AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

HyperGLLM: An Efficient Framework for Endpoint Threat Detection via Hypergraph-Enhanced Large Language Models

Hongyi Zhou, Jianfeng Pan, Min Peng, Shaomang Huang, Hanzhong Zheng

AAAI 2026 · Large language models › Language, safety and interpretability · approach: Data and hallucination detection · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add differential hypergraph network (DHGNN) (ablation)HyperGLLM · EDR3.6B-63FBinary accuracy: 93.90 -> 99.11Improved
add differential hypergraph network (DHGNN) (ablation)HyperGLLM · EDR3.6B-63FOverall accuracy: 88.12 -> 94.65Improved
add global differential mechanism (ablation)HyperGLLM · EDR3.6B-63FBinary accuracy: 94.94 -> 99.11Improved
add global differential mechanism (ablation)HyperGLLM · EDR3.6B-63FOverall accuracy: 89.58 -> 94.65Improved
use multi-granularity clustering instead of coarsest single level (ablation)HyperGLLM · EDR3.6B-63FOverall accuracy: 84.34 -> 94.65Improved
use multi-granularity clustering instead of finest single level (ablation)HyperGLLM · EDR3.6B-63FOverall accuracy: 85.29 -> 94.65Improved
raise max clustering scale S from 3 to 6 (ablation)HyperGLLM · EDR3.6B-63FBinary accuracy: 94.53 -> 99.11Improved
raise max clustering scale S from 6 to 7 (ablation)HyperGLLM · EDR3.6B-63FBinary accuracy: 99.11 -> 94.14Hurt
add hypergraph compression to the LLM versus fine-tuned long-context LLMHyperGLLM vs LongRoPE · EDR3.6B-63FOverall accuracy: 86.31 -> 94.65Improved
replace long-context LLM with HyperGLLM on unseen attacksHyperGLLM vs LongRoPE · EDR3.6B-63F unseen attacksBinary accuracy: 86.20 -> 97.98Improved
replace long-context LLM with HyperGLLM on ATLASv2HyperGLLM vs LongRoPE · ATLASv2 (host 2)Binary accuracy: 69.4 -> 88.1Improved
use HyperGLLM instead of baseline LLMs at 1M-token inputHyperGLLM vs Qwen2.5-3B/LLaMA3-8B · EDR3.6B-63FGPU memory and TTFT: less than 1/15 and 1/1000 of the baselinesImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy