FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3215404543> ?p ?o ?g. }

• W3215404543 endingPage "3830" @default.
• W3215404543 startingPage "3816" @default.
• W3215404543 abstract "Deep neural networks (DNNs), regardless of their impressive performance, are vulnerable to attacks from adversarial inputs and, more recently, Trojans to misguide or hijack the decision of the model. We expose the existence of an intriguing class of spatially bounded, physically realizable, adversarial examples— Universal NaTuralistic adversarial paTches—we call TnTs, by exploring the super set of the spatially bounded adversarial example space and the natural input space within generative adversarial networks. Now, an adversary can arm themselves with a patch that is naturalistic, less malicious-looking, physically realizable, highly effective—achieving high attack success rates, and universal. A TnT is universal because any input image captured with a TnT in the scene will: i) misguide a network (untargeted attack); or ii) force the network to make a malicious decision (targeted attack). Interestingly, now, an adversarial patch attacker has the potential to exert a greater level of control—the ability to choose a location independent, natural-looking patch as a trigger in contrast to being constrained to noisy perturbations—an ability is thus far shown to be only possible with Trojan attack methods needing to interfere with the model building processes to embed a backdoor at the risk discovery; but, still realize a patch deployable in the physical world. Through extensive experiments on the large-scale visual classification task, <monospace xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>ImageNet</monospace> with evaluations across its entire validation set of 50,000 images, we demonstrate the realistic threat from TnTs and the robustness of the attack. We show a generalization of the attack to create patches achieving higher attack success rates than existing state-of-the-art methods. Our results show the generalizability of the attack to different visual classification tasks ( <monospace xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>CIFAR-10</monospace> , <monospace xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>GTSRB</monospace> , <monospace xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>PubFig</monospace> ) and multiple state-of-the-art deep neural networks such as WideResnet50, Inception-V3 and VGG-16." @default.
• W3215404543 created "2021-12-06" @default.
• W3215404543 creator A5009850797 @default.
• W3215404543 creator A5028714018 @default.
• W3215404543 creator A5048703299 @default.
• W3215404543 creator A5058061726 @default.
• W3215404543 creator A5070336991 @default.
• W3215404543 date "2022-01-01" @default.
• W3215404543 modified "2023-10-05" @default.
• W3215404543 title "TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems" @default.
• W3215404543 cites W1673923490 @default.
• W3215404543 cites W1677182931 @default.
• W3215404543 cites W2067713319 @default.
• W3215404543 cites W2099471712 @default.
• W3215404543 cites W2117539524 @default.
• W3215404543 cites W2119112357 @default.
• W3215404543 cites W2145287260 @default.
• W3215404543 cites W2158213899 @default.
• W3215404543 cites W2325939864 @default.
• W3215404543 cites W2408141691 @default.
• W3215404543 cites W2535873859 @default.
• W3215404543 cites W2543927648 @default.
• W3215404543 cites W2603766943 @default.
• W3215404543 cites W2734506812 @default.
• W3215404543 cites W2748789698 @default.
• W3215404543 cites W2753783305 @default.
• W3215404543 cites W2774423163 @default.
• W3215404543 cites W2781800156 @default.
• W3215404543 cites W2783555701 @default.
• W3215404543 cites W2798302089 @default.
• W3215404543 cites W2803850896 @default.
• W3215404543 cites W2902867332 @default.
• W3215404543 cites W2905423756 @default.
• W3215404543 cites W2910992787 @default.
• W3215404543 cites W2911634294 @default.
• W3215404543 cites W2932026309 @default.
• W3215404543 cites W2934843808 @default.
• W3215404543 cites W2962835968 @default.
• W3215404543 cites W2962846186 @default.
• W3215404543 cites W2962879692 @default.
• W3215404543 cites W2963207607 @default.
• W3215404543 cites W2963302614 @default.
• W3215404543 cites W2963542245 @default.
• W3215404543 cites W2963557656 @default.
• W3215404543 cites W2963564844 @default.
• W3215404543 cites W2963857521 @default.
• W3215404543 cites W2964137095 @default.
• W3215404543 cites W2964253222 @default.
• W3215404543 cites W2964318098 @default.
• W3215404543 cites W2970971581 @default.
• W3215404543 cites W2981597369 @default.
• W3215404543 cites W2996629283 @default.
• W3215404543 cites W3022179901 @default.
• W3215404543 cites W3034796035 @default.
• W3215404543 cites W3036426855 @default.
• W3215404543 cites W3081488247 @default.
• W3215404543 cites W3101294892 @default.
• W3215404543 cites W3102748184 @default.
• W3215404543 cites W3103340107 @default.
• W3215404543 cites W3114686421 @default.
• W3215404543 cites W3157207381 @default.
• W3215404543 cites W3177096435 @default.
• W3215404543 cites W3195462295 @default.
• W3215404543 doi "https://doi.org/10.1109/tifs.2022.3198857" @default.
• W3215404543 hasPublicationYear "2022" @default.
• W3215404543 type Work @default.
• W3215404543 sameAs 3215404543 @default.
• W3215404543 citedByCount "6" @default.
• W3215404543 countsByYear W32154045432022 @default.
• W3215404543 countsByYear W32154045432023 @default.
• W3215404543 crossrefType "journal-article" @default.
• W3215404543 hasAuthorship W3215404543A5009850797 @default.
• W3215404543 hasAuthorship W3215404543A5028714018 @default.
• W3215404543 hasAuthorship W3215404543A5048703299 @default.
• W3215404543 hasAuthorship W3215404543A5058061726 @default.
• W3215404543 hasAuthorship W3215404543A5070336991 @default.
• W3215404543 hasBestOaLocation W32154045432 @default.
• W3215404543 hasConcept C119857082 @default.
• W3215404543 hasConcept C134306372 @default.
• W3215404543 hasConcept C154945302 @default.
• W3215404543 hasConcept C174333608 @default.
• W3215404543 hasConcept C177264268 @default.
• W3215404543 hasConcept C199360897 @default.
• W3215404543 hasConcept C2777212361 @default.
• W3215404543 hasConcept C2781045450 @default.
• W3215404543 hasConcept C33923547 @default.
• W3215404543 hasConcept C34388435 @default.
• W3215404543 hasConcept C37736160 @default.
• W3215404543 hasConcept C38652104 @default.
• W3215404543 hasConcept C41008148 @default.
• W3215404543 hasConcept C41065033 @default.
• W3215404543 hasConcept C541664917 @default.
• W3215404543 hasConcept C80444323 @default.
• W3215404543 hasConceptScore W3215404543C119857082 @default.
• W3215404543 hasConceptScore W3215404543C134306372 @default.
• W3215404543 hasConceptScore W3215404543C154945302 @default.
• W3215404543 hasConceptScore W3215404543C174333608 @default.
• W3215404543 hasConceptScore W3215404543C177264268 @default.

• next