paper-with-me

Papers

Towards Understanding Adversarial Robustness of Optical Flow Networks

2021-03-30 · CVPR 2022 1 · Simon Schrodi, Tonmoy Saikia, Thomas Brox

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.

📄 PDF Abstract BibTeX arXiv:2103.16255

Code (1)

lmb-freiburg/understanding_flow_robustness 공식 구현 pytorch

Tasks

Adversarial RobustnessOptical Flow Estimation

Similar Papers 제목 키워드 기반

A Perturbation-Constrained Adversarial Attack for Evaluating the Robustness of Optical Flow

2022-03-24 · Jenny Schmalfuss, Philipp Scholze, Andrés Bruhn

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 Estimation

Detection Defenses: An Empty Promise against Adversarial Patch Attacks on Optical Flow

2023-10-26 · Erik Scheurer, Jenny Schmalfuss, Alexander Lis, Andrés Bruhn

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 Estimation

Attacking Optical Flow

2019-10-22 · ICCV 2019 10 · Anurag Ranjan, Joel Janai, Andreas Geiger, Michael J. Black

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 Cars

Benchmarking the Robustness of Optical Flow Estimation to Corruptions

2024-11-22 · Zhonghua Yi, Hao Shi, Qi Jiang, Yao Gao 외

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 Editing

Attacking Motion Estimation with Adversarial Snow

2022-10-20 · Jenny Schmalfuss, Lukas Mehl, Andrés Bruhn

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