mlsanityData to 7 Oct 2026

Backdoors in Neural Models of Source Code

arXiv 2006.06841 ↗First posted 11 Jun 2020cs.LG cs.CR stat.MLcited by 27

Not on the map. Why?

Abstract (arXiv)

Deep neural networks are vulnerable to a range of adversaries. A particularly pernicious class of vulnerabilities are backdoors, where model predictions diverge in the presence of subtle triggers in inputs. An attacker can implant a backdoor by poisoning the training data to yield a desired target prediction on triggered inputs. We study backdoors in the context of deep-learning for source code. (1) We define a range of backdoor classes for source-code tasks and show how to poison a dataset to install such backdoors. (2) We adapt and improve recent algorithms from robust statistics for our setting, showing that backdoors leave a spectral signature in the learned representation of source code, thus enabling detection of poisoned data. (3) We conduct a thorough evaluation on different architectures and languages, showing the ease of injecting backdoors and our ability to eliminate them.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 1; 2023: 9; 2024: 9; 2025: 5; 2026: 2.

27 papers.

Sort:

By area:

  1. 2023Privacy in Large Language Models: Attacks, Defenses and Future Directionscited by 48
  2. 2021CoProtector: Protect Open-Source Code against Unauthorized Training Usage with Data Poisoningcited by 39
  3. 2023Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attackscited by 29
  4. 2024Compromising Embodied Agents with Contextual Backdoor Attackscited by 29
  5. 2023Large Language Models of Code Fail at Completing Code with Potential Bugscited by 28
  6. 2023CodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Modelscited by 28
  7. 2023Deep Learning for Code Intelligence: Survey, Benchmark and Toolkitcited by 22
  8. 2023Multi-target Backdoor Attacks for Code Pre-trained Modelscited by 19
  9. 2022BagFlip: A Certified Defense against Data Poisoningcited by 18
  10. 2023Backdooring Neural Code Searchcited by 13
  11. 2025A Systematic Review of Poisoning Attacks Against Large Language Modelscited by 8
  12. 2023Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarioscited by 7
15 more
  1. 2023A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attackscited by 5
  2. 2024Poisoning Programs by Un-Repairing Code: Security Concerns of AI-generated Codecited by 5
  3. 2024Flatness-aware Sequential Learning Generates Resilient Backdoorscited by 3
  4. 2025Show Me Your Code! Kill Code Poisoning: A Lightweight Method Based on Code Naturalnesscited by 3
  5. 2024EaTVul: ChatGPT-based Evasion Attack Against Software Vulnerability Detectioncited by 2
  6. 2024Eliminating Backdoors in Neural Code Models for Secure Code Understandingcited by 2
  7. 2024Trojans in Large Language Models of Code: A Critical Review through a Trigger-Based Taxonomycited by 1
  8. 2025Beyond Natural Language Perplexity: Detecting Dead Code Poisoning in Code Generation Datasetscited by 1
  9. 2024On Trojan Signatures in Large Language Models of Codecited by 0
  10. 2024A Disguised Wolf Is More Harmful Than a Toothless Tiger: Adaptive Malicious Code Injection Backdoor Attack Leveraging User Behavior as Triggerscited by 0
  11. 2024CodePurify: Defend Backdoor Attacks on Neural Code Models via Entropy-based Purificationcited by 0
  12. 2025Localizing Malicious Outputs from CodeLLMcited by 0
  13. 2025Signature in Code Backdoor Detection, how far are we?cited by 0
  14. 2026ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Commentscited by 0
  15. 2026Adversarial Testing of Automated Program Repair Agents for Security Vulnerabilitiescited by 0