Pith. sign in

REVIEW 1 cited by

Towards Understanding Adversarial Robustness of Optical Flow Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2103.16255 v3 pith:7CHWT2PP submitted 2021-03-30 cs.CV

classification cs.CV
keywords flowopticalattacksnetworksrobustnessadversarialestimationfind
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Learning by Teaching: Engaging Students as Instructors of Large Language Models in Computer Science Education

    cs.CY 2025-08 unverdicted novelty 4.0 of 10

    The manuscript's abstract (a 'learning by teaching' AI study) does not match its full text (an energy-based test-time adaptation paper for depth completion).

Pith tools