KOPS - The Institutional Repository of the University of Konstanz

BARReL : Bottleneck Attention for Adversarial Robustness in Vision-Based Reinforcement Learning

BARReL : Bottleneck Attention for Adversarial Robustness in Vision-Based Reinforcement Learning

Cite This

Files in this item

Files Size Format View

There are no files associated with this item.

BYKOVETS, Eugene, Yannick METZ, Mennatallah EL-ASSADY, Daniel A. KEIM, Joachim M. BUHMANN, 2022. BARReL : Bottleneck Attention for Adversarial Robustness in Vision-Based Reinforcement Learning

@unpublished{Bykovets2022BARRe-58409, title={BARReL : Bottleneck Attention for Adversarial Robustness in Vision-Based Reinforcement Learning}, year={2022}, author={Bykovets, Eugene and Metz, Yannick and El-Assady, Mennatallah and Keim, Daniel A. and Buhmann, Joachim M.} }

<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:bibo="http://purl.org/ontology/bibo/" xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:void="http://rdfs.org/ns/void#" xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > <rdf:Description rdf:about="https://kops.uni-konstanz.de/rdf/resource/123456789/58409"> <dc:contributor>Buhmann, Joachim M.</dc:contributor> <dc:creator>El-Assady, Mennatallah</dc:creator> <dc:creator>Metz, Yannick</dc:creator> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-08-29T14:25:15Z</dcterms:available> <dc:contributor>Keim, Daniel A.</dc:contributor> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> <dc:creator>Keim, Daniel A.</dc:creator> <dcterms:abstract xml:lang="eng">Robustness to adversarial perturbations has been explored in many areas of computer vision. This robustness is particularly relevant in vision-based reinforcement learning, as the actions of autonomous agents might be safety-critic or impactful in the real world. We investigate the susceptibility of vision-based reinforcement learning agents to gradient-based adversarial attacks and evaluate a potential defense. We observe that Bottleneck Attention Modules (BAM) included in CNN architectures can act as potential tools to increase robustness against adversarial attacks. We show how learned attention maps can be used to recover activations of a convolutional layer by restricting the spatial activations to salient regions. Across a number of RL environments, BAM-enhanced architectures show increased robustness during inference. Finally, we discuss potential future research directions.</dcterms:abstract> <dc:contributor>Bykovets, Eugene</dc:contributor> <dc:contributor>El-Assady, Mennatallah</dc:contributor> <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/> <dc:language>eng</dc:language> <dc:creator>Buhmann, Joachim M.</dc:creator> <dc:contributor>Metz, Yannick</dc:contributor> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dc:creator>Bykovets, Eugene</dc:creator> <dcterms:title>BARReL : Bottleneck Attention for Adversarial Robustness in Vision-Based Reinforcement Learning</dcterms:title> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/58409"/> <dcterms:issued>2022</dcterms:issued> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2022-08-29T14:25:15Z</dc:date> <foaf:homepage rdf:resource="http://localhost:8080/jspui"/> <dc:rights>terms-of-use</dc:rights> </rdf:Description> </rdf:RDF>

This item appears in the following Collection(s)

Search KOPS


Browse

My Account