# Online Learning Defense against Iterative Jailbreak Attacks via Prompt Optimization

arXiv: https://arxiv.org/abs/2510.17006 · HTML: https://mlsanity.com/paper/2510.17006/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 32 of its 48 references that are in the map.
- First posted on arXiv 19 Oct 2025.

## Placed in

- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 30 of 32)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks](https://mlsanity.com/paper/1312.6211/) (2013)
- [Universal Adversarial Triggers for Attacking and Analyzing NLP](https://mlsanity.com/paper/1908.07125/) (2019)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [Baseline Defenses for Adversarial Attacks Against Aligned Language Models](https://mlsanity.com/paper/2309.00614/) (2023)
- [SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks](https://mlsanity.com/paper/2310.03684/) (2023)
- [Deliberative Alignment: Reasoning Enables Safer Language Models](https://mlsanity.com/paper/2412.16339/) (2024)
- [ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs](https://mlsanity.com/paper/2402.11753/) (2024)
- [BPE-Dropout: Simple and Effective Subword Regularization](https://mlsanity.com/paper/1910.13267/) (2019)
- [GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis](https://mlsanity.com/paper/2402.13494/) (2024)
- [JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation](https://mlsanity.com/paper/2502.07557/) (2025)
- [Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs](https://mlsanity.com/paper/2402.14872/) (2024)
- [Debiasing isn't enough! -- On the Effectiveness of Debiasing MLMs and their Social Biases in Downstream Tasks](https://mlsanity.com/paper/2210.02938/) (2022)
- [Principled Instructions Are All You Need for Questioning LLaMA-1/2, GPT-3.5/4](https://mlsanity.com/paper/2312.16171/) (2023)
- [Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks](https://mlsanity.com/paper/2405.20099/) (2024)
- [Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings](https://mlsanity.com/paper/2412.13879/) (2024)
- [DETAM: Defending LLMs Against Jailbreak Attacks via Targeted Attention Modification](https://mlsanity.com/paper/2504.13562/) (2025)

## Built on by (most cited first, 3 of 3)

- [Paraphrasing Adversarial Attack on LLM-as-a-Reviewer](https://mlsanity.com/paper/2601.06884/) (2026)
- [JailNewsBench: Multi-Lingual and Regional Benchmark for Fake News Generation under Jailbreak Attacks](https://mlsanity.com/paper/2603.01291/) (2026)
- [In-Context Learning as Implicit Policy Gradient](https://mlsanity.com/paper/2607.23153/) (2026)

## Abstract (arXiv)

Iterative jailbreak methods that repeatedly rewrite and input prompts into large language models (LLMs) to induce harmful outputs -- using the model's previous responses to guide each new iteration -- have been found to be a highly effective attack strategy. Despite being an effective attack strategy against LLMs and their safety mechanisms, existing defenses do not proactively disrupt this dynamic trial-and-error cycle. In this study, we propose a novel framework that dynamically updates its defense strategy through online learning in response to each new prompt from iterative jailbreak methods. Leveraging the distinctions between harmful jailbreak-generated prompts and typical harmless prompts, we introduce a reinforcement learning-based approach that optimizes prompts to ensure appropriate responses for harmless tasks while explicitly rejecting harmful prompts. Additionally, to curb overfitting to the narrow band of partial input rewrites explored during an attack, we introduce Past-Direction Gradient Damping (PDGD). Experiments conducted on three LLMs show that our approach significantly outperforms five existing defense methods against five iterative jailbreak methods. Moreover, our results indicate that our prompt optimization strategy simultaneously enhances response quality for harmless tasks.