# Backdoor Attacks on Multi-modal Contrastive Learning

arXiv: https://arxiv.org/abs/2601.11006 · HTML: https://mlsanity.com/paper/2601.11006/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 16 Jan 2026.

## Builds on (most cited first, 19 of 19)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning](https://mlsanity.com/paper/2103.00113/) (2021)
- [Poisoning and Backdooring Contrastive Learning](https://mlsanity.com/paper/2106.09667/) (2021)
- [BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning](https://mlsanity.com/paper/2311.12075/) (2023)
- [InfoNCE Loss Provably Learns Cluster-Preserving Representations](https://mlsanity.com/paper/2302.07920/) (2023)
- [CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning](https://mlsanity.com/paper/2211.08229/) (2022)
- [OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning](https://mlsanity.com/paper/2505.04601/) (2025)
- [Federated Intrusion Detection for IoT with Heterogeneous Cohort Privacy](https://mlsanity.com/paper/2101.09878/) (2021)
- [Backdoor Contrastive Learning via Bi-level Trigger Optimization](https://mlsanity.com/paper/2404.07863/) (2024)
- [CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning](https://mlsanity.com/paper/2409.17601/) (2024)
- [On the Difficulty of Defending Contrastive Learning against Backdoor Attacks](https://mlsanity.com/paper/2312.09057/) (2023)
- [PCAP-Backdoor: Backdoor Poisoning Generator for Network Traffic in CPS/IoT Environments](https://mlsanity.com/paper/2501.15563/) (2025)
- [Dynamic User-controllable Privacy-preserving Few-shot Sensing Framework](https://mlsanity.com/paper/2508.03989/) (2025)
- [Dynamic Black-box Backdoor Attacks on IoT Sensory Data](https://mlsanity.com/paper/2511.14074/) (2025)
- [Log Anomaly Detection with Large Language Models via Knowledge-Enriched Fusion](https://mlsanity.com/paper/2512.11997/) (2025)
- [BAGEL: Backdoor Attacks against Federated Contrastive Learning](https://mlsanity.com/paper/2311.16113/) (2023)
- [GANcrop: A Contrastive Defense Against Backdoor Attacks in Federated Learning](https://mlsanity.com/paper/2405.20727/) (2024)

## Abstract (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.