AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant T2I Adversarial Patches

• URL: http://arxiv.org/abs/2506.09538v1
• Date: Wed, 11 Jun 2025 09:14:50 GMT
• Title: AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant T2I Adversarial Patches
• Authors: Wenjun Ji, Yuxiang Fu, Luyang Ying, Deng-Ping Fan, Yuyi Wang, Ming-Ming Cheng, Ivor Tsang, Qing Guo,
• Abstract summary: Text-to-image (T2I) diffusion models can generate adversarial patches that mislead state-of-the-art object detectors in the physical world.<n>We introduce Angle-Robust Concept Learning (AngleRoCL) representing the capability of generating angle-robust patches.<n>We show that AngleRoCL significantly enhances the angle robustness of T2I adversarial patches compared to baseline methods.
• Score: 63.95103818483424
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cutting-edge works have demonstrated that text-to-image (T2I) diffusion models can generate adversarial patches that mislead state-of-the-art object detectors in the physical world, revealing detectors' vulnerabilities and risks. However, these methods neglect the T2I patches' attack effectiveness when observed from different views in the physical world (i.e., angle robustness of the T2I adversarial patches). In this paper, we study the angle robustness of T2I adversarial patches comprehensively, revealing their angle-robust issues, demonstrating that texts affect the angle robustness of generated patches significantly, and task-specific linguistic instructions fail to enhance the angle robustness. Motivated by the studies, we introduce Angle-Robust Concept Learning (AngleRoCL), a simple and flexible approach that learns a generalizable concept (i.e., text embeddings in implementation) representing the capability of generating angle-robust patches. The learned concept can be incorporated into textual prompts and guides T2I models to generate patches with their attack effectiveness inherently resistant to viewpoint variations. Through extensive simulation and physical-world experiments on five SOTA detectors across multiple views, we demonstrate that AngleRoCL significantly enhances the angle robustness of T2I adversarial patches compared to baseline methods. Our patches maintain high attack success rates even under challenging viewing conditions, with over 50% average relative improvement in attack effectiveness across multiple angles. This research advances the understanding of physically angle-robust patches and provides insights into the relationship between textual concepts and physical properties in T2I-generated contents.

Related papers

• Quality Text, Robust Vision: The Role of Language in Enhancing Visual Robustness of Vision-Language Models [17.259725776748482]
  Existing adversarial training methods for robust fine-tuning largely overlook the role of language in enhancing visual robustness.<n>We propose Quality Text-guided Adversarial Fine-Tuning (QT-AFT), which leverages high-quality captions during training to guide adversarial examples away from diverse semantics present in images.<n> QT-AFT achieves state-of-the-art zero-shot adversarial robustness and clean accuracy, evaluated across 16 zero-shot datasets.
  arXiv  Detail & Related papers  (2025-07-22T06:13:30Z)
• Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned Transformers [0.0]
  Large language models (LLMs) aligned for safety often exhibit emergent deceptive behaviors.<n>This paper introduces adversarial activation patching, a novel mechanistic interpretability framework.<n>By sourcing activations from "deceptive" prompts, we simulate vulnerabilities and quantify deception rates.
  arXiv  Detail & Related papers  (2025-07-12T21:29:49Z)
• GenBreak: Red Teaming Text-to-Image Generators Using Large Language Models [65.91565607573786]
  Text-to-image (T2I) models can be misused to generate harmful content, including nudity or violence.<n>Recent research on red-teaming and adversarial attacks against T2I models has notable limitations.<n>We propose GenBreak, a framework that fine-tunes a red-team large language model (LLM) to systematically explore underlying vulnerabilities.
  arXiv  Detail & Related papers  (2025-06-11T09:09:12Z)
• All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learning [45.37237171823581]
  The exponential growth of AI-generated images (AIGIs) underscores the urgent need for robust and generalizable detection methods.<n>In this paper, we establish two key principles for AIGI detection through systematic analysis.
  arXiv  Detail & Related papers  (2025-04-02T06:32:09Z)
• Unified Prompt Attack Against Text-to-Image Generation Models [30.24530622359188]
  We propose UPAM, a framework to evaluate the robustness of T2I models from an attack perspective.<n>UPAM unifies the attack on both textual and visual defenses.<n>It also enables gradient-based optimization, overcoming reliance on enumeration for improved efficiency and effectiveness.
  arXiv  Detail & Related papers  (2025-02-23T03:36:18Z)
• Few-Shot Adversarial Prompt Learning on Vision-Language Models [62.50622628004134]
  The vulnerability of deep neural networks to imperceptible adversarial perturbations has attracted widespread attention. Previous efforts achieved zero-shot adversarial robustness by aligning adversarial visual features with text supervision. We propose a few-shot adversarial prompt framework where adapting input sequences with limited data makes significant adversarial robustness improvement.
  arXiv  Detail & Related papers  (2024-03-21T18:28:43Z)
• GuardT2I: Defending Text-to-Image Models from Adversarial Prompts [16.317849859000074]
  GuardT2I is a novel moderation framework that adopts a generative approach to enhance T2I models' robustness against adversarial prompts. Our experiments reveal that GuardT2I outperforms leading commercial solutions like OpenAI-Moderation and Microsoft Azure Moderator.
  arXiv  Detail & Related papers  (2024-03-03T09:04:34Z)
• Towards Robust Image Stitching: An Adaptive Resistance Learning against Compatible Attacks [66.98297584796391]
  Image stitching seamlessly integrates images captured from varying perspectives into a single wide field-of-view image. Given a pair of captured images, subtle perturbations and distortions which go unnoticed by the human visual system tend to attack the correspondence matching. This paper presents the first attempt to improve the robustness of image stitching against adversarial attacks.
  arXiv  Detail & Related papers  (2024-02-25T02:36:33Z)
• MVPatch: More Vivid Patch for Adversarial Camouflaged Attacks on Object Detectors in the Physical World [7.1343035828597685]
  We introduce generalization theory into the context of Adversarial Patches (APs) We propose a Dual-Perception-Based Framework (DPBF) to generate the More Vivid Patch (MVPatch), which enhances transferability, stealthiness, and practicality. MVPatch achieves superior transferability and a natural appearance in both digital and physical domains, underscoring its effectiveness and stealthiness.
  arXiv  Detail & Related papers  (2023-12-29T01:52:22Z)
• Adversarial Attacks in a Multi-view Setting: An Empirical Study of the Adversarial Patches Inter-view Transferability [3.1542695050861544]
  Adversarial attacks consist of additive noise to an input which can fool a detector. Recent successful real-world printable adversarial patches were proven efficient against state-of-the-art neural networks. We study the effect of view angle on the effectiveness of an adversarial patch.
  arXiv  Detail & Related papers  (2021-10-10T19:59:28Z)
• Enhancing Adversarial Robustness via Test-time Transformation Ensembling [51.51139269928358]
  We show how equipping models with Test-time Transformation Ensembling can work as a reliable defense against adversarial attacks. We show that TTE consistently improves model robustness against a variety of powerful attacks without any need for re-training.
  arXiv  Detail & Related papers  (2021-07-29T15:32:35Z)
• Unsupervised Pretraining for Object Detection by Patch Reidentification [72.75287435882798]
  Unsupervised representation learning achieves promising performances in pre-training representations for object detectors. This work proposes a simple yet effective representation learning method for object detection, named patch re-identification (Re-ID) Our method significantly outperforms its counterparts on COCO in all settings, such as different training iterations and data percentages.
  arXiv  Detail & Related papers  (2021-03-08T15:13:59Z)

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.