# Researchers introduce CoFiBreak to improve jailbreak attack diversity in LLMs

Digest AI · Research · published 2026-11-02T05:00:00Z

Canonical: https://digestai.news/story/researchers-introduce-cofibreak-to-improve-jailbreak-attack-diversity

## Summary

A new method called CoFiBreak aims to enhance the diversity of jailbreak attacks on large language models (LLMs) while maintaining effectiveness. Developed by researchers, CoFiBreak uses a coarse-to-fine diversity reward within Group Relative Policy Optimization (GRPO) to broaden the range of attack strategies without sacrificing success rates or inference efficiency. The approach ensures attacks exceed an effectiveness threshold before diversity rewards are applied, preventing ineffective strategies from skewing results.

Tests on frontier LLMs show CoFiBreak discovers 1.6 to 2.0 times more distinct successful strategies than existing methods on HarmBench. It achieves a 98.8% attack success rate (ASR@10) on AdvBench with the highest diversity score, outperforming baselines by 2.1x. The method also transfers well to unseen models like Claude-Opus-4.6, achieving a 71.0% ASR@10. The code will be publicly released.

## Key points

- CoFiBreak improves jailbreak attack diversity in LLMs using a coarse-to-fine reward system within GRPO
- Method achieves 1.6–2.0x more distinct successful strategies than baselines on HarmBench
- Reaches 98.8% ASR@10 on AdvBench with highest diversity score, transferring to unseen models like Claude-Opus-4.6

## Why it matters

CoFiBreak addresses a critical gap in AI safety testing by ensuring jailbreak attacks cover broader harmful intents, not just repetitive prompts. This could improve how researchers evaluate and defend against LLM vulnerabilities, though it also raises ethical concerns about attack capabilities.

## Sources

1. [CoFiBreak: A Coarse-to-Fine Diversity Reward for Effective Multi-Turn Jailbreak](https://arxiv.org/abs/2610.40926) (arXiv cs.CL, 2026-11-02, primary source)

## Cite

Digest AI, "Researchers introduce CoFiBreak to improve jailbreak attack diversity in LLMs", 2 November 2026, https://digestai.news/story/researchers-introduce-cofibreak-to-improve-jailbreak-attack-diversity

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/researchers-introduce-cofibreak-to-improve-jailbreak-attack-diversity.json