# CURE cuts jailbreak attack success rate from 47.20% to 1.36%

> Original title: How does CURE perform across LLaDA-8B-Instruct,Dream-v0-Instruct-7B, and LLaDA-1.5 on 5 major jailbreak benchmarks (Wild Jailbreak, JBB-B...

- Source: BAAI
- Published: 2026-10-29T13:26:00.000Z
- Bad Influence: https://badinfluence.news/items/rl2rq1fmr0mvxvsca5wuae60u
- Original: https://x.com/BAAIBeijing/status/2115797301163589824

## Summary

BAAI reports that CURE reduces average attack success rate across five jailbreak benchmarks from 47.20% to 1.36% on LLaDA-8B-Instruct, Dream-v0-Instruct-7B, and LLaDA-1.5. On PAD-AdvBench and DIJA-AdvBench, CURE cuts LLaDA-8B's attack success rate from 93.65% and 98.65% to 4.42% and 4.23%. On MMLU and GSM8K, LLaDA-8B's defense success rate rises from 51.00% to 98.17%, while its average utility accuracy increases from 65.68% to 68.48%.

## Post

How does CURE perform across LLaDA-8B-Instruct,Dream-v0-Instruct-7B, and LLaDA-1.5 on 5 major jailbreak benchmarks (Wild Jailbreak, JBB-Behaviors, HarmBench, PAD-AdvBench, DIJA-AdvBench)?

🛡️Crushing Jailbreak Attacks (Lowest ASR Across All Models)：
• Cuts average ASR from 47.20% down to 1.36%(1.83%on LLaDA-8B,2.19%on LLaDA-1.5, and near-zero 0.06% on Dream-7B!)

• Excels against early-anchor attacks (PAD & DIJA), slashing LLaDA-8B ASR from 93.65% / 98.65% down to 4.42% / 4.23%.

📈Pushing the Safety–Utility Pareto Frontier:
• On MMLU & GSM8K, CURE preserves base capabilities without over-refusal—boosting LLaDA-8B defense success from 51.00% to 98.17%while increasing average utility accuracy from65.68% to 68.48%!

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHVyyynqaAAA1nWY.png&mode=thumb&exp=1793491200&sig=9f23fea5544d79f3)

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHVyyynqacAA71_2.png&mode=thumb&exp=1793491200&sig=f4b5d31f675fb6d9)