On the Feasibility of Hijacking MLLMs' Decision Chain via One Perturbation

• URL: http://arxiv.org/abs/2511.20002v1
• Date: Tue, 25 Nov 2025 07:13:13 GMT
• Title: On the Feasibility of Hijacking MLLMs' Decision Chain via One Perturbation
• Authors: Changyue Li, Jiaying Li, Youliang Yuan, Jiaming He, Zhicong Huang, Pinjia He,
• Abstract summary: A single perturbation can hijack the whole decision chain.<n>Semantic-Aware Universal Perturbations (SAUPs) induce varied outcomes based on the semantics of the inputs.<n>Experiments on three multimodal large language models demonstrate their vulnerability.
• Score: 22.536817707658816
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Conventional adversarial attacks focus on manipulating a single decision of neural networks. However, real-world models often operate in a sequence of decisions, where an isolated mistake can be easily corrected, but cascading errors can lead to severe risks. This paper reveals a novel threat: a single perturbation can hijack the whole decision chain. We demonstrate the feasibility of manipulating a model's outputs toward multiple, predefined outcomes, such as simultaneously misclassifying "non-motorized lane" signs as "motorized lane" and "pedestrian" as "plastic bag". To expose this threat, we introduce Semantic-Aware Universal Perturbations (SAUPs), which induce varied outcomes based on the semantics of the inputs. We overcome optimization challenges by developing an effective algorithm, which searches for perturbations in normalized space with a semantic separation strategy. To evaluate the practical threat of SAUPs, we present RIST, a new real-world image dataset with fine-grained semantic annotations. Extensive experiments on three multimodal large language models demonstrate their vulnerability, achieving a 70% attack success rate when controlling five distinct targets using just an adversarial frame.

Related papers

• SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks [53.97948802255959]
  We propose a framework that trains a multi-turn attacker without relying on any existing strategies or external data.<n>Prefilling self-tuning enables usable rollouts by fine-tuning on non-refusal, well-structured, multi-turn adversarial prompts.<n>We anchor harmful intent in multi-turn jailbreaks via an intent-drift-aware reward that combines intent alignment, compliance risk, and level of detail.
  arXiv  Detail & Related papers  (2026-02-06T16:44:57Z)
• Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction [51.50282796099369]
  This paper develops a multi-dimensional instruction uncertainty reduction framework to generate semantically constrained adversarial examples.<n>By predicting the language-guided sampling process, the optimization process will be stabilized by the designed ResAdv-DDIM sampler.<n>We realize the reference-free generation of semantically constrained 3D adversarial examples for the first time.
  arXiv  Detail & Related papers  (2025-10-27T04:02:52Z)
• LLM Unlearning with LLM Beliefs [39.271253385135644]
  Large language models trained on vast corpora inherently risk memorizing sensitive or harmful content, which may later resurface in their outputs.<n>We propose a bootstrapping framework that explicitly links the squeezing effect with the model's own high-confidence generations.<n>By jointly suppressing both target responses and model beliefs, BS-T (token) attenuates high-probability tokens, whereas BS-S (sequence) removes entire high-confidence generations.
  arXiv  Detail & Related papers  (2025-10-22T09:44:36Z)
• DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models [50.21378052667732]
  We conduct an in-depth analysis of dLLM vulnerabilities to jailbreak attacks across two distinct dimensions: intra-step and inter-step dynamics.<n>We propose DiffuGuard, a training-free defense framework that addresses vulnerabilities through a dual-stage approach.
  arXiv  Detail & Related papers  (2025-09-29T05:17:10Z)
• TRAP: Targeted Redirecting of Agentic Preferences [3.6293956720749425]
  We introduce TRAP, a generative adversarial framework that manipulates the agent's decision-making using diffusion-based semantic injections.<n>Our method combines negative prompt-based degradation with positive semantic optimization, guided by a Siamese semantic network and layout-aware spatial masking.<n>TRAP achieves a 100% attack success rate on leading models, including LLaVA-34B, Gemma3, and Mistral-3.1.
  arXiv  Detail & Related papers  (2025-05-29T14:57:16Z)
• Transferable Adversarial Attacks on SAM and Its Downstream Models [87.23908485521439]
  This paper explores the feasibility of adversarial attacking various downstream models fine-tuned from the segment anything model (SAM)<n>To enhance the effectiveness of the adversarial attack towards models fine-tuned on unknown datasets, we propose a universal meta-initialization (UMI) algorithm.
  arXiv  Detail & Related papers  (2024-10-26T15:04:04Z)
• Multi-granular Adversarial Attacks against Black-box Neural Ranking Models [111.58315434849047]
  We create high-quality adversarial examples by incorporating multi-granular perturbations. We transform the multi-granular attack into a sequential decision-making process. Our attack method surpasses prevailing baselines in both attack effectiveness and imperceptibility.
  arXiv  Detail & Related papers  (2024-04-02T02:08:29Z)
• Multi-objective Evolutionary Search of Variable-length Composite Semantic Perturbations [1.9100854225243937]
  We propose a novel method called multi-objective evolutionary search of variable-length composite semantic perturbations (MES-VCSP) MES-VCSP can obtain adversarial examples with a higher attack success rate, more naturalness, and less time cost.
  arXiv  Detail & Related papers  (2023-07-13T04:08:16Z)
• LEAT: Towards Robust Deepfake Disruption in Real-World Scenarios via Latent Ensemble Attack [11.764601181046496]
  Deepfakes, malicious visual contents created by generative models, pose an increasingly harmful threat to society. To proactively mitigate deepfake damages, recent studies have employed adversarial perturbation to disrupt deepfake model outputs. We propose a simple yet effective disruption method called Latent Ensemble ATtack (LEAT), which attacks the independent latent encoding process.
  arXiv  Detail & Related papers  (2023-07-04T07:00:37Z)
• Resisting Adversarial Attacks in Deep Neural Networks using Diverse Decision Boundaries [12.312877365123267]
  Deep learning systems are vulnerable to crafted adversarial examples, which may be imperceptible to the human eye, but can lead the model to misclassify. We develop a new ensemble-based solution that constructs defender models with diverse decision boundaries with respect to the original model. We present extensive experimentations using standard image classification datasets, namely MNIST, CIFAR-10 and CIFAR-100 against state-of-the-art adversarial attacks.
  arXiv  Detail & Related papers  (2022-08-18T08:19:26Z)
• Double Targeted Universal Adversarial Perturbations [83.60161052867534]
  We introduce a double targeted universal adversarial perturbations (DT-UAPs) to bridge the gap between the instance-discriminative image-dependent perturbations and the generic universal perturbations. We show the effectiveness of the proposed DTA algorithm on a wide range of datasets and also demonstrate its potential as a physical attack.
  arXiv  Detail & Related papers  (2020-10-07T09:08:51Z)

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.