LLM Jailbreak Detection for (Almost) Free!

• URL: http://arxiv.org/abs/2509.14558v1
• Date: Thu, 18 Sep 2025 02:42:52 GMT
• Title: LLM Jailbreak Detection for (Almost) Free!
• Authors: Guorui Chen, Yifan Xia, Xiaojun Jia, Zhijiang Li, Philip Torr, Jindong Gu,
• Abstract summary: Large language models (LLMs) enhance security through alignment when widely used, but remain susceptible to jailbreak attacks.<n>Jailbreak detection methods show promise in mitigating jailbreak attacks through the assistance of other models or multiple model inferences.<n>We propose a Free Jailbreak Detection (FJD) which prepends an affirmative instruction to the input and scales the logits by temperature to further distinguish between jailbreak and benign prompts.
• Score: 62.466970731998714
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) enhance security through alignment when widely used, but remain susceptible to jailbreak attacks capable of producing inappropriate content. Jailbreak detection methods show promise in mitigating jailbreak attacks through the assistance of other models or multiple model inferences. However, existing methods entail significant computational costs. In this paper, we first present a finding that the difference in output distributions between jailbreak and benign prompts can be employed for detecting jailbreak prompts. Based on this finding, we propose a Free Jailbreak Detection (FJD) which prepends an affirmative instruction to the input and scales the logits by temperature to further distinguish between jailbreak and benign prompts through the confidence of the first token. Furthermore, we enhance the detection performance of FJD through the integration of virtual instruction learning. Extensive experiments on aligned LLMs show that our FJD can effectively detect jailbreak prompts with almost no additional computational costs during LLM inference.

Related papers

• Machine Learning for Detection and Analysis of Novel LLM Jailbreaks [3.2654923574107357]
  Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text.<n>These so-called jailbreak prompts are designed to trick the LLM into circumventing the safety guardrails put in place to keep responses acceptable to the developer's policies.<n>In this study, we analyse the ability of different machine learning models to distinguish jailbreak prompts from genuine uses.
  arXiv  Detail & Related papers  (2025-10-02T03:55:29Z)
• Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models [80.66766532477973]
  Test-time IMmunization (TIM) can adaptively defend against various jailbreak attacks in a self-evolving way.<n>Test-time IMmunization (TIM) can adaptively defend against various jailbreak attacks in a self-evolving way.
  arXiv  Detail & Related papers  (2025-05-28T11:57:46Z)
• Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness Instruction [32.49886313949869]
  We propose a transferable black-box jailbreak method to attack Large Language Models (LLMs)<n>We find that this rewriting approach is learnable and transferable.<n> Extensive experiments and analysis demonstrate the effectiveness of R2J.
  arXiv  Detail & Related papers  (2025-02-16T11:43:39Z)
• JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation [22.75124155879712]
  Large language models (LLMs) remain vulnerable to jailbreak attacks.<n>We propose a comprehensive jailbreak defense framework, JBShield, consisting of two key components: jailbreak detection JBShield-D and mitigation JBShield-M.
  arXiv  Detail & Related papers  (2025-02-11T13:50:50Z)
• xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking [32.89084809038529]
  Black-box jailbreak is an attack where crafted prompts bypass safety mechanisms in large language models.<n>We propose a novel black-box jailbreak method leveraging reinforcement learning (RL)<n>We introduce a comprehensive jailbreak evaluation framework incorporating keywords, intent matching, and answer validation to provide a more rigorous and holistic assessment of jailbreak success.
  arXiv  Detail & Related papers  (2025-01-28T06:07:58Z)
• LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds [98.20826635707341]
  Jailbreak attacks expose vulnerabilities in safety-aligned LLMs by eliciting harmful outputs through carefully crafted prompts.<n>We frame jailbreaks as inference-time misalignment and introduce LIAR, a fast, black-box, best-of-$N$ sampling attack requiring no training.<n>We also introduce a theoretical "safety net against jailbreaks" metric to quantify safety alignment strength and derive suboptimality bounds.
  arXiv  Detail & Related papers  (2024-12-06T18:02:59Z)
• EnJa: Ensemble Jailbreak on Large Language Models [69.13666224876408]
  Large Language Models (LLMs) are increasingly being deployed in safety-critical applications. LLMs can still be jailbroken by carefully crafted malicious prompts, producing content that violates policy regulations. We propose a novel EnJa attack to hide harmful instructions using prompt-level jailbreak, boost the attack success rate using a gradient-based attack, and connect the two types of jailbreak attacks via a template-based connector.
  arXiv  Detail & Related papers  (2024-08-07T07:46:08Z)
• Efficient Indirect LLM Jailbreak via Multimodal-LLM Jailbreak [62.56901628534646]
  This paper focuses on jailbreaking attacks against large language models (LLMs)<n>Our approach surpasses current state-of-the-art jailbreak methods in terms of both efficiency and effectiveness.
  arXiv  Detail & Related papers  (2024-05-30T12:50:32Z)
• EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models [53.87416566981008]
  This paper introduces EasyJailbreak, a unified framework simplifying the construction and evaluation of jailbreak attacks against Large Language Models (LLMs) It builds jailbreak attacks using four components: Selector, Mutator, Constraint, and Evaluator. Our validation across 10 distinct LLMs reveals a significant vulnerability, with an average breach probability of 60% under various jailbreaking attacks.
  arXiv  Detail & Related papers  (2024-03-18T18:39:53Z)
• A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily [51.63085197162279]
  Large Language Models (LLMs) are designed to provide useful and safe responses. adversarial prompts known as 'jailbreaks' can circumvent safeguards. We propose ReNeLLM, an automatic framework that leverages LLMs themselves to generate effective jailbreak prompts.
  arXiv  Detail & Related papers  (2023-11-14T16:02:16Z)
• Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks [12.540530764250812]
  We propose a formalism and a taxonomy of known (and possible) jailbreaks. We release a dataset of model outputs across 3700 jailbreak prompts over 4 tasks.
  arXiv  Detail & Related papers  (2023-05-24T09:57:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.