# JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift

arXiv: https://arxiv.org/abs/2504.19440 · HTML: https://mlsanity.com/paper/2504.19440/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 42 of its 74 references that are in the map.
- First posted on arXiv 28 Apr 2025.

## Placed in

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

## Builds on (most cited first, 30 of 42)

- [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)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [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)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://mlsanity.com/paper/2312.02119/) (2023)
- [WildChat: 1M ChatGPT Interaction Logs in the Wild](https://mlsanity.com/paper/2405.01470/) (2024)
- [How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs](https://mlsanity.com/paper/2401.06373/) (2024)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models](https://mlsanity.com/paper/2306.11698/) (2023)
- ["Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models](https://mlsanity.com/paper/2308.03825/) (2023)
- [Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples](https://mlsanity.com/paper/1605.07277/) (2016)
- [StruQ: Defending Against Prompt Injection with Structured Queries](https://mlsanity.com/paper/2402.06363/) (2024)
- [Low-Resource Languages Jailbreak GPT-4](https://mlsanity.com/paper/2310.02446/) (2023)
- [LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked](https://mlsanity.com/paper/2308.07308/) (2023)
- [JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks](https://mlsanity.com/paper/2404.03027/) (2024)
- [Automatically Auditing Large Language Models via Discrete Optimization](https://mlsanity.com/paper/2303.04381/) (2023)
- [Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming](https://mlsanity.com/paper/2501.18837/) (2025)
- [COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability](https://mlsanity.com/paper/2402.08679/) (2024)
- [AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs](https://mlsanity.com/paper/2404.16873/) (2024)
- [Evaluating Frontier Models for Dangerous Capabilities](https://mlsanity.com/paper/2403.13793/) (2024)
- [GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis](https://mlsanity.com/paper/2402.13494/) (2024)
- [Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities](https://mlsanity.com/paper/2308.12833/) (2023)

## Built on by (most cited first, 5 of 5)

- [SoK: Evaluating Jailbreak Guardrails for Large Language Models](https://mlsanity.com/paper/2506.10597/) (2025)
- [Preventing Prompt Injection with Type-Directed Privilege Separation](https://mlsanity.com/paper/2509.25926/) (2025)
- [Confidently Wrong: Severity-Aware Calibration of Prompt-Injection Detectors under Attack Shift](https://mlsanity.com/paper/2606.22659/) (2026)
- [BinaryShield: Cross-Service Threat Intelligence in LLM Services using Privacy-Preserving Fingerprints](https://mlsanity.com/paper/2509.05608/) (2025)
- [Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers](https://mlsanity.com/paper/2608.14089/) (2026)

## Abstract (arXiv)

Safety and security remain critical concerns in AI deployment. Despite safety training through reinforcement learning with human feedback (RLHF) [ 32], language models remain vulnerable to jailbreak attacks that bypass safety guardrails. Universal jailbreaks - prefixes that can circumvent alignment for any payload - are particularly concerning. We show empirically that jailbreak detection systems face distribution shift, with detectors trained at one point in time performing poorly against newer exploits. To study this problem, we release JailbreaksOverTime, a comprehensive dataset of timestamped real user interactions containing both benign requests and jailbreak attempts collected over 10 months. We propose a two-pronged method for defenders to detect new jailbreaks and continuously update their detectors. First, we show how to use continuous learning to detect jailbreaks and adapt rapidly to new emerging jailbreaks. While detectors trained at a single point in time eventually fail due to drift, we find that universal jailbreaks evolve slowly enough for self-training to be effective. Retraining our detection model weekly using its own labels - with no new human labels - reduces the false negative rate from 4% to 0.3% at a false positive rate of 0.1%. Second, we introduce an unsupervised active monitoring approach to identify novel jailbreaks. Rather than classifying inputs directly, we recognize jailbreaks by their behavior, specifically, their ability to trigger models to respond to known-harmful prompts. This approach has a higher false negative rate (4.1%) than supervised methods, but it successfully identified some out-of-distribution attacks that were missed by the continuous learning approach.