Hiding-in-Plain-Sight (HiPS) Attack on CLIP for Targetted Object Removal from Images

• URL: http://arxiv.org/abs/2410.13010v1
• Date: Wed, 16 Oct 2024 20:11:32 GMT
• Title: Hiding-in-Plain-Sight (HiPS) Attack on CLIP for Targetted Object Removal from Images
• Authors: Arka Daw, Megan Hong-Thanh Chung, Maria Mahbub, Amir Sadovnik,
• Abstract summary: Hiding-in-Plain-Sight (HiPS) attacks subtly modifies model predictions by selectively concealing target object(s) We propose two HiPS attack variants, HiPS-cls and HiPS-cap, and demonstrate their effectiveness in transferring to downstream image captioning models.
• Score: 3.537369004801589
• License:
• Abstract: Machine learning models are known to be vulnerable to adversarial attacks, but traditional attacks have mostly focused on single-modalities. With the rise of large multi-modal models (LMMs) like CLIP, which combine vision and language capabilities, new vulnerabilities have emerged. However, prior work in multimodal targeted attacks aim to completely change the model's output to what the adversary wants. In many realistic scenarios, an adversary might seek to make only subtle modifications to the output, so that the changes go unnoticed by downstream models or even by humans. We introduce Hiding-in-Plain-Sight (HiPS) attacks, a novel class of adversarial attacks that subtly modifies model predictions by selectively concealing target object(s), as if the target object was absent from the scene. We propose two HiPS attack variants, HiPS-cls and HiPS-cap, and demonstrate their effectiveness in transferring to downstream image captioning models, such as CLIP-Cap, for targeted object removal from image captions.

Related papers

• 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)
• Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks [62.34019142949628]
  Typographic Attacks, which involve pasting misleading text onto an image, were noted to harm the performance of Vision-Language Models like CLIP. We introduce two novel and more effective textitSelf-Generated attacks which prompt the LVLM to generate an attack against itself. Using our benchmark, we uncover that Self-Generated attacks pose a significant threat, reducing LVLM(s) classification performance by up to 33%.
  arXiv  Detail & Related papers  (2024-02-01T14:41:20Z)
• A Review of Adversarial Attacks in Computer Vision [16.619382559756087]
  Adversarial attacks can be invisible to human eyes, but can lead to deep learning misclassification. Adversarial attacks can be divided into white-box attacks, for which the attacker knows the parameters and gradient of the model, and black-box attacks, for the latter, the attacker can only obtain the input and output of the model.
  arXiv  Detail & Related papers  (2023-08-15T09:43:10Z)
• Attack-SAM: Towards Attacking Segment Anything Model With Adversarial Examples [68.5719552703438]
  Segment Anything Model (SAM) has attracted significant attention recently, due to its impressive performance on various downstream tasks. Deep vision models are widely recognized as vulnerable to adversarial examples, which fool the model to make wrong predictions with imperceptible perturbation. This work is the first of its kind to conduct a comprehensive investigation on how to attack SAM with adversarial examples.
  arXiv  Detail & Related papers  (2023-05-01T15:08:17Z)
• Defense-Prefix for Preventing Typographic Attacks on CLIP [14.832208701208414]
  Some adversarial attacks fool a model into false or absurd classifications. We introduce our simple yet effective method: Defense-Prefix (DP), which inserts the DP token before a class name to make words "robust" against typographic attacks. Our method significantly improves the accuracy of classification tasks for typographic attack datasets, while maintaining the zero-shot capabilities of the model.
  arXiv  Detail & Related papers  (2023-04-10T11:05:20Z)
• Ensemble-based Blackbox Attacks on Dense Prediction [16.267479602370543]
  We show that a carefully designed ensemble can create effective attacks for a number of victim models. In particular, we show that normalization of the weights for individual models plays a critical role in the success of the attacks. Our proposed method can also generate a single perturbation that can fool multiple blackbox detection and segmentation models simultaneously.
  arXiv  Detail & Related papers  (2023-03-25T00:08:03Z)
• Object-fabrication Targeted Attack for Object Detection [54.10697546734503]
  adversarial attack for object detection contains targeted attack and untargeted attack. New object-fabrication targeted attack mode can mislead detectors tofabricate extra false objects with specific target labels.
  arXiv  Detail & Related papers  (2022-12-13T08:42:39Z)
• GAMA: Generative Adversarial Multi-Object Scene Attacks [48.33120361498787]
  This paper presents the first approach of using generative models for adversarial attacks on multi-object scenes. We call this attack approach Generative Adversarial Multi-object scene Attacks (GAMA)
  arXiv  Detail & Related papers  (2022-09-20T06:40:54Z)
• Adversarial Pixel Restoration as a Pretext Task for Transferable Perturbations [54.1807206010136]
  Transferable adversarial attacks optimize adversaries from a pretrained surrogate model and known label space to fool the unknown black-box models. We propose Adversarial Pixel Restoration as a self-supervised alternative to train an effective surrogate model from scratch. Our training approach is based on a min-max objective which reduces overfitting via an adversarial objective.
  arXiv  Detail & Related papers  (2022-07-18T17:59:58Z)

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.