Metraipolis › archive › dc_91c26fd409b1

CloakFEM: Agentic FEM Code Generation for Red-Teaming Computational Resource Exhaustion — arXiv:2611.04356

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04356
License (as archived)
CC0-1.0
Archived
2026-11-04T18:36:38.454Z
SHA-256 of the archived text
c3ca2148fc9c3e30ac884d5fe29578abf2a1aab269b0bada008f5b21a7d7ef85
Stable URL of this page
https://metraipolis.com/documento/dc_91c26fd409b1

How to cite

CloakFEM: Agentic FEM Code Generation for Red-Teaming Computational Resource Exhaustion — arXiv:2611.04356 — arXiv (en), https://arxiv.org/abs/2611.04356 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_91c26fd409b1 (Metraipolis archive dc_91c26fd409b1, sha256 c3ca2148fc9c3e30ac884d5fe29578abf2a1aab269b0bada008f5b21a7d7ef85)
BibTeX
@misc{dc91c26fd409b1,
  title = {CloakFEM: Agentic FEM Code Generation for Red-Teaming Computational Resource Exhaustion — arXiv:2611.04356},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04356},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_91c26fd409b1; sha256 c3ca2148fc9c3e30ac884d5fe29578abf2a1aab269b0bada008f5b21a7d7ef85},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04356. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Finite element method (FEM) solvers are foundational to scientific and engineering simulation, yet their susceptibility to \emph{efficiency attacks} remains largely unexplored. An adversary can craft syntactically valid and runnable FEM programs that complete successfully while forcing excessive computational work, enabling computational denial-of-service (DoS) attacks. Finding such inputs is challenging because FEM programs occupy a vast, structured space constrained by numerical, geometric, and constitutive requirements. We introduce CloakFEM, a domain-guided LLM-agent framework for automatically generating runnable adversarial FEM programs that amplify solver computation. CloakFEM combines LLM-guided search with an FEM-specific intermediate representation and a deterministic validity gate that enforces runnable constraints. Across three FEM stacks, 17 problem classes, and 1,068 seeds, CloakFEM discovers adversarial inputs that substantially amplify solver work while remaining valid and solvable. In the most extreme case, solver iterations increase from 43 to 247,367, a \(5{,}752.72\times\) amplification. CloakFEM outperforms five generic black-box baselines and retains an advantage over evolutionary search under a controlled bounded action space. Cross-solver analysis further reveals both problem-intrinsic and solver-specific sources of vulnerability. Our results uncover an underexplored efficiency-attack surface in FEM solvers and show that runnable FEM programs can serve as adversarial inputs.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2611.04356 — 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 2026-11-04T18:32:37.439Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).