Clean-Label Backdoor Attacks on Video Recognition Models

Abstract

Deep neural networks (DNNs) are vulnerable to backdoor attacks which can hide backdoor triggers in DNNs by poisoning training data. A backdoored model behaves normally on clean test images, yet consistently predicts a particular target class for any test examples that contain the trigger pattern. As such, backdoor attacks are hard to detect, and have raised severe security concerns in real-world applications. Thus far, backdoor research has mostly been conducted in the image domain with image classification models. In this paper, we show that existing image backdoor attacks are far less effective on videos, and outline 4 strict conditions where existing attacks are likely to fail: 1) scenarios with more input dimensions (eg. videos), 2) scenarios with high resolution, 3) scenarios with a large number of classes and few examples per class (a "sparse dataset"), and 4) attacks with access to correct labels (eg. clean-label attacks). We propose the use of a universal adversarial trigger as the backdoor trigger to attack video recognition models, a situation where backdoor attacks are likely to be challenged by the above 4 strict conditions. We show on benchmark video datasets that our proposed backdoor attack can manipulate state-of-the-art video models with high success rates by poisoning only a small proportion of training data (without changing the labels). We also show that our proposed backdoor attack is resistant to state-of-the-art backdoor defense/detection methods, and can even be applied to improve image backdoor attacks. Our proposed video backdoor attack not only serves as a strong baseline for improving the robustness of video models, but also provides a new perspective for more understanding more powerful backdoor attacks.

arXiv commentCVPR2020

References in corpus (13)

• Sequence to Sequence Learning with Neural Networks
• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
• BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems
• Robust Physical-World Attacks on Deep Learning Models
• Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality
• Exploiting Feature and Class Relationships in Video Categorization with Regularized Deep Neural Networks
• Spectral Signatures in Backdoor Attacks
• Beyond Short Snippets: Deep Networks for Video Classification
• On the Convergence and Robustness of Adversarial Training
• Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets

Cited by in corpus (4)

• Poisoning MorphNet for Clean-Label Backdoor Attack to Point Clouds
• What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space
• IoU Attack: Towards Temporally Coherent Black-Box Adversarial Attack for Visual Object Tracking
• Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor