English
Related papers

Related papers: Poisoning and Backdooring Contrastive Learning

200 papers

Poisoning-based backdoor attacks pose significant threats to deep neural networks by embedding triggers in training data, causing models to misclassify triggered inputs as adversary-specified labels while maintaining performance on clean…

Cryptography and Security · Computer Science 2026-04-24 Yuchen Shi , Xin Guo , Huajie Chen , Tianqing Zhu , Bo Liu , Wanlei Zhou

Indiscriminate data poisoning attacks are quite effective against supervised learning. However, not much is known about their impact on unsupervised contrastive learning (CL). This paper is the first to consider indiscriminate poisoning…

Machine Learning · Computer Science 2023-03-10 Hao He , Kaiwen Zha , Dina Katabi

Existing vision-text contrastive learning like CLIP aims to match the paired image and caption embeddings while pushing others apart, which improves representation transferability and supports zero-shot prediction. However, medical…

Computer Vision and Pattern Recognition · Computer Science 2022-10-20 Zifeng Wang , Zhenbang Wu , Dinesh Agarwal , Jimeng Sun

Contrastive Vision-Language Pre-training, known as CLIP, has shown promising effectiveness in addressing downstream image recognition tasks. However, recent works revealed that the CLIP model can be implanted with a downstream-oriented…

Computer Vision and Pattern Recognition · Computer Science 2024-03-25 Jiawang Bai , Kuofeng Gao , Shaobo Min , Shu-Tao Xia , Zhifeng Li , Wei Liu

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. Previous defense…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Tong Zhang , Kuofeng Gao , Jiawang Bai , Leo Yu Zhang , Xin Yin , Zonghui Wang , Shouling Ji , Wenzhi Chen

Semi-supervised learning methods can train high-accuracy machine learning models with a fraction of the labeled training samples required for traditional supervised learning. Such methods do not typically involve close review of the…

Machine Learning · Computer Science 2022-12-07 Marissa Connor , Vincent Emanuele

We propose a novel clustering mechanism based on an incompatibility property between subsets of data that emerges during model training. This mechanism partitions the dataset into subsets that generalize only to themselves, i.e., training…

Machine Learning · Computer Science 2023-04-28 Charles Jin , Melinda Sun , Martin Rinard

Poisoning backdoor attacks involve an adversary manipulating the training data to induce certain behaviors in the victim model by inserting a trigger in the signal at inference time. We adapted clean label backdoor (CLBD)-data poisoning…

Cryptography and Security · Computer Science 2024-09-16 Henry Li Xinyuan , Sonal Joshi , Thomas Thebaud , Jesus Villalba , Najim Dehak , Sanjeev Khudanpur

As machine learning (ML) classifiers increasingly oversee the automated monitoring of network traffic, studying their resilience against adversarial attacks becomes critical. This paper focuses on poisoning attacks, specifically backdoor…

Cryptography and Security · Computer Science 2023-06-05 Giorgio Severi , Simona Boboila , Alina Oprea , John Holodnak , Kendra Kratkiewicz , Jason Matterer

Studying backdoor attacks is valuable for model copyright protection and enhancing defenses. While existing backdoor attacks have successfully infected multimodal contrastive learning models such as CLIP, they can be easily countered by…

Computer Vision and Pattern Recognition · Computer Science 2024-03-05 Siyuan Liang , Mingli Zhu , Aishan Liu , Baoyuan Wu , Xiaochun Cao , Ee-Chien Chang

Inspired by the remarkable zero-shot generalization capacity of vision-language pre-trained model, we seek to leverage the supervision from CLIP model to alleviate the burden of data labeling. However, such supervision inevitably contains…

Computer Vision and Pattern Recognition · Computer Science 2022-06-14 Junchu Huang , Weijie Chen , Shicai Yang , Di Xie , Shiliang Pu , Yueting Zhuang

The adversarial machine learning literature is largely partitioned into evasion attacks on testing data and poisoning attacks on training data. In this work, we show that adversarial examples, originally intended for attacking pre-trained…

Machine Learning · Computer Science 2021-06-22 Liam Fowl , Micah Goldblum , Ping-yeh Chiang , Jonas Geiping , Wojtek Czaja , Tom Goldstein

Deep learning models have recently shown to be vulnerable to backdoor poisoning, an insidious attack where the victim model predicts clean images correctly but classifies the same images as the target class when a trigger poison pattern is…

Computer Vision and Pattern Recognition · Computer Science 2019-11-20 Alvin Chan , Yew-Soon Ong

Backdoor attacks insert malicious data into a training set so that, during inference time, it misclassifies inputs that have been patched with a backdoor trigger as the malware specified label. For backdoor attacks to bypass human…

Cryptography and Security · Computer Science 2022-04-18 Yi Zeng , Minzhou Pan , Hoang Anh Just , Lingjuan Lyu , Meikang Qiu , Ruoxi Jia

While pre-trained Vision-Language Models (VLMs) such as CLIP exhibit impressive representational capabilities for multimodal data, recent studies have revealed their vulnerability to backdoor attacks. To alleviate the threat, existing…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Jiawei Kong , Hao Fang , Sihang Guo , Chenxi Qing , Kuofeng Gao , Bin Chen , Shu-Tao Xia , Ke Xu

Contrastive Language-Image Pretraining (CLIP) models excel at understanding image-text relationships but struggle with adapting to new data without forgetting prior knowledge. To address this, models are typically fine-tuned using both new…

Machine Learning · Computer Science 2026-05-06 Ryan King , Gang Li , Bobak Mortazavi , Tianbao Yang

A backdoor data poisoning attack is an adversarial attack wherein the attacker injects several watermarked, mislabeled training examples into a training set. The watermark does not impact the test-time performance of the model on typical…

Machine Learning · Computer Science 2021-11-05 Naren Sarayu Manoj , Avrim Blum

Poisoning attacks on machine learning systems compromise the model performance by deliberately injecting malicious samples in the training dataset to influence the training process. Prior works focus on either availability attacks (i.e.,…

Machine Learning · Computer Science 2021-10-13 Bingyin Zhao , Yingjie Lao

Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence. Existing methods often fail under strong detection or continuous fine-tuning, largely due to (1) cross-modal…

Computer Vision and Pattern Recognition · Computer Science 2026-02-20 Siyuan Liang , Yongcheng Jing , Yingjie Wang , Jiaxing Huang , Ee-chien Chang , Dacheng Tao

Modern NLP models are often trained on public datasets drawn from diverse sources, rendering them vulnerable to data poisoning attacks. These attacks can manipulate the model's behavior in ways engineered by the attacker. One such tactic…

Computation and Language · Computer Science 2024-05-21 Xuanli He , Qiongkai Xu , Jun Wang , Benjamin I. P. Rubinstein , Trevor Cohn