CVPR 2026 Open Access Repository

The 6th Workshop of Adversarial Machine Learning on Computer Vision: Safety of Vision-Language Agents

Robustness of Vision Foundation Models to Common Perturbations: Hongbin Liu,

Zhengyuan Jiang,

Cheng Hong,

Neil Zhenqiang Gong; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Liu_2026_CVPR, author = {Liu, Hongbin and Jiang, Zhengyuan and Hong, Cheng and Gong, Neil Zhenqiang}, title = {Robustness of Vision Foundation Models to Common Perturbations}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {507-515} }
SASA: Sequence-Aware Shadow Attacks via Attention Alignment for Traffic Sign Recognition: Amir Salarpour,

Pedram MohajerAnsari,

David Fernandez,

Mert D Pesé; [pdf]
[bibtex]
@InProceedings{Salarpour_2026_CVPR, author = {Salarpour, Amir and MohajerAnsari, Pedram and Fernandez, David and Pes\'e, Mert D}, title = {SASA: Sequence-Aware Shadow Attacks via Attention Alignment for Traffic Sign Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {533-540} }
ATAC: Augmentation-Based Test-Time Adversarial Correction for CLIP: Linxiang Su,

András Balogh; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Su_2026_CVPR, author = {Su, Linxiang and Balogh, Andr\'as}, title = {ATAC: Augmentation-Based Test-Time Adversarial Correction for CLIP}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {541-551} }
Auditing Traffic-Sign Robustness via DDIM Inversion: Do Diffusion Latents Preserve Shadow Attacks?: Ashton McEntarffer,

Amir Salarpour,

Pedram MohajerAnsari,

Mert D Pesé; [pdf]
[bibtex]
@InProceedings{McEntarffer_2026_CVPR, author = {McEntarffer, Ashton and Salarpour, Amir and MohajerAnsari, Pedram and Pes\'e, Mert D}, title = {Auditing Traffic-Sign Robustness via DDIM Inversion: Do Diffusion Latents Preserve Shadow Attacks?}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {516-524} }
MirrorCheck: Efficient Adversarial Defense for Vision-Language Models: Samar Fares,

Klea Ziu,

Toluwani Aremu,

Nikita Durasov,

Martin Takáč,

Pascal Fua,

Ivan Laptev,

Karthik Nandakumar; [pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Fares_2026_CVPR, author = {Fares, Samar and Ziu, Klea and Aremu, Toluwani and Durasov, Nikita and Tak\'a\v{c}, Martin and Fua, Pascal and Laptev, Ivan and Nandakumar, Karthik}, title = {MirrorCheck: Efficient Adversarial Defense for Vision-Language Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {496-506} }
Interpretable Adversarial Prompt Tuning via Semantic Concepts: Pedram MohajerAnsari,

Zongxi Liu,

Yi Zhu,

Amir Salarpour,

Mert D Pesé; [pdf]
[bibtex]
@InProceedings{MohajerAnsari_2026_CVPR, author = {MohajerAnsari, Pedram and Liu, Zongxi and Zhu, Yi and Salarpour, Amir and Pes\'e, Mert D}, title = {Interpretable Adversarial Prompt Tuning via Semantic Concepts}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {525-532} }
Evaluating Vulnerabilities in Vision-Language Models: Impact of Behavior-Induced Interference: Yuwei Chen,

Shiyong Chu; [pdf]
[bibtex]
@InProceedings{Chen_2026_CVPR, author = {Chen, Yuwei and Chu, Shiyong}, title = {Evaluating Vulnerabilities in Vision-Language Models: Impact of Behavior-Induced Interference}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {486-495} }