paper-with-me

홈 › Papers

Cross-Modal Transferable Image-to-Video Attack on Video Quality Metrics

2025-01-14 · Georgii Gotin, Ekaterina Shumitskaya, Anastasia Antsiferova, Dmitriy Vatolin

Recent studies have revealed that modern image and video quality assessment (IQA/VQA) metrics are vulnerable to adversarial attacks. An attacker can manipulate a video through preprocessing to artificially increase its quality score according to a certain metric, despite no actual improvement in visual quality. Most of the attacks studied in the literature are white-box attacks, while black-box attacks in the context of VQA have received less attention. Moreover, some research indicates a lack of transferability of adversarial examples generated for one model to another when applied to VQA. In this paper, we propose a cross-modal attack method, IC2VQA, aimed at exploring the vulnerabilities of modern VQA models. This approach is motivated by the observation that the low-level feature spaces of images and videos are similar. We investigate the transferability of adversarial perturbations across different modalities; specifically, we analyze how adversarial perturbations generated on a white-box IQA model with an additional CLIP module can effectively target a VQA model. The addition of the CLIP module serves as a valuable aid in increasing transferability, as the CLIP model is known for its effective capture of low-level semantics. Extensive experiments demonstrate that IC2VQA achieves a high success rate in attacking three black-box VQA models. We compare our method with existing black-box attack strategies, highlighting its superiority in terms of attack success within the same number of iterations and levels of attack strength. We believe that the proposed method will contribute to the deeper analysis of robust VQA metrics.

📄 PDF Abstract BibTeX arXiv:2501.08415

Code (1)

georgegotin/ic2vqa 공식 구현 pytorch

Tasks

Video Quality AssessmentVisual Question Answering (VQA)

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Cross-Modal Transferable Adversarial Attacks from Images to Videos

2021-12-10 · CVPR 2022 1 · Zhipeng Wei, Jingjing Chen, Zuxuan Wu, Yu-Gang Jiang

Recent studies have shown that adversarial examples hand-crafted on one white-box model can be used to attack other black-box models. Such cross-model transferability makes it feasible to perform black-box attacks, which…

Video Recognition

Image-based Multimodal Models as Intruders: Transferable Multimodal Attacks on Video-based MLLMs

2025-01-02 · Linhao Huang, Xue Jiang, Zhiqiang Wang, Wentao Mo 외

Video-based multimodal large language models (V-MLLMs) have shown vulnerability to adversarial examples in video-text multimodal tasks. However, the transferability of adversarial videos to unseen models--a common and pr…

Adversarial AttackAttribute

Temporal Consistency Constrained Transferable Adversarial Attacks with Background Mixup for Action Recognition

2025-05-23 · Ping Li, Jianan Ni, Bo Pang

Action recognition models using deep learning are vulnerable to adversarial examples, which are transferable across other models trained on the same data modality. Existing transferable attack methods face two major chal…

Action RecognitionAdversarial Attack

When Background Matters: Breaking Medical Vision Language Models by Transferable Attack

2026-04-19 · Akash Ghosh, Subhadip Baidya, Sriparna Saha, Xiuying Chen arxiv

Vision-Language Models (VLMs) are increasingly used in clinical diagnostics, yet their robustness to adversarial attacks remains largely unexplored, posing serious risks. Existing medical attacks focus on secondary objec…

Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems

2023-11-20 · Guangjing Wang, Ce Zhou, Yuanda Wang, Bocheng Chen 외

As Artificial Intelligence (AI) systems increasingly underpin critical applications, from autonomous vehicles to biometric authentication, their vulnerability to transferable attacks presents a growing concern. These att…

Autonomous DrivingAutonomous VehiclesData AugmentationData Poisoning+2