Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313164923> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4313164923 abstract "Recent studies have shown the vulnerability of deep neural networks (DNNs) to adversarial examples induced by added imperceptible perturbations to the input images. Most of the attack studies focused on target classifiers, but few aimed at target detectors that are more challenging. This paper proposes a more natural and robust adversarial attack scheme against practical object detectors. First, we extract the target area through image semantic segmentation, and perturbations are only added to the extracted target area to generate more practical adversarial examples. Then, style transfer is adopted to make the generated adversarial examples more natural-looking. Finally, we improve our robustness against adversarial examples by simulating angle, lighting, distance, and background changes. Our generated adversarial examples have proved more successful and robust in adversarial attacks than other methods. This paper sheds light on the potential threat of adversarial examples to the real physical world and hopefully provides guidance for defending against such natural and robust adversarial example attacks." @default.
- W4313164923 created "2023-01-06" @default.
- W4313164923 creator A5029494148 @default.
- W4313164923 creator A5063187928 @default.
- W4313164923 date "2022-09-23" @default.
- W4313164923 modified "2023-09-23" @default.
- W4313164923 title "Stealth Attacks: A Natural and Robust Physical World Attack Against Object Detectors" @default.
- W4313164923 cites W1689711448 @default.
- W4313164923 cites W2117130368 @default.
- W4313164923 cites W2797694788 @default.
- W4313164923 cites W2963404857 @default.
- W4313164923 cites W3110105524 @default.
- W4313164923 doi "https://doi.org/10.1109/cei57409.2022.9950141" @default.
- W4313164923 hasPublicationYear "2022" @default.
- W4313164923 type Work @default.
- W4313164923 citedByCount "0" @default.
- W4313164923 crossrefType "proceedings-article" @default.
- W4313164923 hasAuthorship W4313164923A5029494148 @default.
- W4313164923 hasAuthorship W4313164923A5063187928 @default.
- W4313164923 hasConcept C104317684 @default.
- W4313164923 hasConcept C134306372 @default.
- W4313164923 hasConcept C154945302 @default.
- W4313164923 hasConcept C166957645 @default.
- W4313164923 hasConcept C185592680 @default.
- W4313164923 hasConcept C205649164 @default.
- W4313164923 hasConcept C2776151529 @default.
- W4313164923 hasConcept C2776608160 @default.
- W4313164923 hasConcept C2781238097 @default.
- W4313164923 hasConcept C2984842247 @default.
- W4313164923 hasConcept C31972630 @default.
- W4313164923 hasConcept C33923547 @default.
- W4313164923 hasConcept C37736160 @default.
- W4313164923 hasConcept C38652104 @default.
- W4313164923 hasConcept C41008148 @default.
- W4313164923 hasConcept C50644808 @default.
- W4313164923 hasConcept C55493867 @default.
- W4313164923 hasConcept C63479239 @default.
- W4313164923 hasConcept C76155785 @default.
- W4313164923 hasConcept C77618280 @default.
- W4313164923 hasConcept C89600930 @default.
- W4313164923 hasConcept C94915269 @default.
- W4313164923 hasConcept C95713431 @default.
- W4313164923 hasConceptScore W4313164923C104317684 @default.
- W4313164923 hasConceptScore W4313164923C134306372 @default.
- W4313164923 hasConceptScore W4313164923C154945302 @default.
- W4313164923 hasConceptScore W4313164923C166957645 @default.
- W4313164923 hasConceptScore W4313164923C185592680 @default.
- W4313164923 hasConceptScore W4313164923C205649164 @default.
- W4313164923 hasConceptScore W4313164923C2776151529 @default.
- W4313164923 hasConceptScore W4313164923C2776608160 @default.
- W4313164923 hasConceptScore W4313164923C2781238097 @default.
- W4313164923 hasConceptScore W4313164923C2984842247 @default.
- W4313164923 hasConceptScore W4313164923C31972630 @default.
- W4313164923 hasConceptScore W4313164923C33923547 @default.
- W4313164923 hasConceptScore W4313164923C37736160 @default.
- W4313164923 hasConceptScore W4313164923C38652104 @default.
- W4313164923 hasConceptScore W4313164923C41008148 @default.
- W4313164923 hasConceptScore W4313164923C50644808 @default.
- W4313164923 hasConceptScore W4313164923C55493867 @default.
- W4313164923 hasConceptScore W4313164923C63479239 @default.
- W4313164923 hasConceptScore W4313164923C76155785 @default.
- W4313164923 hasConceptScore W4313164923C77618280 @default.
- W4313164923 hasConceptScore W4313164923C89600930 @default.
- W4313164923 hasConceptScore W4313164923C94915269 @default.
- W4313164923 hasConceptScore W4313164923C95713431 @default.
- W4313164923 hasLocation W43131649231 @default.
- W4313164923 hasOpenAccess W4313164923 @default.
- W4313164923 hasPrimaryLocation W43131649231 @default.
- W4313164923 hasRelatedWork W1971759388 @default.
- W4313164923 hasRelatedWork W2004370856 @default.
- W4313164923 hasRelatedWork W2019566805 @default.
- W4313164923 hasRelatedWork W2025800131 @default.
- W4313164923 hasRelatedWork W2095705906 @default.
- W4313164923 hasRelatedWork W2383464976 @default.
- W4313164923 hasRelatedWork W2739874619 @default.
- W4313164923 hasRelatedWork W2922421953 @default.
- W4313164923 hasRelatedWork W2975200075 @default.
- W4313164923 hasRelatedWork W1967061043 @default.
- W4313164923 isParatext "false" @default.
- W4313164923 isRetracted "false" @default.
- W4313164923 workType "article" @default.