Fetching the paper…
Reading the bibliography…
Recent studies have shown that Contrastive Language-Image Pre-training (CLIP) models are threatened by targeted data poisoning and backdoor attacks due to massive training image-caption pairs crawled from the Internet.
Imagenet: A large-scale hierarchical image database
Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009 · 2009
Earlier work this paper cites.
Lightspeed computation of optimal transport
Cuturi M Sinkhorn Distances. 2013 · 2013
Earlier work this paper cites.
Microsoft coco: Common objects in context
Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick. 2014 · 2014
Earlier work this paper cites.
Targeted backdoor attacks on deep learning systems using data poisoning
Xinyun Chen, Chang Liu, Bo Li, Kimberly Lu, and Dawn Song. 2017 · 2017
Earlier work this paper cites.
Badnets: Identifying vulnerabilities in the machine learning model supply chain
Tianyu Gu, Brendan Dolan-Gavitt, and Siddharth Garg. 2017 · 2017
Earlier work this paper cites.
Visual genome: Connecting language and vision using crowdsourced dense image annotations
Ranjay Krishna, Yuke Zhu, Oliver Groth, Justin Johnson, Kenji Hata, Joshua Kravitz, Stephanie Chen, Yannis Kalantidis, Li-Jia Li, David A Shamma, and 1 others. 2017 · 2017
Earlier work this paper cites.
Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning
Piyush Sharma, Nan Ding, Sebastian Goodman, and Radu Soricut. 2018 · 2018
Earlier work this paper cites.
Analyzing the robustness of nearest neighbors to adversarial examples
Yizhen Wang, Somesh Jha, and Kamalika Chaudhuri. 2018 · 2018
Earlier work this paper cites.
Do better imagenet models transfer better?
Simon Kornblith, Jonathon Shlens, and Quoc V Le. 2019 · 2019
Earlier work this paper cites.
Graph optimal transport for cross-domain alignment
Liqun Chen, Zhe Gan, Yu Cheng, Linjie Li, Lawrence Carin, and Jingjing Liu. 2020 · 2020
Earlier work this paper cites.
Oscar: Object-semantics aligned pre-training for vision-language tasks
Xiujun Li, Xi Yin, Chunyuan Li, Pengchuan Zhang, Xiaowei Hu, Lei Zhang, Lijuan Wang, Houdong Hu, Li Dong, Furu Wei, and 1 others. 2020 · 2020
Earlier work this paper cites.
Poisoning and backdooring contrastive learning
Nicholas Carlini and Andreas Terzis. 2021 · 2021
Earlier work this paper cites.
Scaling up visual and vision-language representation learning with noisy text supervision
Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc Le, Yun-Hsuan Sung, Zhen Li, and Tom Duerig. 2021 · 2021
Earlier work this paper cites.
Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm
Yangguang Li, Feng Liang, Lichen Zhao, Yufeng Cui, Wanli Ouyang, Jing Shao, Fengwei Yu, and Junjie Yan. 2021 · 2021
Earlier work this paper cites.
Wanet–imperceptible warping-based backdoor attack
Anh Nguyen and Anh Tran. 2021 · 2021
Cited alongside, same era.
Learning transferable visual models from natural language supervision
Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, and 1 others. 2021 · 2021
Cited alongside, same era.
Filip: Fine-grained interactive language-image pre-training
Lewei Yao, Runhui Huang, Lu Hou, Guansong Lu, Minzhe Niu, Hang Xu, Xiaodan Liang, Zhenguo Li, Xin Jiang, and Chunjing Xu. 2021 · 2021
Cited alongside, same era.
Multi-grained vision language pre-training: Aligning texts with visual concepts
Yan Zeng, Xinsong Zhang, and Hang Li. 2021 · 2021
Cited alongside, same era.
Vinvl: Revisiting visual representations in vision-language models
Robust contrastive language-image pretraining against adversarial attacks
Wenhan Yang and Baharan Mirzasoleiman. 2023 · 2023
Later among the works it cites.
Data poisoning attacks against multimodal encoders
Ziqing Yang, Xinlei He, Zheng Li, Michael Backes, Mathias Humbert, Pascal Berrang, and Yang Zhang. 2023 · 2023
Later among the works it cites.
Badclip: Trigger-aware prompt learning for backdoor attacks on clip
Jiawang Bai, Kuofeng Gao, Shaobo Min, Shu-Tao Xia, Zhifeng Li, and Wei Liu. 2024 · 2024
Later among the works it cites.
