Matches in SemOpenAlex for { <https://semopenalex.org/work/W2940718416> ?p ?o ?g. }
- W2940718416 abstract "Most of the data manipulation attacks on deep neural networks (DNNs) during the training stage introduce a perceptible noise that can be catered by preprocessing during inference or can be identified during the validation phase. Therefore, data poisoning attacks during inference (e.g., adversarial attacks) are becoming more popular. However, many of them do not consider the imperceptibility factor in their optimization algorithms, and can be detected by correlation and structural similarity analysis, or noticeable (e.g., by humans) in a multi-level security system. Moreover, the majority of the inference attack relies on some knowledge about the training dataset. In this paper, we propose a novel methodology which automatically generates imperceptible attack images by using the back-propagation algorithm on pre-trained DNNs, without requiring any information about the training dataset (i.e., completely training data-unaware). We present a case study on traffic sign detection using the VGGNet trained on the German Traffic Sign Recognition Benchmarks dataset in an autonomous driving use case. Our results demonstrate that the generated attack images successfully perform misclassification while remaining imperceptible in both subjective and objective quality tests." @default.
- W2940718416 created "2019-05-03" @default.
- W2940718416 creator A5005190949 @default.
- W2940718416 creator A5023695007 @default.
- W2940718416 creator A5058712739 @default.
- W2940718416 creator A5066402727 @default.
- W2940718416 creator A5074265316 @default.
- W2940718416 date "2019-07-01" @default.
- W2940718416 modified "2023-10-11" @default.
- W2940718416 title "TrISec: Training Data-Unaware Imperceptible Security Attacks on Deep Neural Networks" @default.
- W2940718416 cites W1932198206 @default.
- W2940718416 cites W2099471712 @default.
- W2940718416 cites W2117876524 @default.
- W2940718416 cites W2180612164 @default.
- W2940718416 cites W2243397390 @default.
- W2940718416 cites W2342840547 @default.
- W2940718416 cites W2528914598 @default.
- W2940718416 cites W2535690855 @default.
- W2940718416 cites W2555895109 @default.
- W2940718416 cites W2603766943 @default.
- W2940718416 cites W2739032812 @default.
- W2940718416 cites W2746600820 @default.
- W2940718416 cites W2748789698 @default.
- W2940718416 cites W2755893646 @default.
- W2940718416 cites W2785405530 @default.
- W2940718416 cites W2788963265 @default.
- W2940718416 cites W2798919674 @default.
- W2940718416 cites W2886189420 @default.
- W2940718416 cites W2888975495 @default.
- W2940718416 cites W2897317743 @default.
- W2940718416 cites W2898804478 @default.
- W2940718416 cites W2899111971 @default.
- W2940718416 cites W2914433962 @default.
- W2940718416 cites W2962763344 @default.
- W2940718416 cites W2963003451 @default.
- W2940718416 cites W2963098487 @default.
- W2940718416 cites W2963207607 @default.
- W2940718416 cites W2963343288 @default.
- W2940718416 cites W2963542245 @default.
- W2940718416 cites W2963857521 @default.
- W2940718416 cites W2963888996 @default.
- W2940718416 cites W2964153729 @default.
- W2940718416 cites W3103557498 @default.
- W2940718416 cites W3103940881 @default.
- W2940718416 doi "https://doi.org/10.1109/iolts.2019.8854425" @default.
- W2940718416 hasPublicationYear "2019" @default.
- W2940718416 type Work @default.
- W2940718416 sameAs 2940718416 @default.
- W2940718416 citedByCount "12" @default.
- W2940718416 countsByYear W29407184162019 @default.
- W2940718416 countsByYear W29407184162020 @default.
- W2940718416 countsByYear W29407184162021 @default.
- W2940718416 countsByYear W29407184162022 @default.
- W2940718416 crossrefType "proceedings-article" @default.
- W2940718416 hasAuthorship W2940718416A5005190949 @default.
- W2940718416 hasAuthorship W2940718416A5023695007 @default.
- W2940718416 hasAuthorship W2940718416A5058712739 @default.
- W2940718416 hasAuthorship W2940718416A5066402727 @default.
- W2940718416 hasAuthorship W2940718416A5074265316 @default.
- W2940718416 hasBestOaLocation W29407184162 @default.
- W2940718416 hasConcept C103278499 @default.
- W2940718416 hasConcept C10551718 @default.
- W2940718416 hasConcept C108583219 @default.
- W2940718416 hasConcept C115961682 @default.
- W2940718416 hasConcept C119857082 @default.
- W2940718416 hasConcept C121332964 @default.
- W2940718416 hasConcept C124101348 @default.
- W2940718416 hasConcept C134306372 @default.
- W2940718416 hasConcept C139676723 @default.
- W2940718416 hasConcept C153180895 @default.
- W2940718416 hasConcept C153294291 @default.
- W2940718416 hasConcept C154945302 @default.
- W2940718416 hasConcept C2776214188 @default.
- W2940718416 hasConcept C2777211547 @default.
- W2940718416 hasConcept C2983860417 @default.
- W2940718416 hasConcept C2984842247 @default.
- W2940718416 hasConcept C33923547 @default.
- W2940718416 hasConcept C34736171 @default.
- W2940718416 hasConcept C41008148 @default.
- W2940718416 hasConcept C50644808 @default.
- W2940718416 hasConcept C6528762 @default.
- W2940718416 hasConceptScore W2940718416C103278499 @default.
- W2940718416 hasConceptScore W2940718416C10551718 @default.
- W2940718416 hasConceptScore W2940718416C108583219 @default.
- W2940718416 hasConceptScore W2940718416C115961682 @default.
- W2940718416 hasConceptScore W2940718416C119857082 @default.
- W2940718416 hasConceptScore W2940718416C121332964 @default.
- W2940718416 hasConceptScore W2940718416C124101348 @default.
- W2940718416 hasConceptScore W2940718416C134306372 @default.
- W2940718416 hasConceptScore W2940718416C139676723 @default.
- W2940718416 hasConceptScore W2940718416C153180895 @default.
- W2940718416 hasConceptScore W2940718416C153294291 @default.
- W2940718416 hasConceptScore W2940718416C154945302 @default.
- W2940718416 hasConceptScore W2940718416C2776214188 @default.
- W2940718416 hasConceptScore W2940718416C2777211547 @default.
- W2940718416 hasConceptScore W2940718416C2983860417 @default.
- W2940718416 hasConceptScore W2940718416C2984842247 @default.
- W2940718416 hasConceptScore W2940718416C33923547 @default.
- W2940718416 hasConceptScore W2940718416C34736171 @default.
- W2940718416 hasConceptScore W2940718416C41008148 @default.