← Back to all news
arXiv AI By Boyang Li, Bingyu Shen, Weihao Hong, Zhiyuan Jiang, Xinlei Guan, Yan Ma, Miles Q. Li, Yi Sheng, Ruiyang Qin

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

Read the original on arXiv AI →

MOMAT (Mixture of Multiple Atlases) is a hardware‑enhanced safety framework designed to defend quantized large language models (qLLMs) on edge devices against jailbreak attacks. It uses a collection of semantic atlases—each containing harmful or benign sample clusters and policy templates—to perform domain‑localized Retrieval‑Augmented Generation. A lightweight Mixture of Experts detector evaluates top‑k similarity features retrieved by a Compute‑in‑Memory (CiM) accelerated engine, achieving a 4.69 × 10⁶‑fold speedup and a 2.5 × 10⁵‑fold energy reduction compared to DRAM‑based baselines while matching state‑of‑the‑art defense performance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Jul 21

TurboVec: A Case Study in Cost-Efficient Private Retrieval for Enterprise RAG via Codebook-Oblivious Quantization

arXiv:2607. 16973v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems increasingly power enterprise LLM applications, yet the vector retrieval layer introduces two underexplored challenges: (1) trained codebook quantizers may expose corpus statistics during index construction, creating a leakage channel in multi-tenant deployments, and (2) post-hoc filtering for tenant isolation degrades recall on selective queries.

By Navnit Shukla, Kamal Pandey, Omsankar Tiwari
llmsragefficiencybenchmarkssafety
More like this →
arXiv Machine Learning
Aug 19

Reflex-Guard: A Low-Latency Guardrail for LLM Prompt Safety Using Dense Semantic Embeddings

Reflex-Guard is a lightweight, locally‑run guardrail for large language models that uses jailbreak‑aware preprocessing, compact sentence‑transformer embeddings, and seven fast binary classifiers to filter unsafe prompts. It achieves 95.9 % recall on harmful prompts with an end‑to‑end latency of 37.6 ms, outperforming existing solutions such as Llama Guard 2 (255 ms) and SafeDecoding (723 ms). The system can detect all GCG suffix attacks and Base64‑encoded prompts at the default threshold, while DrAttack structured prompts require a lower threshold of 0.03 for optimal detection, and it attains a Reflex Efficiency Score of up to 16.79.

By Istiaque Ahmed, Afia Anjum Borsha, Ranat Das Prangon, Abu-fuad Ahmad, Thi Hong Tran
llmsragsafety
More like this →