LAMP: Learning Universal Adversarial Perturbations for Multi-Image Tasks via Pre-trained Models

• URL: http://arxiv.org/abs/2601.21220v1
• Date: Thu, 29 Jan 2026 03:36:17 GMT
• Title: LAMP: Learning Universal Adversarial Perturbations for Multi-Image Tasks via Pre-trained Models
• Authors: Alvi Md Ishmam, Najibul Haque Sarker, Zaber Ibn Abdul Hakim, Chris Thomas,
• Abstract summary: This paper introduces LAMP, a black-box method for learning Universal Adversarial Perturbations (UAPs) targeting multi-image MLLMs.<n>LAMP applies an attention-based constraint that prevents the model from effectively aggregating information across images.<n>LAMP also introduces a novel cross-image contagious constraint that forces perturbed tokens to influence clean tokens, spreading adversarial effects without requiring all inputs to be modified.
• Score: 6.127898072805579
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable performance across vision-language tasks. Recent advancements allow these models to process multiple images as inputs. However, the vulnerabilities of multi-image MLLMs remain unexplored. Existing adversarial attacks focus on single-image settings and often assume a white-box threat model, which is impractical in many real-world scenarios. This paper introduces LAMP, a black-box method for learning Universal Adversarial Perturbations (UAPs) targeting multi-image MLLMs. LAMP applies an attention-based constraint that prevents the model from effectively aggregating information across images. LAMP also introduces a novel cross-image contagious constraint that forces perturbed tokens to influence clean tokens, spreading adversarial effects without requiring all inputs to be modified. Additionally, an index-attention suppression loss enables a robust position-invariant attack. Experimental results show that LAMP outperforms SOTA baselines and achieves the highest attack success rates across multiple vision-language tasks and models.

Related papers

• Multi-Paradigm Collaborative Adversarial Attack Against Multi-Modal Large Language Models [67.45032003041399]
  We propose a novel Multi-Paradigm Collaborative Attack (MPCAttack) framework to boost the transferability of adversarial examples against MLLMs.<n>MPCO adaptively balances the importance of different paradigm representations and guides the global optimisation.<n>Our solution consistently outperforms state-of-the-art methods in both targeted and untargeted attacks on open-source and closed-source MLLMs.
  arXiv  Detail & Related papers  (2026-03-05T06:01:26Z)
• Unleashing the Intrinsic Visual Representation Capability of Multimodal Large Language Models [58.91911788912665]
  We propose Latent Visual Reconstruction (LaVer), a novel training framework that facilitates MLLMs in learning more discrimi visual representations.<n>Our method offers direct visual activation to MLLMs, which exhibit increased visual attention allocation, indicating enhanced utilization of visual information.
  arXiv  Detail & Related papers  (2025-12-06T04:20:13Z)
• Adversarial Confusion Attack: Disrupting Multimodal Large Language Models [1.4037095606573826]
  We introduce the Adversarial Confusion Attack, a new class of threats against multimodal large language models (MLLMs)<n>Unlike jailbreaks or targeted misclassification, the goal is to induce systematic disruption that makes the model generate incoherent or confidently incorrect outputs.<n> Practical applications include embedding such adversarial images into websites to prevent MLLM-powered AI Agents from operating reliably.
  arXiv  Detail & Related papers  (2025-11-25T17:00:31Z)
• A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models [85.30893355216486]
  We study how visual token redundancy evolves with different dMLLM architectures and tasks.<n>Our study reveals that visual redundancy emerges only in from-scratch dMLLMs while handling long-answer tasks.<n>Layer-skipping is promising for accelerating AR-to-diffusion dMLLMs, whereas progressive or late-step pruning is more effective for from-scratch dMLLMs.
  arXiv  Detail & Related papers  (2025-11-19T04:13:36Z)
• AVAM: Universal Training-free Adaptive Visual Anchoring Embedded into Multimodal Large Language Model for Multi-image Question Answering [10.967073982905752]
  We propose a straightforward yet universal Adaptive Visual Anchoring strategy, which can be seamlessly integrated into existing MLLMs.<n>To balance the results derived from both global and compressed visual input, we introduce a novel collaborative decoding mechanism.
  arXiv  Detail & Related papers  (2025-08-25T10:10:46Z)
• Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens [66.02261367232256]
  Multimodal Large Language Models (MLLMs) aim to unify visual comprehension and generation.<n>Existing approaches rely on spatial visual tokens, where image patches are encoded and arranged according to a spatial order.<n>In this paper, we build a proper visual language by reconstructing diffusion timesteps to learn discrete visual tokens.
  arXiv  Detail & Related papers  (2025-04-20T16:14:28Z)
• Doubly-Universal Adversarial Perturbations: Deceiving Vision-Language Models Across Both Images and Text with a Single Perturbation [15.883062174902093]
  Large Vision-Language Models (VLMs) have demonstrated remarkable performance across multimodal tasks by integrating vision encoders with large language models (LLMs)<n>We introduce a novel UAP specifically designed for VLMs: the Doubly-Universal Adversarial Perturbation (Doubly-UAP)
  arXiv  Detail & Related papers  (2024-12-11T05:23:34Z)
• Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning [53.766434746801366]
  Multimodal contrastive learning (MCL) has shown remarkable advances in zero-shot classification by learning from millions of image-caption pairs crawled from the Internet. Hackers may unauthorizedly exploit image-text data for model training, potentially including personal and privacy-sensitive information. Recent works propose generating unlearnable examples by adding imperceptible perturbations to training images to build shortcuts for protection. We propose Multi-step Error Minimization (MEM), a novel optimization process for generating multimodal unlearnable examples.
  arXiv  Detail & Related papers  (2024-07-23T09:00:52Z)
• Adversarial Robustness for Visual Grounding of Multimodal Large Language Models [49.71757071535619]
  Multi-modal Large Language Models (MLLMs) have recently achieved enhanced performance across various vision-language tasks. adversarial robustness of visual grounding remains unexplored in MLLMs. We propose three adversarial attack paradigms as follows.
  arXiv  Detail & Related papers  (2024-05-16T10:54:26Z)

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.