Metraipolis › archive › dc_eaf9a69f4e92

Mind Your Boundaries: Boundary-Aware Model Obfuscation against Cross-node Attack — arXiv:2610.27135

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.27135
License (as archived)
CC0-1.0
Archived
2026-10-21T07:07:28.634Z
SHA-256 of the archived text
e0d71e18ba9d23fe6c4f6a9ee68cc2e50a3ba031bc05d809104d56d3e8830ca0
Stable URL of this page
https://metraipolis.com/documento/dc_eaf9a69f4e92

How to cite

Mind Your Boundaries: Boundary-Aware Model Obfuscation against Cross-node Attack — arXiv:2610.27135 — arXiv (en), https://arxiv.org/abs/2610.27135 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eaf9a69f4e92 (Metraipolis archive dc_eaf9a69f4e92, sha256 e0d71e18ba9d23fe6c4f6a9ee68cc2e50a3ba031bc05d809104d56d3e8830ca0)
BibTeX
@misc{dceaf9a69f4e92,
  title = {Mind Your Boundaries: Boundary-Aware Model Obfuscation against Cross-node Attack — arXiv:2610.27135},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.27135},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eaf9a69f4e92; sha256 e0d71e18ba9d23fe6c4f6a9ee68cc2e50a3ba031bc05d809104d56d3e8830ca0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.27135. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

With the advancement of powerful AI chips, on-device machine learning is gaining traction for its low latency and privacy protection. However, when edge devices are compromised, attackers can obtain white-box access to the deployed models by reversing the apps directly to obtain the knowledge of peer devices, which is known as Cross-Node Attacks, like performing efficient adversarial attacks. Most existing defenses target known vulnerabilities, yet white-box access still enables attackers to uncover more unknown weaknesses. This creates a critical risk for edge-device deployments, where one compromised device can endanger all models distributed from the same source. Motivated by findings that the model robustness is primarily influenced by the curvature of the decision boundary, we investigate how model parameters shape its curvature. In this paper, we propose a novel method, BMO, that obfuscates model parameters to diversify the decision boundary further resisting cross-node attack while preserving its benign accuracy. Specifically, we explore decomposing model parameters into boundary-position and boundary-curvature components based on null-space constraints, then models with differentiated decision boundaries are instantiated by injecting noise into the boundary-curvature component. Across all four major types of adversarial attacks with four widely-deployed on-device models, BMO achieves an average success rate of 68.68% in defense, far exceeding the most competitive baseline, which attains only 22.32% in defending against cross-node attacks. Moreover, BMO achieves comparable performance in benign accuracy compared with baselines.

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).
Pagina del lavoro: https://arxiv.org/abs/2610.27135 — 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 2026-10-21T07:05:43.525Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).