Poisoning and Backdooring Contrastive Learning

17 June 2021

Papers citing "Poisoning and Backdooring Contrastive Learning"

50 / 118 papers shown

Title
Trustworthy Large Models in Vision: A Survey Ziyan Guo Li Xu Jun Liu MU 58 0 0 16 Nov 2023
Defending Our Privacy With Backdoors Dominik Hintersdorf Lukas Struppek Daniel Neider Kristian Kersting SILM AAML 18 2 0 12 Oct 2023
Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks Wenhan Yang Jingdong Gao Baharan Mirzasoleiman VLM 24 6 0 05 Oct 2023
Towards Stable Backdoor Purification through Feature Shift Tuning Rui Min Zeyu Qin Li Shen Minhao Cheng AAML 40 21 0 03 Oct 2023
GhostEncoder: Stealthy Backdoor Attacks with Dynamic Triggers to Pre-trained Encoders in Self-supervised Learning Qiannan Wang Changchun Yin Zhe Liu Liming Fang Run Wang Chenhao Lin AAML 30 4 0 01 Oct 2023
Privacy Preservation in Artificial Intelligence and Extended Reality (AI-XR) Metaverses: A Survey Mahdi Alkaeed Adnan Qayyum Junaid Qadir 26 16 0 19 Sep 2023
BAGEL: Backdoor Attacks against Federated Contrastive Learning Yao Huang Kongyang Chen Jiannong Cao Jiaxing Shen Shaowei Wang Yun Peng Weilong Peng Kechao Cai FedML 27 3 0 14 Sep 2023
Identifying and Mitigating the Security Risks of Generative AI Clark W. Barrett Bradley L Boyd Ellie Burzstein Nicholas Carlini Brad Chen ... Zulfikar Ramzan Khawaja Shams D. Song Ankur Taly Diyi Yang SILM 29 91 0 28 Aug 2023
Balancing Transparency and Risk: The Security and Privacy Risks of Open-Source Machine Learning Models Dominik Hintersdorf Lukas Struppek Kristian Kersting SILM 20 4 0 18 Aug 2023
Test-Time Poisoning Attacks Against Test-Time Adaptation Models Tianshuo Cong Xinlei He Yun Shen Yang Zhang AAML TTA 24 5 0 16 Aug 2023
SSL-Auth: An Authentication Framework by Fragile Watermarking for Pre-trained Encoders in Self-supervised Learning Xiaobei Li Changchun Yin Liyue Zhu Xiaogang Xu Liming Fang Run Wang Chenhao Lin AAML 20 0 0 09 Aug 2023
Downstream-agnostic Adversarial Examples Ziqi Zhou Shengshan Hu Rui-Qing Zhao Qian Wang L. Zhang Junhui Hou Hai Jin SILM AAML 21 24 0 23 Jul 2023
NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models Kai Mei Zheng Li Zhenting Wang Yang Zhang Shiqing Ma AAML SILM 34 48 0 28 May 2023
The Curse of Recursion: Training on Generated Data Makes Models Forget Ilia Shumailov Zakhar Shumaylov Yiren Zhao Y. Gal Nicolas Papernot Ross J. Anderson DiffM 23 280 0 27 May 2023
Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation Xuanli He Qiongkai Xu Jun Wang Benjamin I. P. Rubinstein Trevor Cohn AAML 29 18 0 19 May 2023
Pick your Poison: Undetectability versus Robustness in Data Poisoning Attacks Nils Lukas Florian Kerschbaum 28 1 0 07 May 2023
Assessing Vulnerabilities of Adversarial Learning Algorithm through Poisoning Attacks Jingfeng Zhang Bo Song Bo Han Lei Liu Gang Niu Masashi Sugiyama AAML 16 2 0 30 Apr 2023
RoCOCO: Robustness Benchmark of MS-COCO to Stress-test Image-Text Matching Models Seulki Park Daeho Um Hajung Yoon Sanghyuk Chun Sangdoo Yun Jin Young Choi 35 2 0 21 Apr 2023
Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning Ajinkya Tejankar Maziar Sanjabi Qifan Wang Sinong Wang Hamed Firooz Hamed Pirsiavash L Tan AAML 30 19 0 04 Apr 2023
Detecting Backdoors in Pre-trained Encoders Shiwei Feng Guanhong Tao Shuyang Cheng Guangyu Shen Xiangzhe Xu Yingqi Liu Kaiyuan Zhang Shiqing Ma Xiangyu Zhang 76 47 0 23 Mar 2023
Black-box Backdoor Defense via Zero-shot Image Purification Yucheng Shi Mengnan Du Xuansheng Wu Zihan Guan Jin Sun Ninghao Liu 40 28 0 21 Mar 2023
Robust Contrastive Language-Image Pre-training against Data Poisoning and Backdoor Attacks Wenhan Yang Jingdong Gao Baharan Mirzasoleiman VLM 102 18 0 13 Mar 2023
Backdoor Defense via Deconfounded Representation Learning Zaixin Zhang Qi Liu Zhicai Wang Zepu Lu Qingyong Hu AAML 49 39 0 13 Mar 2023
CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning Hritik Bansal Nishad Singhi Yu Yang Fan Yin Aditya Grover Kai-Wei Chang AAML 34 42 0 06 Mar 2023
Single Image Backdoor Inversion via Robust Smoothed Classifiers Mingjie Sun Zico Kolter AAML 8 12 0 01 Mar 2023
ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms Minzhou Pan Yi Zeng Lingjuan Lyu X. Lin R. Jia AAML 26 35 0 22 Feb 2023
Poisoning Web-Scale Training Datasets is Practical Nicholas Carlini Matthew Jagielski Christopher A. Choquette-Choo Daniel Paleka Will Pearce Hyrum S. Anderson Andreas Terzis Kurt Thomas Florian Tramèr SILM 31 182 0 20 Feb 2023
Temporal Robustness against Data Poisoning Wenxiao Wang S. Feizi AAML OOD 30 11 0 07 Feb 2023
Uncovering Adversarial Risks of Test-Time Adaptation Tong Wu Feiran Jia Xiangyu Qi Jiachen T. Wang Vikash Sehwag Saeed Mahloujifar Prateek Mittal AAML TTA 29 9 0 29 Jan 2023
A Study on FGSM Adversarial Training for Neural Retrieval Simon Lupart S. Clinchant AAML 24 7 0 25 Jan 2023
REaaS: Enabling Adversarially Robust Downstream Classifiers via Robust Encoder as a Service Wenjie Qu Jinyuan Jia Neil Zhenqiang Gong SILM AAML 21 4 0 07 Jan 2023
Backdoor Attacks Against Dataset Distillation Yugeng Liu Zheng Li Michael Backes Yun Shen Yang Zhang DD 34 27 0 03 Jan 2023
Pre-trained Encoders in Self-Supervised Learning Improve Secure and Privacy-preserving Supervised Learning Hongbin Liu Wenjie Qu Jinyuan Jia Neil Zhenqiang Gong SSL 28 6 0 06 Dec 2022
CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning Jinghuai Zhang Hongbin Liu Jinyuan Jia Neil Zhenqiang Gong AAML 35 20 0 15 Nov 2022
ContextCLIP: Contextual Alignment of Image-Text pairs on CLIP visual representations Chanda Grover Indra Deep Mastan Debayan Gupta VLM CLIP 11 4 0 14 Nov 2022
Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis Lukas Struppek Dominik Hintersdorf Kristian Kersting SILM 22 36 0 04 Nov 2022
Apple of Sodom: Hidden Backdoors in Superior Sentence Embeddings via Contrastive Learning Xiaoyi Chen Baisong Xin Shengfang Zhai Shiqing Ma Qingni Shen Zhonghai Wu SILM 17 2 0 20 Oct 2022
An Embarrassingly Simple Backdoor Attack on Self-supervised Learning Changjiang Li Ren Pang Zhaohan Xi Tianyu Du S. Ji Yuan Yao Ting Wang AAML 25 25 0 13 Oct 2022
How to Sift Out a Clean Data Subset in the Presence of Data Poisoning? Yi Zeng Minzhou Pan Himanshu Jahagirdar Ming Jin Lingjuan Lyu R. Jia AAML 36 21 0 12 Oct 2022
Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork Haotao Wang Junyuan Hong Aston Zhang Jiayu Zhou Zhangyang Wang AAML 36 12 0 12 Oct 2022
Backdoor Attacks in the Supply Chain of Masked Image Modeling Xinyue Shen Xinlei He Zheng Li Yun Shen Michael Backes Yang Zhang 38 7 0 04 Oct 2022
Data Poisoning Attacks Against Multimodal Encoders Ziqing Yang Xinlei He Zheng Li Michael Backes Mathias Humbert Pascal Berrang Yang Zhang AAML 110 45 0 30 Sep 2022
Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection Yiming Li Yang Bai Yong Jiang Yong-Liang Yang Shutao Xia Bo Li AAML 45 97 0 27 Sep 2022
Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis Lukas Struppek Dominik Hintersdorf Felix Friedrich Manuel Brack P. Schramowski Kristian Kersting 73 26 0 19 Sep 2022
Invisible Backdoor Attacks Using Data Poisoning in the Frequency Domain Chang Yue Peizhuo Lv Ruigang Liang Kai Chen AAML 26 10 0 09 Jul 2022
CyCLIP: Cyclic Contrastive Language-Image Pretraining Shashank Goel Hritik Bansal S. Bhatia Ryan A. Rossi Vishwa Vinay Aditya Grover CLIP VLM 173 132 0 28 May 2022
BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning Zhenting Wang Juan Zhai Shiqing Ma AAML 126 97 0 26 May 2022
On Trace of PGD-Like Adversarial Attacks Mo Zhou Vishal M. Patel AAML 27 4 0 19 May 2022
PoisonedEncoder: Poisoning the Unlabeled Pre-training Data in Contrastive Learning Hongbin Liu Jinyuan Jia Neil Zhenqiang Gong 25 34 0 13 May 2022
Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning Hao He Kaiwen Zha Dina Katabi AAML 31 32 0 22 Feb 2022