Ontology type: schema:Chapter Open Access: True
2018-10-06
AUTHORSChaowei Xiao , Ruizhi Deng , Bo Li , Fisher Yu , Mingyan Liu , Dawn Song
ABSTRACTDeep Neural Networks (DNNs) have been widely applied in various recognition tasks. However, recently DNNs have been shown to be vulnerable against adversarial examples, which can mislead DNNs to make arbitrary incorrect predictions. While adversarial examples are well studied in classification tasks, other learning problems may have different properties. For instance, semantic segmentation requires additional components such as dilated convolutions and multiscale processing. In this paper, we aim to characterize adversarial examples based on spatial context information in semantic segmentation. We observe that spatial consistency information can be potentially leveraged to detect adversarial examples robustly even when a strong adaptive attacker has access to the model and detection strategies. We also show that adversarial examples based on attacks considered within the paper barely transfer among models, even though transferability is common in classification. Our observations shed new light on developing adversarial attacks and defenses to better understand the vulnerabilities of DNNs. More... »
PAGES220-237
Computer Vision – ECCV 2018
ISBN
978-3-030-01248-9
978-3-030-01249-6
http://scigraph.springernature.com/pub.10.1007/978-3-030-01249-6_14
DOIhttp://dx.doi.org/10.1007/978-3-030-01249-6_14
DIMENSIONShttps://app.dimensions.ai/details/publication/pub.1107454674
JSON-LD is the canonical representation for SciGraph data.
TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT
[
{
"@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json",
"about": [
{
"id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08",
"inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/",
"name": "Information and Computing Sciences",
"type": "DefinedTerm"
},
{
"id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801",
"inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/",
"name": "Artificial Intelligence and Image Processing",
"type": "DefinedTerm"
}
],
"author": [
{
"affiliation": {
"alternateName": "University of Michigan, Ann Arbor, USA",
"id": "http://www.grid.ac/institutes/grid.214458.e",
"name": [
"University of Michigan, Ann Arbor, USA"
],
"type": "Organization"
},
"familyName": "Xiao",
"givenName": "Chaowei",
"id": "sg:person.015156355516.52",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015156355516.52"
],
"type": "Person"
},
{
"affiliation": {
"alternateName": "Simon Fraser University, Burnaby, Canada",
"id": "http://www.grid.ac/institutes/grid.61971.38",
"name": [
"Simon Fraser University, Burnaby, Canada"
],
"type": "Organization"
},
"familyName": "Deng",
"givenName": "Ruizhi",
"id": "sg:person.016247430134.38",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016247430134.38"
],
"type": "Person"
},
{
"affiliation": {
"alternateName": "UC Berkeley, Berkeley, USA",
"id": "http://www.grid.ac/institutes/grid.47840.3f",
"name": [
"UIUC, Champaign, USA",
"UC Berkeley, Berkeley, USA"
],
"type": "Organization"
},
"familyName": "Li",
"givenName": "Bo",
"id": "sg:person.011355161257.61",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011355161257.61"
],
"type": "Person"
},
{
"affiliation": {
"alternateName": "UC Berkeley, Berkeley, USA",
"id": "http://www.grid.ac/institutes/grid.47840.3f",
"name": [
"UC Berkeley, Berkeley, USA"
],
"type": "Organization"
},
"familyName": "Yu",
"givenName": "Fisher",
"id": "sg:person.012020671543.60",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012020671543.60"
],
"type": "Person"
},
{
"affiliation": {
"alternateName": "University of Michigan, Ann Arbor, USA",
"id": "http://www.grid.ac/institutes/grid.214458.e",
"name": [
"University of Michigan, Ann Arbor, USA"
],
"type": "Organization"
},
"familyName": "Liu",
"givenName": "Mingyan",
"id": "sg:person.010560654372.62",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010560654372.62"
],
"type": "Person"
},
{
"affiliation": {
"alternateName": "UC Berkeley, Berkeley, USA",
"id": "http://www.grid.ac/institutes/grid.47840.3f",
"name": [
"UC Berkeley, Berkeley, USA"
],
"type": "Organization"
},
"familyName": "Song",
"givenName": "Dawn",
