Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective

25 November 2023

Papers citing "Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective"

20 / 20 papers shown

Title
Sigmoid Loss for Language Image Pre-Training Xiaohua Zhai Basil Mustafa Alexander Kolesnikov Lucas Beyer CLIP VLM 168 1,138 0 27 Mar 2023
Not All Poisons are Created Equal: Robust Training against Data Poisoning Yu Yang Tianwei Liu Baharan Mirzasoleiman AAML 42 38 0 18 Oct 2022
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation Junnan Li Dongxu Li Caiming Xiong Guosheng Lin MLLM BDL VLM CLIP 524 4,343 0 28 Jan 2022
SLIP: Self-supervision meets Language-Image Pre-training Norman Mu Alexander Kirillov David Wagner Saining Xie VLM CLIP 136 488 0 23 Dec 2021
FILIP: Fine-grained Interactive Language-Image Pre-Training Lewei Yao Runhu Huang Lu Hou Guansong Lu Minzhe Niu Hang Xu Xiaodan Liang Zhenguo Li Xin Jiang Chunjing Xu VLM CLIP 92 634 0 09 Nov 2021
Anti-Backdoor Learning: Training Clean Models on Poisoned Data Yige Li X. Lyu Nodens Koren Lingjuan Lyu Yue Liu Xingjun Ma OnRL 68 334 0 22 Oct 2021
Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm Yangguang Li Feng Liang Lichen Zhao Yufeng Cui Wanli Ouyang Jing Shao F. Yu Junjie Yan VLM CLIP 145 453 0 11 Oct 2021
Poisoning and Backdooring Contrastive Learning Nicholas Carlini Andreas Terzis 58 166 0 17 Jun 2021
Backdoor Attacks on Self-Supervised Learning Aniruddha Saha Ajinkya Tejankar Soroush Abbasi Koohpayegani Hamed Pirsiavash SSL AAML 48 109 0 21 May 2021
With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations Debidatta Dwibedi Y. Aytar Jonathan Tompson P. Sermanet Andrew Zisserman SSL 233 467 0 29 Apr 2021
Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts Soravit Changpinyo P. Sharma Nan Ding Radu Soricut VLM 426 1,127 0 17 Feb 2021
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision Chao Jia Yinfei Yang Ye Xia Yi-Ting Chen Zarana Parekh Hieu H. Pham Quoc V. Le Yun-hsuan Sung Zhen Li Tom Duerig VLM CLIP 443 3,842 0 11 Feb 2021
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses Micah Goldblum Dimitris Tsipras Chulin Xie Xinyun Chen Avi Schwarzschild D. Song Aleksander Madry Yue Liu Tom Goldstein SILM 79 281 0 18 Dec 2020
The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization Dan Hendrycks Steven Basart Norman Mu Saurav Kadavath Frank Wang ... Samyak Parajuli Mike Guo D. Song Jacob Steinhardt Justin Gilmer OOD 328 1,734 0 29 Jun 2020
Natural Adversarial Examples Dan Hendrycks Kevin Zhao Steven Basart Jacob Steinhardt D. Song OODD 200 1,469 0 16 Jul 2019
Learning Robust Global Representations by Penalizing Local Predictive Power Haohan Wang Songwei Ge Eric Xing Zachary Chase Lipton OOD 114 957 0 29 May 2019
Do ImageNet Classifiers Generalize to ImageNet? Benjamin Recht Rebecca Roelofs Ludwig Schmidt Vaishaal Shankar OOD SSeg VLM 113 1,714 0 13 Feb 2019
BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain Tianyu Gu Brendan Dolan-Gavitt S. Garg SILM 118 1,772 0 22 Aug 2017
Certified Defenses for Data Poisoning Attacks Jacob Steinhardt Pang Wei Koh Percy Liang AAML 83 754 0 09 Jun 2017
Billion-scale similarity search with GPUs Jeff Johnson Matthijs Douze Hervé Jégou 257 3,720 0 28 Feb 2017