Metraipolis › archive › dc_7ee8df2dad41

Towards Effective Black-Box Adversarial Attacks on Deep Code Models via Structural and Identifier Perturbations — arXiv:2609.26234

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.26234
License (as archived): CC0-1.0
Archived: 2026-10-08T14:42:07.907Z
SHA-256 of the archived text: 2513fa24c2dac6c579c25d0b3ba1117827db29f263c2a0ed408538ed2a886126
Stable URL of this page: https://metraipolis.com/documento/dc_7ee8df2dad41

How to cite

Towards Effective Black-Box Adversarial Attacks on Deep Code Models via Structural and Identifier Perturbations — arXiv:2609.26234 — arXiv (en), https://arxiv.org/abs/2609.26234 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7ee8df2dad41 (Metraipolis archive dc_7ee8df2dad41, sha256 2513fa24c2dac6c579c25d0b3ba1117827db29f263c2a0ed408538ed2a886126)

BibTeX

@misc{dc7ee8df2dad41,
  title = {Towards Effective Black-Box Adversarial Attacks on Deep Code Models via Structural and Identifier Perturbations — arXiv:2609.26234},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26234},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7ee8df2dad41; sha256 2513fa24c2dac6c579c25d0b3ba1117827db29f263c2a0ed408538ed2a886126},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26234. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep code models (DCMs) are increasingly embedded in code intelligence tasks. However, their robustness under adversarial attacks remains insufficiently understood. Prior black-box attacks mainly rely on identifier- only substitutions or structural edits transferred from reference samples, yielding perturbation spaces defined largely independently of the attacked input. We introduce Strike, an input-conditioned black-box adversarial robustness-testing framework that constructs and searches a hierarchical perturbation space for each input. Strike first partitions code into blocks and uses an LLM to generate context-specific structural candidates, filtered for syntactic validity, ranked by similarity, and adaptively combined. It then refines the best structural variant through similarity-guided identifier substitutions drawn from dynamically constructed candidate pools. Evaluations across representative code intelligence tasks, including clone detection, vulnerability detection, and code summarization, demonstrate that Strike achieves higher attack success rates with competitive target- model query overhead. Strategy-specific static checks across all three tasks and execution-based validation on the executable Juliet vulnerability-detection subset provide complementary, task-bounded evidence regarding the validity of the generated variants. Representation similarity and human evaluation further indicate that the variants remain highly similar to the original code and contextually natural. Fine-tuning with Strike- generated samples improves cross-attack performance on fixed perturbed evaluation sets while preserving clean performance.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-23 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR) ; Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2609.26234 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T13:55:11.748Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).