Reduced Representationscited by 14
  16. 2024Assemblage: Automatic Binary Dataset Construction for Machine Learningcited by 12
  17. 2021Leveraging Uncertainty for Improved Static Malware Detection Under Extreme False Positive Constraintscited by 11
  18. 2025ClarAVy: A Tool for Scalable and Accurate Malware Family Labelingcited by 10
  19. 2020Machine Learning (In) Security: A Stream of Problemscited by 8
  20. 2013Unveiling Zeuscited by 7
  21. 2017Learning the PE Header, Malware Detection with Minimal Domain Knowledgecited by 7
  22. 2021Rank-1 Similarity Matrix Decomposition For Modeling Changes in Antivirus Consensus Through Timecited by 7
  23. 2022Transformers for End-to-End InfoSec Tasks: A Feasibility Studycited by 6
  24. 2024Holographic Global Convolutional Networks for Long-Range Prediction Tasks in Malware Detectioncited by 6
  25. 2024Is Function Similarity Over-Engineered? Building a Benchmarkcited by 6
  26. 2024Can LLMs Obfuscate Code? A Systematic Analysis of Large Language Models into Assembly Code Obfuscationcited by 6
  27. 2020Getting Passive Aggressive About False Positives: Patching Deployed Malware Detectorscited by 5
  28. 2023That Escalated Quickly: An ML Framework for Alert Prioritizationcited by 4
  29. 2017Rise of the HaCRS: Augmenting Autonomous Cyber Reasoning Systems with Human Assistancecited by 3
  30. 2024SoK: Leveraging Transformers for Malware Analysiscited by 3
  31. 2025UTF-8 Plumbing: Byte-level Tokenizers Unavoidably Enable LLMs to Generate Ill-formed UTF-8cited by 3
  32. 2024Detecting new obfuscated malware variants: A lightweight and interpretable machine learning approachcited by 2
  33. 2024A New Dataset and Methodology for Malicious URL Classificationcited by 2
  34. 2025Disassembly as Weighted Interval Scheduling with Learned Weightscited by 2
  35. 2025Tady: A Neural Disassembler without Structural Constraint Violationscited by 2
  36. 2026Superset Decompilationcited by 2
  37. 2024Unleashing the Power of Unlabeled Data: A Self-supervised Learning Framework for Cyber Attack Detection in Smart Gridscited by 1
  38. 2025Robust Intrusion Detection System with Explainable Artificial Intelligencecited by 1

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Identifying Security Platform Product Abuse with Machine Learningcited by 0
  2. 2026An Introduction to Compression-Based Machine Learningcited by 0