paper-with-me

홈 › Papers

Backdoor Attacks on Multi-modal Contrastive Learning

2026-01-16 · Simi D Kuniyilh, Rita Machacy arxiv

Contrastive learning has become a leading self- supervised approach to representation learning across domains, including vision, multimodal settings, graphs, and federated learning. However, recent studies have shown that contrastive learning is susceptible to backdoor and data poisoning attacks. In these attacks, adversaries can manipulate pretraining data or model updates to insert hidden malicious behavior. This paper offers a thorough and comparative review of backdoor attacks in contrastive learning. It analyzes threat models, attack methods, target domains, and available defenses. We summarize recent advancements in this area, underline the specific vulnerabilities inherent to contrastive learning, and discuss the challenges and future research directions. Our findings have significant implications for the secure deployment of systems in industrial and distributed environments.

📄 PDF Abstract BibTeX arXiv:2601.11006

Code (0)

등록된 구현이 없습니다.

Tasks

Representation LearningContrastive LearningFederated Learning

Similar Papers 제목 키워드 기반

CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning

2023-03-06 · ICCV 2023 1 · Hritik Bansal, Nishad Singhi, Yu Yang, Fan Yin 외

Multimodal contrastive pretraining has been used to train multimodal representation models, such as CLIP, on large amounts of paired image-text data. However, previous studies have revealed that such models are vulnerabl…

Backdoor AttackContrastive LearningData Poisoning

BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning

2023-11-20 · CVPR 2024 1 · Siyuan Liang, Mingli Zhu, Aishan Liu, Baoyuan Wu 외

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 eas…

Backdoor AttackContrastive Learning

Robust Defense Strategies for Multimodal Contrastive Learning: Efficient Fine-tuning Against Backdoor Attacks

2025-11-17 · Md. Iqbal Hossain, Afia Sajeeda, Neeresh Kumar Perla, Ming Shao arxiv

The advent of multimodal deep learning models, such as CLIP, has unlocked new frontiers in a wide range of applications, from image-text understanding to classification tasks. However, these models are not safe for adver…

Multimodal Deep LearningContrastive LearningImage Segmentation

Robust Contrastive Language-Image Pre-training against Data Poisoning and Backdoor Attacks

2023-03-13 · Wenhan Yang, Jingdong Gao, Baharan Mirzasoleiman

Contrastive vision-language representation learning has achieved state-of-the-art performance for zero-shot classification, by learning from millions of image-caption pairs crawled from the internet. However, the massive…

Backdoor AttackData PoisoningRepresentation Learningzero-shot-classification+1

Robust Contrastive Language-Image Pretraining against Data Poisoning and Backdoor Attacks

2023-09-21 · NeurIPS 2023 11

Contrastive vision-language representation learning has achieved state-of-the-art performance for zero-shot classification, by learning from millions of image-caption pairs crawled from the internet. However, the massive…