Re-Triggering Safeguards within LLMs for Jailbreak Detection
On the map: LLM safety and security → Jailbreaking
Abstract (arXiv)
This paper proposes a jailbreaking prompt detection method for large language models (LLMs) to defend against jailbreak attacks. Although recent LLMs are equipped with built-in safeguards, it remains possible to craft jailbreaking prompts that bypass them. We argue that such jailbreaking prompts are inherently fragile, and thus introduce an embedding disruption method to re-activate the safeguards within LLMs. Unlike previous defense methods that aim to serve as standalone solutions, our approach instead cooperates with the LLM's internal defense mechanisms by re-triggering them. Moreover, through extensive analysis, we gain a comprehensive understanding of the disruption effects and develop an efficient search algorithm to identify appropriate disruptions for effective jailbreak detection. Extensive experiments demonstrate that our approach effectively defends against state-of-the-art jailbreak attacks in white-box and black-box settings, and remains robust even against adaptive attacks.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 21 of its 23 references that are in the map. First posted on arXiv 11 May 2026.
Builds on
21 of 23 references.
Closest ancestors · 10
Same direction, newest first
- 2025Smoothed Embeddings for Robust Language Models27 Jan
- 2024AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs3 Oct
- 2024Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses3 Jun
- 2024Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks2 Apr
- 2024JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models28 Mar
- 2023Jailbreaking Black Box Large Language Models in Twenty Queries12 Oct
- 2023Certifying LLM Safety against Adversarial Prompting6 Sep
- 2023Detecting Language Model Attacks with Perplexity27 Aug
- 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul
- 2023Jailbroken: How Does LLM Safety Training Fail?5 Jul
Other references · 11
- 2022Training language models to follow instructions with human feedbackcited by 15,971
- 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
- 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
- 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalcited by 1,429
- 2023Instruction-Following Evaluation for Large Language Modelscited by 1,228
- 2024Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluatorscited by 897
- 2023Baseline Defenses for Adversarial Attacks Against Aligned Language Modelscited by 651
- 2023Pretraining Language Models with Human Preferencescited by 247
- 2019BPE-Dropout: Simple and Effective Subword Regularizationcited by 195
- 2023On the Reliability of Watermarks for Large Language Modelscited by 189
- 2021Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Modelscited by 105
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks
- 2023Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks
- 2024Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis
- 2025Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval
- 2023A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily
- 2025Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement
- 2025You Can't Eat Your Cake and Have It Too: The Performance Degradation of LLMs with Jailbreak Defense
- 2024Subtoxic Questions: Dive Into Attitude Change of LLM's Response in Jailbreak Attempts