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

arXiv: https://arxiv.org/abs/2303.06854 · HTML: https://mlsanity.com/paper/2303.06854/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 23 of its 27 references that are in the map.
- First posted on arXiv 13 Mar 2023.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)
- LLM safety and security / [Backdoor and data poisoning attacks](https://mlsanity.com/safety/backdoor-and-data-poisoning-attacks/)

## Builds on (most cited first, 23 of 23)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [FILIP: Fine-grained Interactive Language-Image Pre-Training](https://mlsanity.com/paper/2111.07783/) (2021)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)
- [SLIP: Self-supervision meets Language-Image Pre-training](https://mlsanity.com/paper/2112.12750/) (2021)
- [Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm](https://mlsanity.com/paper/2110.05208/) (2021)
- [Hidden Trigger Backdoor Attacks](https://mlsanity.com/paper/1910.00033/) (2019)
- [With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2104.14548/) (2021)
- [Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching](https://mlsanity.com/paper/2009.02276/) (2020)
- [Poisoning and Backdooring Contrastive Learning](https://mlsanity.com/paper/2106.09667/) (2021)
- [CyCLIP: Cyclic Contrastive Language-Image Pretraining](https://mlsanity.com/paper/2205.14459/) (2022)
- [Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoff](https://mlsanity.com/paper/2011.09527/) (2020)
- [CleanCLIP: Mitigating Data Poisoning Attacks in Multimodal Contrastive Learning](https://mlsanity.com/paper/2303.03323/) (2023)
- [Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations](https://mlsanity.com/paper/2106.05967/) (2021)
- [Data Poisoning Attacks Against Multimodal Encoders](https://mlsanity.com/paper/2209.15266/) (2022)

## Built on by (most cited first, 30 of 31)

- [A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends](https://mlsanity.com/paper/2407.07403/) (2024)
- [Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack](https://mlsanity.com/paper/2405.16134/) (2024)
- [Unbridled Icarus: A Survey of the Potential Perils of Image Inputs in Multimodal Large Language Model Security](https://mlsanity.com/paper/2404.05264/) (2024)
- [Espresso: Robust Concept Filtering in Text-to-Image Models](https://mlsanity.com/paper/2404.19227/) (2024)
- [Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning](https://mlsanity.com/paper/2412.20392/) (2024)
- [Adversarial Backdoor Defense in CLIP](https://mlsanity.com/paper/2409.15968/) (2024)
- [Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment](https://mlsanity.com/paper/2411.15673/) (2024)
- [Data-centric NLP Backdoor Defense from the Lens of Memorization](https://mlsanity.com/paper/2409.14200/) (2024)
- [Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats](https://mlsanity.com/paper/2409.19526/) (2024)
- [DeDe: Detecting Backdoor Samples for SSL Encoders via Decoders](https://mlsanity.com/paper/2411.16154/) (2024)
- [Test-Time Multimodal Backdoor Detection by Contrastive Prompting](https://mlsanity.com/paper/2405.15269/) (2024)
- [TokenSwap: Backdoor Attack on the Compositional Understanding of Large Vision-Language Models](https://mlsanity.com/paper/2509.24566/) (2025)
- [Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP](https://mlsanity.com/paper/2412.00727/) (2024)
- [ToxicTextCLIP: Text-Based Poisoning and Backdoor Attacks on CLIP Pre-training](https://mlsanity.com/paper/2511.00446/) (2025)
- [T2UE: Generating Unlearnable Examples from Text Descriptions](https://mlsanity.com/paper/2508.03091/) (2025)
- [Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective](https://mlsanity.com/paper/2311.14948/) (2023)
- [New Emerged Security and Privacy of Pre-trained Model: a Survey and Outlook](https://mlsanity.com/paper/2411.07691/) (2024)
- [BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning](https://mlsanity.com/paper/2602.17168/) (2026)
- [Neural Antidote: Class-Wise Prompt Tuning for Purifying Backdoors in CLIP](https://mlsanity.com/paper/2502.19269/) (2025)
- [InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning](https://mlsanity.com/paper/2506.12411/) (2025)
- [Backdoor Unlearning by Linear Task Decomposition](https://mlsanity.com/paper/2510.14845/) (2025)
- [Assimilation Matters: Model-level Backdoor Detection in Vision-Language Pretrained Models](https://mlsanity.com/paper/2512.00343/) (2025)
- [Hidden Ads: Behavior Triggered Semantic Backdoors for Advertisement Injection in Vision Language Models](https://mlsanity.com/paper/2603.27522/) (2026)
- [BYORn: Bootstrap Your Own Responses to Defend Large Vision-Language Models Against Backdoor Attacks](https://mlsanity.com/paper/2606.02947/) (2026)
- [Beyond Native Success: Auditing Deployment-Interface Exposure of CLIP Backdoors](https://mlsanity.com/paper/2606.17815/) (2026)
- [The Platonic Defense: Backdoor Defense for Self-Supervised Encoders in the Era of Large Scale Pre-training](https://mlsanity.com/paper/2606.29451/) (2026)
- [When Modalities Fail to Tango: Conformal Backdoor Detection in Multimodal Contrastive Learning](https://mlsanity.com/paper/2608.04052/) (2026)
- [DSPrompt: Dynamic Soft Prompt Defense Against M-RAG Corruption](https://mlsanity.com/paper/2608.16536/) (2026)
- [ViTeGate: Visual-Textual Triggered Knowledge Poisoning for Vision-Language Retrieval-Augmented Generation](https://mlsanity.com/paper/2609.14685/) (2026)
- [TraceGuard: Adaptive Multimodal Poison Filtering through Cross-Feature Rank Agreement](https://mlsanity.com/paper/2609.29099/) (2026)

## Abstract (arXiv)

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 data that powers large multimodal models such as CLIP, makes them extremely vulnerable to various types of targeted data poisoning and backdoor attacks. Despite this vulnerability, robust contrastive vision-language pre-training against such attacks has remained unaddressed. In this work, we propose ROCLIP, the first effective method for robust pre-training multimodal vision-language models against targeted data poisoning and backdoor attacks. ROCLIP effectively breaks the association between poisoned image-caption pairs by considering a relatively large and varying pool of random captions, and matching every image with the text that is most similar to it in the pool instead of its own caption, every few epochs.It also leverages image and text augmentations to further strengthen the defense and improve the performance of the model. Our extensive experiments show that ROCLIP renders state-of-the-art targeted data poisoning and backdoor attacks ineffective during pre-training CLIP models. In particular, ROCLIP decreases the success rate for targeted data poisoning attacks from 93.75% to 12.5% and that of backdoor attacks down to 0%, while improving the model's linear probe performance by 10% and maintains a similar zero shot performance compared to CLIP. By increasing the frequency of matching, ROCLIP is able to defend strong attacks, which add up to 1% poisoned examples to the data, and successfully maintain a low attack success rate of 12.5%, while trading off the performance on some tasks.