Metraipolis › archive › dc_feb48748c3dc

MOMAT: Mixture of Multiple Atlases for Low-Power Jailbreak Defense of Quantized LLMs — arXiv:2610.01058

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.01058
License (as archived): CC0-1.0
Archived: 2026-10-06T12:12:37.152Z
SHA-256 of the archived text: 53b3a6f33d0b24e32304a02772935149ea6939d70650114891b0f29f02d797b6
Stable URL of this page: https://metraipolis.com/documento/dc_feb48748c3dc

How to cite

MOMAT: Mixture of Multiple Atlases for Low-Power Jailbreak Defense of Quantized LLMs — arXiv:2610.01058 — arXiv (en), https://arxiv.org/abs/2610.01058 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_feb48748c3dc (Metraipolis archive dc_feb48748c3dc, sha256 53b3a6f33d0b24e32304a02772935149ea6939d70650114891b0f29f02d797b6)

BibTeX

@misc{dcfeb48748c3dc,
  title = {MOMAT: Mixture of Multiple Atlases for Low-Power Jailbreak Defense of Quantized LLMs — arXiv:2610.01058},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01058},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_feb48748c3dc; sha256 53b3a6f33d0b24e32304a02772935149ea6939d70650114891b0f29f02d797b6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01058. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Quantized large language models are increasingly deployed on edge devices for their low latency and energy efficiency. However, model quantization weakens alignment safeguards, leaving qLLMs (quantized large language models) highly vulnerable to jailbreak attacks. To address this challenge, we present MOMAT (Mixture of Multiple Atlases), a hardware-enhanced safety framework that combines structured knowledge retrieval with low-power defense acceleration. Each atlas represents a semantic cluster of harmful or benign sample sets and policy templates, enabling domain-localized Retrieval-Augmented Generation guarding that mitigates the curse of dimensionality and the resulting semantic sparsity problem in large, heterogeneous safety databases. MOMAT retrieves top-$k$ similarity features from all atlases for each prompt and evaluates them using a lightweight MoE (Mixture of Experts) detector, while a CiM (Compute-in-Memory)-accelerated similarity engine performs fast, low-power atlas-local retrieval. MOMAT's CiM-based retrieval accelerates a 100-query batch from 15,052.44 ms to 3,207.21 ns (a $4.69 \times 10^6\times$ speedup) and reduces energy from $8.1 \times 10^7$ $\mu$J to 3.32 $\mu$J, yielding an approximately $2.5 \times 10^5\times$ energy reduction over DRAM-based (Raspberry Pi) baselines. Red-team evaluations across standard benchmarks show that MOMAT matches the defense performance of state-of-the-art methods while avoiding benign overkill and providing substantial efficiency gains, demonstrating that CiM-based modular defenses can make edge-deployed qLLMs both safer and more energy-efficient. We will release the full 223.2k-sample dataset to foster future research.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.01058 — 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 2026-10-06T10:21:28.150Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).