Towards Understanding Adversarial Robustness of Optical Flow Networks
Recent work demonstrated the lack of robustness of optical flow networks to physical patch-based adversarial attacks. The possibility to physically attack a basic component of automotive systems is a reason for serious concerns. In this paper, we analyze the cause of the problem and show that the lack of robustness is rooted in the classical aperture problem of optical flow estimation in combination with bad choices in the details of the network architecture. We show how these mistakes can be rectified in order to make optical flow networks robust to physical patch-based attacks. Additionally, we take a look at global white-box attacks in the scope of optical flow. We find that targeted white-box attacks can be crafted to bias flow estimation models towards any desired output, but this requires access to the input images and model weights. However, in the case of universal attacks, we find that optical flow networks are robust. Code is available at https://github.com/lmb-freiburg/understanding_flow_robustness.
Code (1)
Tasks
Adversarial RobustnessOptical Flow EstimationSimilar Papers 제목 키워드 기반
A Perturbation-Constrained Adversarial Attack for Evaluating the Robustness of Optical Flow
Recent optical flow methods are almost exclusively judged in terms of accuracy, while their robustness is often neglected. Although adversarial attacks offer a useful tool to perform such an analysis, current attacks on …
Adversarial AttackAdversarial RobustnessOptical Flow EstimationDetection Defenses: An Empty Promise against Adversarial Patch Attacks on Optical Flow
Adversarial patches undermine the reliability of optical flow predictions when placed in arbitrary scene locations. Therefore, they pose a realistic threat to real-world motion detection and its downstream applications. …
Adversarial RobustnessMotion Detectionmotion predictionOptical Flow EstimationAttacking Optical Flow
Deep neural nets achieve state-of-the-art performance on the problem of optical flow estimation. Since optical flow is used in several safety-critical applications like self-driving cars, it is important to gain insights…
DecoderOptical Flow EstimationSelf-Driving CarsBenchmarking the Robustness of Optical Flow Estimation to Corruptions
Optical flow estimation is extensively used in autonomous driving and video editing. While existing models demonstrate state-of-the-art performance across various benchmarks, the robustness of these methods has been infr…
Autonomous DrivingBenchmarkingOptical Flow EstimationVideo EditingAttacking Motion Estimation with Adversarial Snow
Current adversarial attacks for motion estimation (optical flow) optimize small per-pixel perturbations, which are unlikely to appear in the real world. In contrast, we exploit a real-world weather phenomenon for a novel…
Motion EstimationOptical Flow Estimation