One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models

v1v2v3 (latest)

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models

8 June 2024

Hao Fang

Bin Chen

Hao Wu

Ke Xu

ArXiv (abs)PDF HTML

Papers citing "One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models"

7 / 107 papers shown

Title
Distributional Smoothing with Virtual Adversarial Training Takeru Miyato S. Maeda Masanori Koyama Ken Nakae S. Ishii 91 458 0 02 Jul 2015
Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models Bryan A. Plummer Liwei Wang Christopher M. Cervantes Juan C. Caicedo Julia Hockenmaier Svetlana Lazebnik 202 2,071 0 19 May 2015
Explaining and Harnessing Adversarial Examples Ian Goodfellow Jonathon Shlens Christian Szegedy AAML GAN 280 19,107 0 20 Dec 2014
Deep Visual-Semantic Alignments for Generating Image Descriptions A. Karpathy Li Fei-Fei 140 5,590 0 07 Dec 2014
CIDEr: Consensus-based Image Description Evaluation Ramakrishna Vedantam C. L. Zitnick Devi Parikh 295 4,508 0 20 Nov 2014
Show and Tell: A Neural Image Caption Generator Oriol Vinyals Alexander Toshev Samy Bengio D. Erhan 3DV 249 6,035 0 17 Nov 2014
Microsoft COCO: Common Objects in Context Nayeon Lee Michael Maire Serge J. Belongie Lubomir Bourdev Ross B. Girshick James Hays Pietro Perona Deva Ramanan C. L. Zitnick Piotr Dollár ObjD 419 43,777 0 01 May 2014