Conceal, Reconstruct, Jailbreak: Exploiting the Reconstruction-Concealment Tradeoff in MLLMs

• URL: http://arxiv.org/abs/2605.05709v1
• Date: Thu, 07 May 2026 05:54:49 GMT
• Title: Conceal, Reconstruct, Jailbreak: Exploiting the Reconstruction-Concealment Tradeoff in MLLMs
• Abstract summary: Intent-obfuscation-based jailbreak attacks on multimodal large language models (MLLMs)<n>We show that such attacks are governed by a emphreconstruction--concealment tradeoff<n>We propose emphconcealment-aware variant construction, which greedily selects character-removed variants that are low in harmful-keyword alignment and mutually diverse.
• Score: 38.904948168003536
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Intent-obfuscation-based jailbreak attacks on multimodal large language models (MLLMs) transform a harmful query into a concealed multimodal input to bypass safety mechanisms. We show that such attacks are governed by a \emph{reconstruction--concealment tradeoff}: the transformed input must hide harmful intent from safety filters while remaining recoverable enough for the victim model to reconstruct the original request. Through a reconstruction analysis of three representative black-box methods, we find that existing transformations struggle to balance this tradeoff, limiting their effectiveness. In contrast, we show that character-removed variants achieve a better balance. Building on this, we propose \emph{concealment-aware variant construction}, which greedily selects character-removed variants that are low in harmful-keyword alignment and mutually diverse, and instantiates them through five modality-aware prompting strategies. We further introduce \emph{keyword-related distractor images} that depict the harmful keyword in diverse contexts, providing more effective auxiliary visual context than generic distractor images. Experiments across closed-source and open-source MLLMs show the proposed strategies outperform strong baselines, revealing an underexplored vulnerability: a model's own reconstruction ability can be exploited to recover hidden harmful intent and produce unsafe responses.

Related papers

• MIDAS: Multi-Image Dispersion and Semantic Reconstruction for Jailbreaking MLLMs [22.919956583415324]
  Multi-Image Dispersion and Semantic Reconstruction (MIDAS)<n>We propose a multimodal jailbreak framework that decomposes harmful semantics into risk-bearing subunits.<n>MIDAS enforces longer and more structured multi-image chained reasoning.
  arXiv  Detail & Related papers  (2026-02-28T09:29:36Z)
• Jailbreaks on Vision Language Model via Multimodal Reasoning [10.066621451320792]
  We present a framework that exploits post-training Chain-of-Thought prompting to construct stealthy prompts capable of bypassing safety filters.<n>We also propose a ReAct-driven adaptive noising mechanism that iteratively perturbs input images based on model feedback.
  arXiv  Detail & Related papers  (2026-01-29T23:09:24Z)
• SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models [67.84174763413178]
  We introduce SafeRedir, a lightweight inference-time framework for robust unlearning via prompt embedding redirection.<n>We show that SafeRedir achieves effective unlearning capability, high semantic and perceptual preservation, robust image quality, and enhanced resistance to adversarial attacks.
  arXiv  Detail & Related papers  (2026-01-13T15:01:38Z)
• GAMBIT: A Gamified Jailbreak Framework for Multimodal Large Language Models [16.68943715789759]
  We propose a novel framework that drives a model to explore, reconstruct intent, and answer as part of winning the game.<n>GAMBIT achieves high Attack Success Rates (ASR), reaching 92.13% on Gemini 2.5 Flash, 91.20% on QvQ-MAX, and 85.87% on GPT-4o.
  arXiv  Detail & Related papers  (2026-01-06T21:09:10Z)
• VRSA: Jailbreaking Multimodal Large Language Models through Visual Reasoning Sequential Attack [40.68344330540352]
  Multimodal Large Language Models (MLLMs) are widely used in various fields due to their powerful cross-modal comprehension and generation capabilities.<n>Previous jailbreak attacks try to explore reasoning safety risk in text modal, while similar threats have been largely overlooked in the visual modal.<n>We propose Visual Reasoning Sequential Attack (VRSA), which induces MLLMs to gradually externalize and aggregate complete harmful intent.
  arXiv  Detail & Related papers  (2025-12-05T16:29:52Z)
• Multimodal Safety Is Asymmetric: Cross-Modal Exploits Unlock Black-Box MLLMs Jailbreaks [33.836587055255954]
  Multimodal large language models (MLLMs) have demonstrated significant utility across diverse real-world applications.<n>But MLLMs remain vulnerable to jailbreaks, where adversarial inputs can collapse their safety constraints and trigger unethical responses.<n>We develop PolyJailbreak, a black-box jailbreak method grounded in reinforcement learning.
  arXiv  Detail & Related papers  (2025-10-20T08:03:39Z)
• MIRAGE: Multimodal Immersive Reasoning and Guided Exploration for Red-Team Jailbreak Attacks [85.3303135160762]
  MIRAGE is a novel framework that exploits narrative-driven context and role immersion to circumvent safety mechanisms in Multimodal Large Language Models.<n>It achieves state-of-the-art performance, improving attack success rates by up to 17.5% over the best baselines.<n>We demonstrate that role immersion and structured semantic reconstruction can activate inherent model biases, facilitating the model's spontaneous violation of ethical safeguards.
  arXiv  Detail & Related papers  (2025-03-24T20:38:42Z)
• White-box Multimodal Jailbreaks Against Large Vision-Language Models [61.97578116584653]
  We propose a more comprehensive strategy that jointly attacks both text and image modalities to exploit a broader spectrum of vulnerability within Large Vision-Language Models. Our attack method begins by optimizing an adversarial image prefix from random noise to generate diverse harmful responses in the absence of text input. An adversarial text suffix is integrated and co-optimized with the adversarial image prefix to maximize the probability of eliciting affirmative responses to various harmful instructions.
  arXiv  Detail & Related papers  (2024-05-28T07:13:30Z)
• AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting [54.931241667414184]
  We propose textbfAdaptive textbfShield Prompting, which prepends inputs with defense prompts to defend MLLMs against structure-based jailbreak attacks. Our methods can consistently improve MLLMs' robustness against structure-based jailbreak attacks.
  arXiv  Detail & Related papers  (2024-03-14T15:57:13Z)
• VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models [65.23688155159398]
  Autoregressive Visual Language Models (VLMs) showcase impressive few-shot learning capabilities in a multimodal context. Recently, multimodal instruction tuning has been proposed to further enhance instruction-following abilities. Adversaries can implant a backdoor by injecting poisoned samples with triggers embedded in instructions or images. We propose a multimodal instruction backdoor attack, namely VL-Trojan.
  arXiv  Detail & Related papers  (2024-02-21T14:54:30Z)

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.