Robustness Guarantees for Deep Neural Networks on Videos

by   Min Wu, et al.
University of Oxford

The widespread adoption of deep learning models places demands on their robustness. In this paper, we consider the robustness of deep neural networks on videos, which comprise both the spatial features of individual frames extracted by a convolutional neural network and the temporal dynamics between adjacent frames captured by a recurrent neural network. To measure robustness, we study the maximum safe radius problem, which computes the minimum distance from the optical flow set obtained from a given input to that of an adversarial example in the norm ball. We demonstrate that, under the assumption of Lipschitz continuity, the problem can be approximated using finite optimisation via discretising the optical flow space, and the approximation has provable guarantees. We then show that the finite optimisation problem can be solved by utilising a two-player turn-based game in a cooperative setting, where the first player selects the optical flows and the second player determines the dimensions to be manipulated in the chosen flow. We employ an anytime approach to solve the game, in the sense of approximating the value of the game by monotonically improving its upper and lower bounds. We exploit a gradient-based search algorithm to compute the upper bounds, and the admissible A* algorithm to update the lower bounds. Finally, we evaluate our framework on the UCF101 video dataset.


page 7

page 8

page 12

page 13

page 14


A Game-Based Approximate Verification of Deep Neural Networks with Provable Guarantees

Despite the improved accuracy of deep neural networks, the discovery of ...

Global Robustness Evaluation of Deep Neural Networks with Provable Guarantees for L0 Norm

Deployment of deep neural networks (DNNs) in safety or security-critical...

The Invertible U-Net for Optical-Flow-free Video Interframe Generation

Video frame interpolation is the task of creating an interface between t...

Optical-Flow-Reuse-Based Bidirectional Recurrent Network for Space-Time Video Super-Resolution

In this paper, we consider the task of space-time video super-resolution...

What Causes Optical Flow Networks to be Vulnerable to Physical Adversarial Attacks

Recent work demonstrated the lack of robustness of optical flow networks...

Dual-view Snapshot Compressive Imaging via Optical Flow Aided Recurrent Neural Network

Dual-view snapshot compressive imaging (SCI) aims to capture videos from...

Assessing Robustness of Text Classification through Maximal Safe Radius Computation

Neural network NLP models are vulnerable to small modifications of the i...

Please sign up or login with your details

Forgot password? Click here to reset