mlsanityData to 14 Oct 2026

ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage

arXiv 2605.21615 ↗First posted 20 May 2026cs.CR cs.LG cs.SEcited by 0

Not on the map. Why?

Abstract (arXiv)

Existing binary corpora typically capture only one or two axes of binary variation: they either provide cross-compiler builds without a temporal axis, or CVE labels for single-build binaries. None combine cross-build diversity, cross-version history, and CVE labels into a queryable structure. We present ASSEMBLAGE-DEEPHISTORY, which consolidates these dimensions into a unified framework where every binary's compilation context, source code, vulnerable functions, and package version are stored as first-class metadata. ASSEMBLAGE-DEEPHISTORY comprises 73,610 binaries spanning 248 open-source projects, compiled across GCC, Clang, and MSVC at multiple optimization levels on Linux and Windows, with multi-year historical builds. Each binary is indexed in a database that links it to its source code, functions, debug info, variant builds, historical versions, and vulnerable functions. Three analyses demonstrate this structure's value: (1) a three-stage LLM benchmark (recognition, strategy-guided detection, and cross-build transfer) to test whether LLMs reason about binary vulnerabilities or pattern-match on build-specific artifacts; (2) a comparison of MalConv embeddings, jTrans function embeddings, and TLSH fuzzy hashes quantifying how same-package versions cluster in each space; and (3) a Bayesian regression decomposing binary similarity into contributions from temporal distance, file changes, and commits.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 46 of its 98 references that are in the map. First posted on arXiv 20 May 2026.

Builds on

46 of 98 references.

References · 46

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  3. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,346
  4. 2020CodeBLEU: a Method for Automatic Evaluation of Code Synthesiscited by 479
  5. 2019Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyrocited by 191
  6. 2018EMBER: An Open Dataset for Training Static PE Malware Machine Learning Modelscited by 165
  7. 2024Vulnerability Detection with Code Language Models: How Far Are We?cited by 139
  8. 2023LLMs Cannot Reliably Identify and Reason About Security Vulnerabilities (Yet?): A Comprehensive Evaluation, Framework, and Benchmarkscited by 97
  9. 2021CVEfixes: Automated Collection of Vulnerabilities and Their Fixes from Open-Source Softwarecited by 91
  10. 2025SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Taskscited by 75
  11. 2017Neural Network-based Graph Embedding for Cross-Platform Binary Code Similarity Detectioncited by 65
  12. 2024Quantifying Contamination in Evaluating Code Generation Capabilities of Language Modelscited by 65
34 more
  1. 2024Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalizationcited by 55
  2. 2021PalmTree: Learning an Assembly Language Model for Instruction Embeddingcited by 49
  3. 2022jTrans: Jump-Aware Transformer for Binary Code Similaritycited by 44
  4. 2024LLM4Decompile: Decompiling Binary Code with Large Language Modelscited by 39
  5. 2018SAFE: Self-Attentive Function Embeddings for Binary Similaritycited by 33
  6. 2024MegaVul: A C/C++ Vulnerability Dataset with Comprehensive Code Representationcited by 27
  7. 2020Classifying Sequences of Extreme Length with Constant Memory Applied to Malware Detectioncited by 24
  8. 2025EquiBench: Benchmarking Large Language Models' Reasoning about Program Semantics via Equivalence Checkingcited by 24
  9. 2025SecVulEval: Benchmarking LLMs for Real-World C/C++ Vulnerability Detectioncited by 19
  10. 2025EMBER2024 -- A Benchmark Dataset for Holistic Evaluation of Malware Classifierscited by 19
  11. 2025SafeGenBench: A Benchmark Framework for Security Vulnerability Detection in LLM-Generated Codecited by 19
  12. 2021MOTIF: A Large Malware Reference Dataset with Ground Truth Family Labelscited by 17
  13. 2020Revisiting Binary Code Similarity Analysis using Interpretable Feature Engineering and Lessons Learnedcited by 14
  14. 2023Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learningcited by 12
  15. 2024Assemblage: Automatic Binary Dataset Construction for Machine Learningcited by 12
  16. 2025Decompile-Bench: Million-Scale Binary-Source Function Pairs for Real-World Binary Decompilationcited by 11
  17. 2023kTrans: Knowledge-Aware Transformer for Binary Code Embeddingcited by 10
  18. 2024BinaryAI: Binary Software Composition Analysis via Intelligent Binary Source Code Matchingcited by 9
  19. 2021Asteria: Deep Learning-based AST-Encoding for Cross-platform Binary Code Similarity Detectioncited by 8
  20. 2023EMBERSim: A Large-Scale Databank for Boosting Similarity Search in Malware Analysiscited by 6
  21. 2024Is Function Similarity Over-Engineered? Building a Benchmarkcited by 6
  22. 2020paper2repo: GitHub Repository Recommendation for Academic Paperscited by 5
  23. 2025On the Eligibility of LLMs for Counterfactual Reasoning: A Decompositional Studycited by 5
  24. 2025D-LiFT: Improving LLM-based Decompiler Backend via Code Quality-driven Fine-tuningcited by 5
  25. 2024VulZoo: A Comprehensive Vulnerability Intelligence Datasetcited by 4
  26. 2025VulBinLLM: LLM-powered Vulnerability Detection for Stripped Binariescited by 4
  27. 2025Idioms: Neural Decompilation With Joint Code and Type Definition Predictioncited by 3
  28. 2026Evaluating and Enhancing the Vulnerability Reasoning Capabilities of Large Language Modelscited by 3
  29. 2018Ubuntu One Investigation: Detecting Evidences on Client Machinescited by 2
  30. 2025BinPool: A Dataset of Vulnerabilities for Binary Security Analysiscited by 2
  31. 2026Superset Decompilationcited by 2
  32. 2024BinSimDB: Benchmark Dataset Construction for Fine-Grained Binary Code Similarity Analysiscited by 1
  33. 2025ORCAS: Obfuscation-Resilient Binary Code Similarity Analysis using Dominance Enhanced Semantic Graphcited by 1
  34. 2026Pushan: Trace-Free Deobfuscation of Virtualization-Obfuscated Binariescited by 1

Built on by

Not cited yet.