AI Paper Atlas

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

EquaCode: A Multi-Strategy Jailbreak Approach for Large Language Models via Equation Solving and Code Completion

Zhen Liang, Hai Huang, Zhengkui Chen

AAAI 2026 · Large language models › Language, safety and interpretability · approach: Jailbreak attacks and defenses · 2 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 equation module on top of natural-language step decomposition (STSA) (ablation)jailbreak prompts · AdvBench subset 50, LLaMA-ASR, 6-LLM averageASR (%): 17.33 -> 44.67Improved
add code-completion wrapper to STSA (ablation)jailbreak prompts · AdvBench subset 50, LLaMA-ASR, 6-LLM averageASR (%): 17.33 -> 65.73Improved
add code module to equation module (ablation)EquaCode · AdvBench subset 50, LLaMA-ASR, 6-LLM averageASR (%): 44.67 -> 87.33Improved
add equation module to code module (ablation)EquaCode · AdvBench subset 50, LLaMA-ASR, 6-LLM averageASR (%): 65.73 -> 87.33Improved
add equation module to STSA on GPT-3.5-turbo (ablation)GPT-3.5-turbo · AdvBench subset 50, LLaMA-ASRASR (%): 76.00 -> 74.00Hurt
add equation module to STSA on GPT-4o and GPT-4o-mini (ablation)GPT-4o, GPT-4o-mini · AdvBench subset 50, LLaMA-ASRASR (%): 0 -> 30 (GPT-4o), 0 -> 16 (GPT-4o-mini)Improved
EquaCode versus FlipAttack on Llama-3.1-405BLlama-3.1-405B · AdvBench (520, GPT-ASR)ASR (%): 27.50 -> 17.88Hurt
EquaCode versus CodeChameleon on GPT-4oGPT-4o · AdvBench (520, GPT-ASR)ASR (%): 92.67 -> 87.12Hurt
use EquaCode against Llama Guard 7B moderationLlama Guard 7B · defensebypass rate (%): 100%Improved
apply output filtering defense against EquaCodeEquaCode · defenseattack success rate (%): 14% success under output filterHurt

Later papers that compared with this method

1 later accepted paper reports EquaCode as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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