Metraipolis › archive › dc_caaa4bb3c6a0

LLM-Assisted Dynamic Threat Analysis for Attacker-Reachable Software Weaknesses in Autonomous Vehicles — arXiv:2608.13450

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13450
License (as archived)
CC0-1.0
Archived
2026-10-19T04:26:21.511Z
SHA-256 of the archived text
9e001b0a6830699b52f4b075ffd12fe11a426747dd666a2145ff8b7eb88fa032
Stable URL of this page
https://metraipolis.com/documento/dc_caaa4bb3c6a0

How to cite

LLM-Assisted Dynamic Threat Analysis for Attacker-Reachable Software Weaknesses in Autonomous Vehicles — arXiv:2608.13450 — arXiv (en), https://arxiv.org/abs/2608.13450 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_caaa4bb3c6a0 (Metraipolis archive dc_caaa4bb3c6a0, sha256 9e001b0a6830699b52f4b075ffd12fe11a426747dd666a2145ff8b7eb88fa032)
BibTeX
@misc{dccaaa4bb3c6a0,
  title = {LLM-Assisted Dynamic Threat Analysis for Attacker-Reachable Software Weaknesses in Autonomous Vehicles — arXiv:2608.13450},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13450},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_caaa4bb3c6a0; sha256 9e001b0a6830699b52f4b075ffd12fe11a426747dd666a2145ff8b7eb88fa032},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13450. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autonomous vehicles depend on large safety-critical software stacks, where weaknesses reachable from adversarial inputs may affect steering, braking, or other control decisions. Static analysis can identify candidate sites, but dynamically confirming exploitability requires executable test artifacts that are difficult to construct manually. We investigate whether large language models (LLMs) can automate this process for Autoware, an open-source autonomous-driving stack. We perform compiler-precise static analysis across 185 packages, identifying 1,375 decision rules, 2,274 validation checks, and 482 input-to-safety-output flows, from which we derive a weakness taxonomy and sample 740 reachable sites. Two local open-weight LLMs, a no-static-context ablation, and a naive-template baseline generate 3,700 artifact sets, which are compiled against the real build under sanitizers, repaired through compiler-in-the-loop feedback, and fuzzed when executable. The main result is a build-integration failure taxonomy showing that 80% of first-shot compilation failures arise from dependency wiring rather than program logic. The reasoning model compiled 64% of harnesses on the first attempt, compared with 6% for the code-specialized model. Repair achieved full object-compileability for the reasoning model only through extensive stubbing; fewer than half of its harnesses reached the fuzzer, and all 37 observed crashes originated in stubbed code rather than Autoware. No candidate weakness was dynamically confirmed within budget. These results show that build integration, not candidate generation or fuzzing, is the primary barrier to reliable LLM-assisted dynamic analysis of full autonomous-vehicle software stacks.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-08-14 in cs.CR).
Categorie arXiv: Software Engineering (cs.SE) ; Cryptography and Security (cs.CR); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.13450 — 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 2026-10-19T04:20:00.587Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).