Papers › JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift
JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift
Julien Piet, Xiao Huang, Dennis Jacob, Annabella Chow, Maha Alrashed, Geng Zhao, Zhanhao Hu, Chawin Sitawarin, Basel Alomair, David Wagner
The archive published only this paper's code-link row. Authors, date and abstract are from arXiv's metadata (CC0), read from the Kaggle arXiv metadata snapshot of 2026-09-12 where its title matched the archive's; the title is the archive's.
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.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections