mlsanityData to 14 Oct 2026

New Wide-Net-Casting Jailbreak Attacks Risk Large Models

arXiv 2605.17128 ↗First posted 16 May 2026cs.CR cs.AIcited by 0

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

Jailbreak attacks on large models have drawn growing attention due to their close ties to societal safety. This work identifies a practical yet unexplored jailbreak scenario, the wide-net-casting scenario, where an adversary can query a group of large models instead of a single one to elicit harmful outputs. Our analysis reveals substantial yet previously overlooked safety risks under this scenario. As a key part of our analysis, we further develop a novel jailbreak method tailored to the wide-net-casting scenario. With this tailored method, the jailbreak success rate can even reach 100% in some experiments when targeting the large models without additional safeguards, exposing wide-net-casting as a distinct, high-risk scenario that warrants attention in future evaluation and defense research.

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 49 of its 57 references that are in the map. First posted on arXiv 16 May 2026.

Builds on

49 of 57 references.

Closest ancestors · 12

Same direction, newest first

  1. 2025Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy26 Mar
  2. 2024Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment27 Nov
  3. 2024RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction25 Oct
  4. 2024Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities24 Oct
  5. 2024Virtual Context: Enhancing Jailbreak Attacks with Special Token Injection28 Jun
  6. 2024Jailbreaking as a Reward Misspecification Problem20 Jun
  7. 2024Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis16 Jun
  8. 2024Improved Techniques for Optimization-Based Jailbreaking on Large Language Models31 May
  9. 2024AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs21 Apr
  10. 2024AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs11 Apr
  11. 2023AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models3 Oct
  12. 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul

Other references · 37

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  6. 2023Visual Instruction Tuningcited by 7,869
  7. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  8. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  9. 2023Qwen Technical Reportcited by 3,344
  10. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  11. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  12. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
25 more
  1. 2021Convex optimizationcited by 2,515
  2. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,255
  3. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,207
  4. 2024ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Toolscited by 1,121
  5. 2023A Survey on Multimodal Large Language Modelscited by 909
  6. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 864
  7. 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Datasetcited by 860
  8. 2023Visual Adversarial Examples Jailbreak Aligned Large Language Modelscited by 328
  9. 2023MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Modelscited by 274
  10. 2023Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Modelscited by 273
  11. 2024Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Modelscited by 167
  12. 2024Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Modelscited by 136
  13. 2023From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Modelscited by 98
  14. 2024Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreakscited by 48
  15. 2025Distraction is All You Need for Multimodal Large Language Model Jailbreakingcited by 36
  16. 2025Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injectioncited by 25
  17. 2024Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealingcited by 12
  18. 2024Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Modelscited by 12
  19. 2025Safety Alignment Can Be Not Superficial With Explicit Safety Signalscited by 9
  20. 2025Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalitiescited by 7
  21. 2023Realistic Noise Synthesis with Diffusion Modelscited by 5
  22. 2024Annealed Winner-Takes-All for Motion Forecastingcited by 4
  23. 2024Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Modelscited by 4
  24. 2026DiffGraph: An Automated Agent-driven Model Merging Framework for In-the-Wild Text-to-Image Generationcited by 4
  25. 2025AVAM: Universal Training-free Adaptive Visual Anchoring Embedded into Multimodal Large Language Model for Multi-image Question Answeringcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models
  2. 2025Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space
  3. 2025SafeInt: Shielding Large Language Models from Jailbreak Attacks via Safety-Aware Representation Intervention
  4. 2024Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring
  5. 2025Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval
  6. 2026Systematic Scaling Analysis of Jailbreak Attacks in Large Language Models
  7. 2024Rapid Response: Mitigating LLM Jailbreaks with a Few Examples
  8. 2026JailMeter: An Evidence-Based Evaluation Framework for Jailbreak Attacks on Large Language Models