mlsanityData to 14 Oct 2026

Exploring Jailbreak Attacks on LLMs through Intent Concealment and Diversion

arXiv 2505.14316 ↗First posted 20 May 2025cs.CR cs.AIcited by 9

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

Although large language models (LLMs) have achieved remarkable advancements, their security remains a pressing concern. One major threat is jailbreak attacks, where adversarial prompts bypass model safeguards to generate harmful or objectionable content. Researchers study jailbreak attacks to understand security and robustness of LLMs. However, existing jailbreak attack methods face two main challenges: (1) an excessive number of iterative queries, and (2) poor generalization across models. In addition, recent jailbreak evaluation datasets focus primarily on question-answering scenarios, lacking attention to text generation tasks that require accurate regeneration of toxic content. To tackle these challenges, we propose two contributions: (1) ICE, a novel black-box jailbreak method that employs Intent Concealment and divErsion to effectively circumvent security constraints. ICE achieves high attack success rates (ASR) with a single query, significantly improving efficiency and transferability across different models. (2) BiSceneEval, a comprehensive dataset designed for assessing LLM robustness in question-answering and text-generation tasks. Experimental results demonstrate that ICE outperforms existing jailbreak techniques, revealing critical vulnerabilities in current defense mechanisms. Our findings underscore the necessity of a hybrid security strategy that integrates predefined security mechanisms with real-time semantic decomposition to enhance the security of LLMs.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 21 of its 37 references that are in the map. First posted on arXiv 20 May 2025.

Builds on

21 of 37 references.

Closest ancestors · 9

Same direction, newest first

  1. 2024Jailbreak Attacks and Defenses Against Large Language Models: A Survey5 Jul
  2. 2024Distract Large Language Models for Automatic Jailbreak Attack13 Mar
  3. 2024Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction28 Feb
  4. 2024Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue27 Feb
  5. 2024A StrongREJECT for Empty Jailbreaks15 Feb
  6. 2024COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability13 Feb
  7. 2023A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily14 Nov
  8. 2023Jailbreaking Black Box Large Language Models in Twenty Queries12 Oct
  9. 2023Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation10 Oct

Other references · 12

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  4. 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalcited by 1,429
  5. 2024Qwen2.5-Coder Technical Reportcited by 1,203
  6. 2020HateXplain: A Benchmark Dataset for Explainable Hate Speech Detectioncited by 407
  7. 2023Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attackscited by 278
  8. 2023Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignmentcited by 223
  9. 2023Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Healthcited by 118
  10. 2024From LLMs to MLLMs: Exploring the Landscape of Multimodal Jailbreakingcited by 24
  11. 2024Are You Human? An Adversarial Benchmark to Expose LLMscited by 5
  12. 2024Low-Resource Fast Text Classification Based on Intra-Class and Inter-Class Distance Calculationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 6.

9 papers.

  1. 2025From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystemcited by 12
  2. 2026Now You Hear Me: Audio Narrative Attacks Against Large Audio-Language Modelscited by 8
  3. 2025CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMscited by 5
  4. 2025Jailbreaking Large Language Models Through Content Concretizationcited by 2
  5. 2026Voices Across Registers: Corpus-Conditioned Vernacular Jailbreaks against Aligned LLMs via Fanfiction Subgenrescited by 1
  6. 2026ChartAttack: Testing the Vulnerability of LLMs to Malicious Prompting in Chart Generationcited by 0
  7. 2026Reasoning-targeted Jailbreak Attacks on Large Reasoning Models via Semantic Triggers and Psychological Framingcited by 0
  8. 2026The Evaluation Game: Beyond Static LLM Benchmarkingcited by 0
  9. 2026From Generation to Detection: Exploration of Discourse Driven Scenario based LLM Generated Fake Newscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Paper Summary Attack: Jailbreaking LLMs through LLM Safety Papers
  2. 2024Rapid Response: Mitigating LLM Jailbreaks with a Few Examples
  3. 2024Characterizing and Evaluating the Reliability of LLMs against Jailbreak Attacks
  4. 2024Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks
  5. 2026SoK: Robustness in Large Language Models against Jailbreak Attacks
  6. 2024JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks
  7. 2025Attack via Overfitting: 10-shot Benign Fine-tuning to Jailbreak LLMs
  8. 2024SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner