Defending Multimodal Fusion Models against Single-Source Adversaries

Defending Multimodal Fusion Models against Single-Source Adversaries

Computer Vision and Pattern Recognition (CVPR), 2021

25 June 2022

Filipe Condessa

ArXiv (abs)PDF HTML

Papers citing "Defending Multimodal Fusion Models against Single-Source Adversaries"

19 / 19 papers shown

Title
Adversarial Video Promotion Against Text-to-Video Retrieval Qiwei Tian Chenhao Lin Zhengyu Zhao Qian Li Shuai Liu Chao Shen AAML 103 0 0 09 Aug 2025
Temporal Misalignment Attacks against Multimodal Perception in Autonomous Driving Md Hasan Shahriar Md Mohaimin Al Barat Harshavardhan Sundar Ning Zhang Naren Ramakrishnan Y. T. Hou W. Lou 98 0 0 12 Jul 2025
$$\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time$ $\texttt{AVROBUSTBENCH}$ : Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time Sarthak Kumar Maharana Saksham Singh Kushwaha Baoming Zhang Adrian Rodriguez Songtao Wei Yapeng Tian Yunhui Guo TTA VLM 186 0 0 31 May 2025
Replace-then-Perturb: Targeted Adversarial Attacks With Visual Reasoning for Vision-Language Models Jonggyu Jang Hyeonsu Lyu Jungyeon Koh H. Yang VLM AAML 167 0 0 01 Nov 2024
One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models Hao Fang Jiawei Kong Wenbo Yu Bin Chen Jiawei Li Hao Wu Ke Xu Ke Xu AAML VLM 337 26 0 08 Jun 2024
MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models Yanting Wang Hongye Fu Wei Zou Jinyuan Jia AAML 298 3 0 28 Mar 2024
Counter-Samples: A Stateless Strategy to Neutralize Black Box Adversarial AttacksACM Transactions on Intelligent Systems and Technology (ACM TIST), 2024 Roey Bokobza Yisroel Mirsky AAML 133 0 0 14 Mar 2024
One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models Lin Li Haoyan Guan Jianing Qiu Michael W. Spratling AAML VLM VPVLM 228 39 0 04 Mar 2024
A Survey on Safe Multi-Modal Learning System Tianyi Zhao Liangliang Zhang Yao Ma Lu Cheng 423 21 0 08 Feb 2024
Understanding the Vulnerability of CLIP to Image Compression Cangxiong Chen Vinay P. Namboodiri Julian Padget 111 3 0 23 Nov 2023
Black-box Attacks on Image Activity Prediction and its Natural Language Explanations Alina Elena Baia Valentina Poggioni Andrea Cavallaro AAML 184 1 0 30 Sep 2023
Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language ModelsNeural Information Processing Systems (NeurIPS), 2023 Shuo Chen Jindong Gu Zhen Han Yunpu Ma Juil Sock Volker Tresp VPVLM VLM 312 30 0 03 Jun 2023
Iterative Adversarial Attack on Image-guided Story Ending GenerationIEEE transactions on multimedia (IEEE TMM), 2023 Youze Wang Wenbo Hu Richang Hong 189 8 0 16 May 2023
Instance-Level Trojan Attacks on Visual Question Answering via Adversarial Learning in Neuron Activation SpaceIEEE International Joint Conference on Neural Network (IJCNN), 2023 Yuwei Sun H. Ochiai Jun Sakuma AAML 209 6 0 02 Apr 2023
HateProof: Are Hateful Meme Detection Systems really Robust?The Web Conference (WWW), 2023 Piush Aggarwal Pranit Chawla Mithun Das Punyajoy Saha Binny Mathew Torsten Zesch Animesh Mukherjee AAML 138 12 0 11 Feb 2023
Robustness Analysis of Video-Language Models Against Visual and Language PerturbationsNeural Information Processing Systems (NeurIPS), 2022 Madeline Chantry Schiappa Shruti Vyas Hamid Palangi Yogesh S Rawat Vibhav Vineet VLM 473 29 0 05 Jul 2022
On the Limitations of Stochastic Pre-processing DefensesNeural Information Processing Systems (NeurIPS), 2022 Yue Gao Ilia Shumailov Kassem Fawaz Nicolas Papernot AAML SILM 284 32 0 19 Jun 2022
Towards Adversarial Attack on Vision-Language Pre-training ModelsACM Multimedia (ACM MM), 2022 Jiaming Zhang Qiaomin Yi Jitao Sang VLM AAML 237 140 0 19 Jun 2022
YOLO9000: Better, Faster, StrongerComputer Vision and Pattern Recognition (CVPR), 2016 Joseph Redmon Ali Farhadi VLM ObjD 523 16,892 0 25 Dec 2016