AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

LoopLLM: Transferable Energy-Latency Attacks in LLMs via Repetitive Generation

Xingyu Li, Xiaolei Liu, Cheng Liu, Yixiao Xu, Kangyi Ding, Bangzhou Xin, Jia-Li Yin

AAAI 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: LLM jailbreak and injection defense · 9 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
induce repetitive generation instead of delaying EOS (LoopLLM-t vs Engorgio)energy-latency attack · Dialogue prompts, Llama3-8BASR: 1% -> 94%Improved
add token-aligned ensemble of Llama3-3B and Llama3-8B surrogates (ablation)LoopLLM-t transfer attack · Transfer to Phi4-miniASR: 49% -> 76%Improved
add Llama2-7B & 13B ensemble (ablation)LoopLLM-t transfer attack · Transfer to Vicuna-7BASR: 16% -> 42%Improved
ensemble of Llama2-7B & 13B instead of single Llama3-8B surrogate (ablation)LoopLLM-t transfer attack · Transfer to Mistral-7BASR: 33% -> 27%Hurt
use shorter cyclic segment (length 1 vs 5 vs 10) (ablation)LoopLLM · GLM4-9BASR: 88% -> 67%Improved
choose specific tokens instead of random vocabulary tokens for the cyclic segment (ablation)LoopLLM-t · GLM4-9BASR: 64% -> 88%Improved
add repeated-token halting defenseLoopLLM-t · Llama3-8BASR: 93% -> 14%Hurt
add repeated-token halting defenseLoopLLM-p · Llama3-8BASR: 79% -> 76%No clear effect
use beam search instead of greedy search (ablation)LoopLLM-t · GLM4-9BASR: 68% -> 94%Improved
raise sampling temperature to 1.2 (ablation)LoopLLM-t · GLM4-9BASR: 84% -> 61%Hurt
increase suffix length (ablation)LoopLLM · Avg-len and ASR vs suffix lengthAvg-len / ASRImproved
add more optimization steps (ablation)LoopLLM · Avg-len and ASR vs stepsAvg-len / ASRImproved

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