"id": "sg:person.01143152610.86",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01143152610.86"
],
"type": "Person"
}
],
"datePublished": "2018-10-06",
"datePublishedReg": "2018-10-06",
"description": "Deep Neural Networks (DNNs) have been widely applied in various recognition tasks. However, recently DNNs have been shown to be vulnerable against adversarial examples, which can mislead DNNs to make arbitrary incorrect predictions. While adversarial examples are well studied in classification tasks, other learning problems may have different properties. For instance, semantic segmentation requires additional components such as dilated convolutions and multiscale processing. In this paper, we aim to characterize adversarial examples based on spatial context information in semantic segmentation. We observe that spatial consistency information can be potentially leveraged to detect adversarial examples robustly even when a strong adaptive attacker has access to the model and detection strategies. We also show that adversarial examples based on attacks considered within the paper barely transfer among models, even though transferability is common in classification. Our observations shed new light on developing adversarial attacks and defenses to better understand the vulnerabilities of DNNs.",
"editor": [
{
"familyName": "Ferrari",
"givenName": "Vittorio",
"type": "Person"
},
{
"familyName": "Hebert",
"givenName": "Martial",
"type": "Person"
},
{
"familyName": "Sminchisescu",
"givenName": "Cristian",
"type": "Person"
},
{
"familyName": "Weiss",
"givenName": "Yair",
"type": "Person"
}
],
"genre": "chapter",
"id": "sg:pub.10.1007/978-3-030-01249-6_14",
"inLanguage": "en",
"isAccessibleForFree": true,
"isPartOf": {
"isbn": [
"978-3-030-01248-9",
"978-3-030-01249-6"
],
"name": "Computer Vision \u2013 ECCV 2018",
"type": "Book"
},
"keywords": [
"deep neural networks",
"adversarial examples",
"semantic segmentation",
"vulnerability of DNNs",
"consistency information",
"spatial context information",
"context information",
"adversarial attacks",
"adaptive attackers",
"classification task",
"neural network",
"multiscale processing",
"learning problem",
"recognition task",
"segmentation",
"detection strategy",
"task",
"attacks",
"incorrect predictions",
"information",
"attacker",
"network",
"example",
"convolution",
"classification",
"processing",
"instances",
"access",
"model",
"vulnerability",
"additional components",
"different properties",
"prediction",
"transferability",
"strategies",
"components",
"defense",
"properties",
"observations",
"new light",
"light",
"paper",
"problem"
],
"name": "Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation",
"pagination": "220-237",
"productId": [
{
"name": "dimensions_id",
"type": "PropertyValue",
"value": [
"pub.1107454674"
]
},
{
"name": "doi",
"type": "PropertyValue",
"value": [
"10.1007/978-3-030-01249-6_14"
]
}
],
"publisher": {
"name": "Springer Nature",
"type": "Organisation"
},
"sameAs": [
"https://doi.org/10.1007/978-3-030-01249-6_14",
"https://app.dimensions.ai/details/publication/pub.1107454674"
],
"sdDataset": "chapters",
"sdDatePublished": "2022-05-20T07:48",
"sdLicense": "https://scigraph.springernature.com/explorer/license/",
"sdPublisher": {
"name": "Springer Nature - SN SciGraph project",
"type": "Organization"
},
"sdSource": "s3://com-springernature-scigraph/baseset/20220519/entities/gbq_results/chapter/chapter_458.jsonl",
"type": "Chapter",
"url": "https://doi.org/10.1007/978-3-030-01249-6_14"
}
]Download the RDF metadata as: json-ld nt turtle xml License info
JSON-LD is a popular format for linked data which is fully compatible with JSON.
curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-01249-6_14'
N-Triples is a line-based linked data format ideal for batch operations.
curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-01249-6_14'
Turtle is a human-readable linked data format.
curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-01249-6_14'
RDF/XML is a standard XML format for linked data.
curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-030-01249-6_14'
This table displays all metadata directly associated to this object as RDF triples.
160 TRIPLES
23 PREDICATES
68 URIs
61 LITERALS
7 BLANK NODES