Metraipolis › archive › dc_0f2faa0ba040
ALIBI: Adversarial Legitimacy Injection in Binary Input against LLM Malware Analyzers — arXiv:2609.19722
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.19722
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T04:00:02.750Z
- SHA-256 of the archived text
c9eb170a30f380c55a435f5601f0e2be7e0dcb4f5e302651ffcbe0fa075122e8- Stable URL of this page
https://metraipolis.com/documento/dc_0f2faa0ba040
How to cite
ALIBI: Adversarial Legitimacy Injection in Binary Input against LLM Malware Analyzers — arXiv:2609.19722 — arXiv (en), https://arxiv.org/abs/2609.19722 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0f2faa0ba040 (Metraipolis archive dc_0f2faa0ba040, sha256 c9eb170a30f380c55a435f5601f0e2be7e0dcb4f5e302651ffcbe0fa075122e8)
BibTeX
@misc{dc0f2faa0ba040,
title = {ALIBI: Adversarial Legitimacy Injection in Binary Input against LLM Malware Analyzers — arXiv:2609.19722},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.19722},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0f2faa0ba040; sha256 c9eb170a30f380c55a435f5601f0e2be7e0dcb4f5e302651ffcbe0fa075122e8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19722. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models are being integrated into malware triage workflows as reasoning components that summarize static evidence and produce analyst-facing verdicts. This paper shows that the same reasoning capability introduces a new attack surface. We present ALIBI, a semantic cover story attack against frontier LLM-based malware analyzers. ALIBI adds a small, non-executed read-only section to a compiled binary, containing a coherent but false security product narrative, without altering imports or executable behavior. Instead of issuing direct instructions to the model, it reframes suspicious evidence as expected behavior of a benign endpoint security tool. On a frozen PE set of 50 malicious samples, the payload flips 30 of the 35 baseline-malicious samples to benign on Gemini 2.5 Pro, while GPT-5.5 Pro and Claude Opus 4.7 produce substantial severity downgrades with significant confidence reductions even when verdict labels are preserved. The attack transfers to ELF binaries, where Gemini flips 16 of 40. A verification-guided defense prompt roughly halves the benign verdicts, but 42.9 percent of malicious samples still reach benign. LLM malware analyzers therefore require provenance checks that separate verified facts from attacker-controlled claims, not narrative trust. Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-18 in cs.CR). Categorie arXiv: Cryptography and Security (cs.CR) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.19722 — 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 2026-10-10T03:26:20.869Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).