Jailbreaking Frontier Foundation Models Through Intention Deception

• URL: http://arxiv.org/abs/2604.24082v1
• Date: Mon, 27 Apr 2026 06:12:43 GMT
• Title: Jailbreaking Frontier Foundation Models Through Intention Deception
• Abstract summary: Large (vision-) models exhibit remarkable capability but remain highly susceptible to jailbreaking.<n>We introduce a novel multi-turn jailbreaking method that exploits this vulnerability.<n>Our approach also uncovered an additional class of model vulnerability that we call para-jailbreaking.
• Score: 6.119674554651102
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large (vision-)language models exhibit remarkable capability but remain highly susceptible to jailbreaking. Existing safety training approaches aim to have the model learn a refusal boundary between safe and unsafe, based on the user's intent. It has been found that this binary training regime often leads to brittleness, since the user intent cannot reliably be evaluated, especially if the attacker obfuscates their intent, and also makes the system seem unhelpful. In response, frontier models, such as GPT-5, have shifted from refusal-based safeguards to safe completion, that aims to maximize helpfulness while obeying safety constraints. However, safe completion could be exploited when a user pretends their intention is benign. Specifically, this intent inversion would be effective in multi-turn conversation, where the attacker has multiple opportunities to reinforce their deceptively benign intent. In this work, we introduce a novel multi-turn jailbreaking method that exploits this vulnerability. Our approach gradually builds conversational trust by simulating benign-seeming intentions and by exploiting the consistency property of the model, ultimately guiding the target model toward harmful, detailed outputs. Most crucially, our approach also uncovered an additional class of model vulnerability that we call para-jailbreaking that has been unnoticed up to now. Para-jailbreaking describes the situation where the model may not reveal harmful direct reply to the attack query, however the information that it reveals is nevertheless harmful. Our contributions are threefold. First, it achieves high success rates against frontier models including GPT-5-thinking and Claude-Sonnet-4.5. Second, our approach revealed and addressed para-jailbreaking harmful output. Third, experiments on multimodal VLM models showed that our approach outperformed state-of-the-art models.

Related papers

• Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack [19.201635180438313]
  Large language models (LLMs) are rigorously aligned to refuse harmful requests.<n>In this work, we reveal that this advanced safety awareness inadvertently introduces a fatal vulnerability.
  arXiv  Detail & Related papers  (2026-06-04T02:36:41Z)
• Bag of Tricks for Subverting Reasoning-based Safety Guardrails [62.139297207938036]
  We present a bag of jailbreak methods that subvert the reasoning-based guardrails.<n>Our attacks span white-, gray-, and black-box settings and range from effortless template manipulations to fully automated optimization.
  arXiv  Detail & Related papers  (2025-10-13T16:16:44Z)
• Refusal Falls off a Cliff: How Safety Alignment Fails in Reasoning? [68.82210578851442]
  We investigate why safety alignment fails in reasoning models through a mechanistic interpretability lens.<n>Using a linear probing approach to trace refusal intentions across token positions, we discover a phenomenon termed as textbfrefusal cliff<n>We propose textbfCliff-as-a-Judge, a novel data selection method that identifies training examples exhibiting the largest refusal cliff to efficiently repair reasoning models' safety alignment.
  arXiv  Detail & Related papers  (2025-10-07T15:32:59Z)
• Activation-Guided Local Editing for Jailbreaking Attacks [33.13949817155855]
  Token-level jailbreak attacks often produce incoherent or unreadable inputs.<n> prompt-level attacks lack scalability and rely heavily on manual effort and human ingenuity.<n>We propose a concise and effective two-stage framework that combines the advantages of these approaches.
  arXiv  Detail & Related papers  (2025-08-01T11:52:24Z)
• GRAF: Multi-turn Jailbreaking via Global Refinement and Active Fabrication [55.63412213263305]
  Large Language Models pose notable safety risks due to potential misuse for malicious purposes.<n>We propose a novel multi-turn jailbreaking method that globally refines the attack trajectory at each interaction.<n>In addition, we actively fabricate model responses to suppress safety-related warnings, thereby increasing the likelihood of eliciting harmful outputs.
  arXiv  Detail & Related papers  (2025-06-22T03:15:05Z)
• No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms [22.667573777927203]
  We present a new fine-tuning attack that trains models to first refuse harmful requests before answering them.<n>This "refuse-then-comply" strategy bypasses shallow defenses and produces harmful responses that evade output filters.<n>Our attack received a $2000 bug bounty from OpenAI and was acknowledged as a vulnerability by Anthropic.
  arXiv  Detail & Related papers  (2025-02-26T20:20:01Z)
• Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions [50.40122190627256]
  We introduce POATE, a novel jailbreak technique that harnesses contrastive reasoning to provoke unethical responses.<n>PoATE crafts semantically opposing intents and integrates them with adversarial templates, steering models toward harmful outputs with remarkable subtlety.<n>To counter this, we propose Intent-Aware CoT and Reverse Thinking CoT, which decompose queries to detect malicious intent and reason in reverse to evaluate and reject harmful responses.
  arXiv  Detail & Related papers  (2025-01-03T15:40:03Z)
• Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks [6.614364170035397]
  We find that language models have difficulties generating fallacious and deceptive reasoning.<n>We propose a jailbreak attack method that elicits an aligned language model for malicious output.
  arXiv  Detail & Related papers  (2024-07-01T00:23:43Z)
• Navigating the OverKill in Large Language Models [84.62340510027042]
  We investigate the factors for overkill by exploring how models handle and determine the safety of queries. Our findings reveal the presence of shortcuts within models, leading to an over-attention of harmful words like 'kill' and prompts emphasizing safety will exacerbate overkill. We introduce Self-Contrastive Decoding (Self-CD), a training-free and model-agnostic strategy, to alleviate this phenomenon.
  arXiv  Detail & Related papers  (2024-01-31T07:26:47Z)
• Jailbroken: How Does LLM Safety Training Fail? [92.8748773632051]
  "jailbreak" attacks on early releases of ChatGPT elicit undesired behavior. We investigate why such attacks succeed and how they can be created. New attacks utilizing our failure modes succeed on every prompt in a collection of unsafe requests.
  arXiv  Detail & Related papers  (2023-07-05T17:58:10Z)

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.