File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Counteracting Adversarial Attacks in Autonomous Driving

TitleCounteracting Adversarial Attacks in Autonomous Driving
Authors
KeywordsAdversarial defense
autonomous system
local smoothness
robust stereo vision
Issue Date2022
Citation
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2022, v. 41, n. 12, p. 5193-5206 How to Cite?
AbstractThis article studies the robust deep stereo vision in autonomous driving systems and counteracting adversarial attacks. The autonomous system operation requires real-time processing of measurement data which often contain significant uncertainties and noise. Adversarial attacks have been widely studied to simulate these perturbations in recent years. To counteract the practical attacks in autonomous systems, novel methods based on simulated attacks are proposed in this article. Univariate and multivariate functions are adopted to represent the relationships between the left and right input images and the deep stereo model. A stereo regularizer is proposed to guide the model to learn the implicit relationship between the images and characterize the loss function's local smoothness. The attacks are generated by maximizing the regularizer term to break the linearity and smoothness. The model then defends the attacks by minimizing the loss and regularization terms. Two techniques are developed in this article. The first technique, SmoothStereo, explores the basic knowledge from the physical world and smoothness, while the second technique, SmoothStereoV2, improves SmoothStereo through leveraging the smooth activation functions during the defense. SmoothStereoV2 can learn and utilize the gradient information concerning the attacks. The gradients of the smooth activation functions can handle attacks for improving the model robustness. Numerical experiments on KITTI datasets demonstrate that the proposed methods offer superior performance.
Persistent Identifierhttp://hdl.handle.net/10722/336315
ISSN
2023 Impact Factor: 2.7
2023 SCImago Journal Rankings: 0.957
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorSun, Qi-
dc.contributor.authorYao, Xufeng-
dc.contributor.authorRao, Arjun Ashok-
dc.contributor.authorYu, Bei-
dc.contributor.authorHu, Shiyan-
dc.date.accessioned2024-01-15T08:25:30Z-
dc.date.available2024-01-15T08:25:30Z-
dc.date.issued2022-
dc.identifier.citationIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2022, v. 41, n. 12, p. 5193-5206-
dc.identifier.issn0278-0070-
dc.identifier.urihttp://hdl.handle.net/10722/336315-
dc.description.abstractThis article studies the robust deep stereo vision in autonomous driving systems and counteracting adversarial attacks. The autonomous system operation requires real-time processing of measurement data which often contain significant uncertainties and noise. Adversarial attacks have been widely studied to simulate these perturbations in recent years. To counteract the practical attacks in autonomous systems, novel methods based on simulated attacks are proposed in this article. Univariate and multivariate functions are adopted to represent the relationships between the left and right input images and the deep stereo model. A stereo regularizer is proposed to guide the model to learn the implicit relationship between the images and characterize the loss function's local smoothness. The attacks are generated by maximizing the regularizer term to break the linearity and smoothness. The model then defends the attacks by minimizing the loss and regularization terms. Two techniques are developed in this article. The first technique, SmoothStereo, explores the basic knowledge from the physical world and smoothness, while the second technique, SmoothStereoV2, improves SmoothStereo through leveraging the smooth activation functions during the defense. SmoothStereoV2 can learn and utilize the gradient information concerning the attacks. The gradients of the smooth activation functions can handle attacks for improving the model robustness. Numerical experiments on KITTI datasets demonstrate that the proposed methods offer superior performance.-
dc.languageeng-
dc.relation.ispartofIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems-
dc.subjectAdversarial defense-
dc.subjectautonomous system-
dc.subjectlocal smoothness-
dc.subjectrobust stereo vision-
dc.titleCounteracting Adversarial Attacks in Autonomous Driving-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TCAD.2022.3166112-
dc.identifier.scopuseid_2-s2.0-85128252915-
dc.identifier.volume41-
dc.identifier.issue12-
dc.identifier.spage5193-
dc.identifier.epage5206-
dc.identifier.eissn1937-4151-
dc.identifier.isiWOS:000906580100005-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats