Matches in SemOpenAlex for { <https://semopenalex.org/work/W3216736699> ?p ?o ?g. }
- W3216736699 abstract "Adversarial attacks provide a good way to study the robustness of deep learning models. One category of methods in transfer-based black-box attack utilizes several image transformation operations to improve the transferability of adversarial examples, which is effective, but fails to take the specific characteristic of the input image into consideration. In this work, we propose a novel architecture, called Adaptive Image Transformation Learner (AITL), which incorporates different image transformation operations into a unified framework to further improve the transferability of adversarial examples. Unlike the fixed combinational transformations used in existing works, our elaborately designed transformation learner adaptively selects the most effective combination of image transformations specific to the input image. Extensive experiments on ImageNet demonstrate that our method significantly improves the attack success rates on both normally trained models and defense models under various settings." @default.
- W3216736699 created "2021-12-06" @default.
- W3216736699 creator A5009171844 @default.
- W3216736699 creator A5017784727 @default.
- W3216736699 creator A5022033626 @default.
- W3216736699 date "2021-11-27" @default.
- W3216736699 modified "2023-10-17" @default.
- W3216736699 title "Adaptive Image Transformations for Transfer-based Adversarial Attack" @default.
- W3216736699 cites W104184427 @default.
- W3216736699 cites W2117539524 @default.
- W3216736699 cites W2183341477 @default.
- W3216736699 cites W2194775991 @default.
- W3216736699 cites W2243397390 @default.
- W3216736699 cites W2302255633 @default.
- W3216736699 cites W2412782625 @default.
- W3216736699 cites W2594877703 @default.
- W3216736699 cites W2607219512 @default.
- W3216736699 cites W2630837129 @default.
- W3216736699 cites W2746600820 @default.
- W3216736699 cites W2774018344 @default.
- W3216736699 cites W2774644650 @default.
- W3216736699 cites W2798302089 @default.
- W3216736699 cites W2945793108 @default.
- W3216736699 cites W2949736877 @default.
- W3216736699 cites W2962847335 @default.
- W3216736699 cites W2962898354 @default.
- W3216736699 cites W2963001136 @default.
- W3216736699 cites W2963062382 @default.
- W3216736699 cites W2963098487 @default.
- W3216736699 cites W2963143631 @default.
- W3216736699 cites W2963163009 @default.
- W3216736699 cites W2963207607 @default.
- W3216736699 cites W2963361074 @default.
- W3216736699 cites W2963384482 @default.
- W3216736699 cites W2963389226 @default.
- W3216736699 cites W2963399829 @default.
- W3216736699 cites W2963466847 @default.
- W3216736699 cites W2963557656 @default.
- W3216736699 cites W2963744840 @default.
- W3216736699 cites W2963770044 @default.
- W3216736699 cites W2963771536 @default.
- W3216736699 cites W2963821229 @default.
- W3216736699 cites W2963894448 @default.
- W3216736699 cites W2963920068 @default.
- W3216736699 cites W2964081807 @default.
- W3216736699 cites W2964121744 @default.
- W3216736699 cites W2964153729 @default.
- W3216736699 cites W2964253222 @default.
- W3216736699 cites W2964288706 @default.
- W3216736699 cites W2964350391 @default.
- W3216736699 cites W2969542116 @default.
- W3216736699 cites W2969985801 @default.
- W3216736699 cites W2971126145 @default.
- W3216736699 cites W2995053405 @default.
- W3216736699 cites W2996261834 @default.
- W3216736699 cites W2996564870 @default.
- W3216736699 cites W2996694668 @default.
- W3216736699 cites W3006076803 @default.
- W3216736699 cites W3034190247 @default.
- W3216736699 cites W3034994123 @default.
- W3216736699 cites W3035569111 @default.
- W3216736699 cites W3041992316 @default.
- W3216736699 cites W3099873944 @default.
- W3216736699 cites W3100197791 @default.
- W3216736699 cites W3102631365 @default.
- W3216736699 cites W3103340107 @default.
- W3216736699 cites W3103385169 @default.
- W3216736699 cites W3104032928 @default.
- W3216736699 cites W3104620392 @default.
- W3216736699 cites W3127807678 @default.
- W3216736699 cites W3128513745 @default.
- W3216736699 cites W3136429007 @default.
- W3216736699 cites W3167676691 @default.
- W3216736699 cites W3171288285 @default.
- W3216736699 cites W3177184533 @default.
- W3216736699 cites W3202281277 @default.
- W3216736699 doi "https://doi.org/10.48550/arxiv.2111.13844" @default.
- W3216736699 hasPublicationYear "2021" @default.
- W3216736699 type Work @default.
- W3216736699 sameAs 3216736699 @default.
- W3216736699 citedByCount "0" @default.
- W3216736699 crossrefType "posted-content" @default.
- W3216736699 hasAuthorship W3216736699A5009171844 @default.
- W3216736699 hasAuthorship W3216736699A5017784727 @default.
- W3216736699 hasAuthorship W3216736699A5022033626 @default.
- W3216736699 hasBestOaLocation W32167366991 @default.
- W3216736699 hasConcept C104317684 @default.
- W3216736699 hasConcept C108583219 @default.
- W3216736699 hasConcept C115961682 @default.
- W3216736699 hasConcept C119857082 @default.
- W3216736699 hasConcept C140331021 @default.
- W3216736699 hasConcept C150899416 @default.
- W3216736699 hasConcept C154945302 @default.
- W3216736699 hasConcept C185592680 @default.
- W3216736699 hasConcept C204241405 @default.
- W3216736699 hasConcept C31972630 @default.
- W3216736699 hasConcept C37736160 @default.
- W3216736699 hasConcept C41008148 @default.
- W3216736699 hasConcept C55493867 @default.
- W3216736699 hasConcept C61272859 @default.