Metraipolis › archive › dc_ccafe815bcfa

CITADEL: CWE-Guided Insertion of Hardware Trojans via Analysis of DFG-Enabled LLMs — arXiv:2610.02544

Source
arXiv
Original
https://arxiv.org/abs/2610.02544
License (as archived)
CC0-1.0
Archived
2026-10-05T23:06:19.413Z
SHA-256 of the archived text
89323b3f8557e88b859af7e3bef968995b845f8a3eb3f4f611991041d7e8910e
Stable URL of this page
https://metraipolis.com/documento/dc_ccafe815bcfa

How to cite

CITADEL: CWE-Guided Insertion of Hardware Trojans via Analysis of DFG-Enabled LLMs — arXiv:2610.02544 — arXiv, https://arxiv.org/abs/2610.02544 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ccafe815bcfa (Metraipolis archive dc_ccafe815bcfa, sha256 89323b3f8557e88b859af7e3bef968995b845f8a3eb3f4f611991041d7e8910e)
BibTeX
@misc{dcccafe815bcfa,
  title = {CITADEL: CWE-Guided Insertion of Hardware Trojans via Analysis of DFG-Enabled LLMs — arXiv:2610.02544},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.02544},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ccafe815bcfa; sha256 89323b3f8557e88b859af7e3bef968995b845f8a3eb3f4f611991041d7e8910e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02544. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The increasing sophistication of Hardware Trojans (HTs) and system-level vulnerabilities poses significant risks to modern integrated circuits. However, constructing realistic HT scenarios, remains a substantial burden: researchers must manually analyze complex RTL structures, identify plausible weaknesses, and craft stealthy, synthesizable insertions that preserve functional correctness. This paper introduces CITADEL CWE-Guided Insertion of Trojans via Analysis of DFG-Enabled LLMs, a framework that leverages Large Language Models (LLMs) and Data Flow Graphs (DFGs) to automate CWE-grounded HT synthesis. CITADEL uses structured CWE semantics together with DFG-derived structural context to assist the user in identifying relevant vulnerabilities, localize the module surrounding the chosen insertion point, and perform intent-conditioned RTL modification. The framework produces minimal, synthesizable, and interface-preserving HTs with ultra-rare triggers. Experimental evaluation across diverse RTL designs demonstrates that all generated HTs are 100% syntactically correct, remain undetectable under large-scale random simulation, and are functionally triggerable under their intended activation conditions. These results highlight CITADEL as a scalable and principled method for generating realistic HT benchmarks.

Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2610.02544 — 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 2026-10-05T23:01:08.535Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).