paper-with-me

홈 › Papers

Poisoning and Backdooring Contrastive Learning

2021-06-17 · ICLR 2022 4 · Nicholas Carlini, Andreas Terzis

Multimodal contrastive learning methods like CLIP train on noisy and uncurated training datasets. This is cheaper than labeling datasets manually, and even improves out-of-distribution robustness. We show that this practice makes backdoor and poisoning attacks a significant threat. By poisoning just 0.01% of a dataset (e.g., just 300 images of the 3 million-example Conceptual Captions dataset), we can cause the model to misclassify test images by overlaying a small patch. Targeted poisoning attacks, whereby the model misclassifies a particular test input with an adversarially-desired label, are even easier requiring control of 0.0001% of the dataset (e.g., just three out of the 3 million images). Our attacks call into question whether training on noisy and uncurated Internet scrapes is desirable.

📄 PDF Abstract BibTeX arXiv:2106.09667

Code (1)

giantseaweed/decree pytorch

Tasks

Contrastive Learning

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment

2024-11-23 · CVPR 2024 1 · Alvi Md Ishmam, Christopher Thomas

In recent years there has been enormous interest in vision-language models trained using self-supervised objectives. However, the use of large-scale datasets scraped from the web for training also makes these models vuln…

Language ModelingLanguage Modelling

Backdooring Self-Supervised Contrastive Learning by Noisy Alignment

2025-08-19 · Tuo Chen, Jie Gui, Minjing Dong, Ju Jia 외 arxiv

Self-supervised contrastive learning (CL) effectively learns transferable representations from unlabeled data containing images or image-text pairs but suffers vulnerability to data poisoning backdoor attacks (DPCLs). An…

Contrastive Learning

Backdooring and Poisoning Neural Networks with Image-Scaling Attacks

2020-03-19 · Erwin Quiring, Konrad Rieck

Backdoors and poisoning attacks are a major threat to the security of machine-learning and vision systems. Often, however, these attacks leave visible artifacts in the images that can be visually detected and weaken the …

Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning

2022-02-22 · Hao He, Kaiwen Zha, Dina Katabi

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 indiscri…

Contrastive LearningData AugmentationData PoisoningMatrix Completion

Universal Backdoor Attacks

2023-11-30 · Benjamin Schneider, Nils Lukas, Florian Kerschbaum

Web-scraped datasets are vulnerable to data poisoning, which can be used for backdooring deep image classifiers during training. Since training on large datasets is expensive, a model is trained once and re-used many tim…

Data Poisoning