mlsanityData to 14 Oct 2026

Enhancing Jailbreak Attacks with Diversity Guidance

arXiv 2403.00292 ↗First posted 1 Mar 2024cs.CLcited by 0

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

As large language models(LLMs) become commonplace in practical applications, the security issues of LLMs have attracted societal concerns. Although extensive efforts have been made to safety alignment, LLMs remain vulnerable to jailbreak attacks. We find that redundant computations limit the performance of existing jailbreak attack methods. Therefore, we propose DPP-based Stochastic Trigger Searching (DSTS), a new optimization algorithm for jailbreak attacks. DSTS incorporates diversity guidance through techniques including stochastic gradient search and DPP selection during optimization. Detailed experiments and ablation studies demonstrate the effectiveness of the algorithm. Moreover, we use the proposed algorithm to compute the risk boundaries for different LLMs, providing a new perspective on LLM safety evaluation.

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 27 of its 46 references that are in the map. First posted on arXiv 1 Mar 2024.

Builds on

27 of 46 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation10 Oct
  2. 2023Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations10 Oct
  3. 2023Detecting Language Model Attacks with Perplexity27 Aug
  4. 2023Jailbroken: How Does LLM Safety Training Fail?5 Jul

Other references · 23

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  4. 2020Extracting Training Data from Large Language Modelscited by 2,189
  5. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,255
  6. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,154
  7. 2022Red Teaming Language Models with Language Modelscited by 1,026
  8. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 722
  9. 2023Baseline Defenses for Adversarial Attacks Against Aligned Language Modelscited by 651
  10. 2019Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classificationcited by 404
  11. 2023Multi-step Jailbreaking Privacy Attacks on ChatGPTcited by 333
  12. 2021Gradient-based Adversarial Attacks against Text Transformerscited by 234
11 more
  1. 2024ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMscited by 216
  2. 2023Automatically Auditing Large Language Models via Discrete Optimizationcited by 191
  3. 2022Fine-tuning language models to find agreement among humans with diverse preferencescited by 189
  4. 2023MART: Improving LLM Safety with Multi-round Automatic Red-Teamingcited by 163
  5. 2024Attacks, Defenses and Evaluations for LLM Conversation Safety: A Surveycited by 130
  6. 2023FLIRT: Feedback Loop In-context Red Teamingcited by 83
  7. 2023Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilitiescited by 82
  8. 2023Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competitioncited by 68
  9. 2022Adversarial Training for High-Stakes Reliabilitycited by 60
  10. 2024Benchmarking Knowledge Boundary for Large Language Models: A Different Perspective on Model Evaluationcited by 38
  11. 2019Multi-Document Summarization with Determinantal Point Processes and Contextualized Representationscited by 16

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space
  2. 2025Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints
  3. 2024Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization
  4. 2024Distract Large Language Models for Automatic Jailbreak Attack
  5. 2026Re-Triggering Safeguards within LLMs for Jailbreak Detection
  6. 2024JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs
  7. 2024Rapid Response: Mitigating LLM Jailbreaks with a Few Examples
  8. 2025Stand on The Shoulders of Giants: Building JailExpert from Previous Attack Experience