Poisoning web-scale training datasets is practical
Nicholas Carlini, Matthew Jagielski, Christopher A Choquette-Choo, Daniel Paleka, Will Pearce, Hyrum Anderson, Andreas Terzis, Kurt Thomas, and Florian Tramèr. 2024 · 2024
Later among the works it cites.
Adversarial backdoor defense in clip
Junhao Kuang, Siyuan Liang, Jiawei Liang, Kuanrong Liu, and Xiaochun Cao. 2024 · 2024
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Pengchuan Zhang, Xiujun Li, Xiaowei Hu, Jianwei Yang, Lei Zhang, Lijuan Wang, Yejin Choi, and Jianfeng Gao. 2021 · 2021
Cited alongside, same era.
Unified optimal transport framework for universal domain adaptation
Wanxing Chang, Ye Shi, Hoang Tuan, and Jingya Wang. 2022 · 2022
Cited alongside, same era.
Pyramidclip: Hierarchical feature alignment for vision-language model pretraining
Yuting Gao, Jinfeng Liu, Zihan Xu, Jun Zhang, Ke Li, Rongrong Ji, and Chunhua Shen. 2022 · 2022
Cited alongside, same era.
Mvp: Multi-stage vision-language pre-training via multi-level semantic alignment
Zejun Li, Zhihao Fan, Huaixiao Tou, and Zhongyu Wei. 2022 · 2022
Cited alongside, same era.
A large-scale multiple-objective method for black-box attack against object detection
Siyuan Liang, Longkang Li, Yanbo Fan, Xiaojun Jia, Jingzhi Li, Baoyuan Wu, and Xiaochun Cao. 2022 · 2022
Cited alongside, same era.
Conditional prompt learning for vision-language models
Kaiyang Zhou, Jingkang Yang, Chen Change Loy, and Ziwei Liu. 2022 · 2022
Cited alongside, same era.
Cleanclip: Mitigating data poisoning attacks in multimodal contrastive learning
Hritik Bansal, Nishad Singhi, Yu Yang, Fan Yin, Aditya Grover, and Kai-Wei Chang. 2023 · 2023
Cited alongside, same era.
Detecting backdoors in pre-trained encoders
Shiwei Feng, Guanhong Tao, Siyuan Cheng, Guangyu Shen, Xiangzhe Xu, Yingqi Liu, Kaiyuan Zhang, Shiqing Ma, and Xiangyu Zhang. 2023 · 2023
Cited alongside, same era.
Unsupervised cross-domain image retrieval via prototypical optimal transport
Bin Li, Ye Shi, Qian Yu, and Jingya Wang. 2024 · 2024
Later among the works it cites.
Badclip: Dual-embedding guided backdoor attack on multimodal contrastive learning
Siyuan Liang, Mingli Zhu, Aishan Liu, Baoyuan Wu, Xiaochun Cao, and Ee-Chien Chang. 2024 · 2024
Later among the works it cites.
Yuan Xun, Siyuan Liang, Xiaojun Jia, Xinwei Liu, and Xiaochun Cao. 2024 · 2024
Later among the works it cites.
Better safe than sorry: Pre-training clip against targeted data poisoning and backdoor attacks
Wenhan Yang, Jingdong Gao, and Baharan Mirzasoleiman. 2024 · 2024
Later among the works it cites.
Detecting backdoor samples in contrastive language image pretraining
Hanxun Huang, Sarah Erfani, Yige Li, Xingjun Ma, and James Bailey. 2025 · 2025
Closest in time.
Revisiting backdoor attacks against large vision-language models from domain shift
Siyuan Liang, Jiawei Liang, Tianyu Pang, Chao Du, Aishan Liu, Mingli Zhu, Xiaochun Cao, and Dacheng Tao. 2025 · 2025
Closest in time.
Bdetclip: Multimodal prompting contrastive test-time backdoor detection
Yuwei Niu, Shuo He, Qi Wei, Zongyu Wu, Feng Liu, and Lei Feng. 2025 · 2025
Closest in time.
Beyond surface-level patterns: An essence-driven defense framework against jailbreak attacks in LLMs
Shiyu Xiang, Ansen Zhang, Yanfei Cao, Fan Yang, and Ronghao Chen. 2025a · 2025
Closest in time.