BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
Authors:
Preprint
Abstract
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 specialized backdoor defenses for MCL models. This paper reveals the threats in this practical scenario that backdoor attacks can remain effective even after defenses and introduces the \emph{\toolns} attack, which is resistant to backdoor detection and model fine-tuning defenses. To achieve this, we draw motivations from the perspective of the Bayesian rule and propose a dual-embedding guided framework for backdoor attacks. Specifically, we ensure that visual trigger patterns approximate the textual target semantics in the embedding space, making it challenging to detect the subtle parameter variations induced by backdoor learning on such natural trigger patterns. Additionally, we optimize the visual trigger patterns to align the poisoned samples with target vision features in order to hinder the backdoor unlearning through clean fine-tuning. Extensive experiments demonstrate that our attack significantly outperforms state-of-the-art baselines (+45.3% ASR) in the presence of SoTA backdoor defenses, rendering these mitigation and detection strategies virtually ineffective. Furthermore, our approach effectively attacks some more rigorous scenarios like downstream tasks. We believe that this paper raises awareness regarding the potential threats associated with the practical application of multimodal contrastive learning and encourages the development of more robust defense mechanisms.Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor LearningInternational Journal of Computer Vision, 2025
- SSL-Cleanse: Trojan Detection and Mitigation in Self-Supervised Learning2024
- GhostEncoder: Stealthy backdoor attacks with dynamic triggers to pre-trained encoders in self-supervised learningComputers & Security, 2024
- Towards Defending Multiple $\ell _p$-Norm Bounded Adversarial Perturbations via Gated Batch NormalizationInternational Journal of Computer Vision, 2023
- Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical World2021
- Bias-Based Universal Adversarial Patch Attack for Automatic Check-Out2020
- Spatiotemporal Attacks for Embodied Agents2020
- UNITER: UNiversal Image-TExt Representation Learning2020
- DeepStyle: Multimodal Search Engine for Fashion and Interior DesignIEEE Access, 2019
- Large Scale Incremental Learning2019