Matches in SemOpenAlex for { <https://semopenalex.org/work/W3126451824> ?p ?o ?g. }
- W3126451824 abstract "Adversarial training is one of the most effective approaches defending against adversarial examples for deep learning models. Unlike other defense strategies, adversarial training aims to promote the robustness of models intrinsically. During the last few years, adversarial training has been studied and discussed from various aspects. A variety of improvements and developments of adversarial training are proposed, which were, however, neglected in existing surveys. For the first time in this survey, we systematically review the recent progress on adversarial training for adversarial robustness with a novel taxonomy. Then we discuss the generalization problems in adversarial training from three perspectives. Finally, we highlight the challenges which are not fully tackled and present potential future directions." @default.
- W3126451824 created "2021-02-15" @default.
- W3126451824 creator A5024709593 @default.
- W3126451824 creator A5029733098 @default.
- W3126451824 creator A5046225712 @default.
- W3126451824 creator A5071321132 @default.
- W3126451824 creator A5072156971 @default.
- W3126451824 date "2021-02-02" @default.
- W3126451824 modified "2023-10-02" @default.
- W3126451824 title "Recent Advances in Adversarial Training for Adversarial Robustness" @default.
- W3126451824 cites W2146989110 @default.
- W3126451824 cites W2230740169 @default.
- W3126451824 cites W2269778407 @default.
- W3126451824 cites W2460937040 @default.
- W3126451824 cites W2552767274 @default.
- W3126451824 cites W2612637113 @default.
- W3126451824 cites W2746314669 @default.
- W3126451824 cites W2765407302 @default.
- W3126451824 cites W2774018344 @default.
- W3126451824 cites W2783113218 @default.
- W3126451824 cites W2786118190 @default.
- W3126451824 cites W2798966449 @default.
- W3126451824 cites W2802379474 @default.
- W3126451824 cites W2803678876 @default.
- W3126451824 cites W2807539765 @default.
- W3126451824 cites W2884821828 @default.
- W3126451824 cites W2887603965 @default.
- W3126451824 cites W2911510572 @default.
- W3126451824 cites W2912070915 @default.
- W3126451824 cites W2912237282 @default.
- W3126451824 cites W2938867157 @default.
- W3126451824 cites W2942630857 @default.
- W3126451824 cites W2943642558 @default.
- W3126451824 cites W2943657790 @default.
- W3126451824 cites W2945793108 @default.
- W3126451824 cites W2947775933 @default.
- W3126451824 cites W2949103145 @default.
- W3126451824 cites W2950774971 @default.
- W3126451824 cites W2950787360 @default.
- W3126451824 cites W2962700793 @default.
- W3126451824 cites W2962729158 @default.
- W3126451824 cites W2962972504 @default.
- W3126451824 cites W2963026800 @default.
- W3126451824 cites W2963076808 @default.
- W3126451824 cites W2963178695 @default.
- W3126451824 cites W2963207607 @default.
- W3126451824 cites W2963249138 @default.
- W3126451824 cites W2963289726 @default.
- W3126451824 cites W2963501948 @default.
- W3126451824 cites W2963597678 @default.
- W3126451824 cites W2963636205 @default.
- W3126451824 cites W2963744840 @default.
- W3126451824 cites W2963857521 @default.
- W3126451824 cites W2964153729 @default.
- W3126451824 cites W2965198951 @default.
- W3126451824 cites W2970049488 @default.
- W3126451824 cites W2970088379 @default.
- W3126451824 cites W2970316625 @default.
- W3126451824 cites W2970317235 @default.
- W3126451824 cites W2970451906 @default.
- W3126451824 cites W2970680991 @default.
- W3126451824 cites W2971316968 @default.
- W3126451824 cites W2980728855 @default.
- W3126451824 cites W2987644081 @default.
- W3126451824 cites W2989929945 @default.
- W3126451824 cites W2995245581 @default.
- W3126451824 cites W2995645057 @default.
- W3126451824 cites W2996180708 @default.
- W3126451824 cites W2996344901 @default.
- W3126451824 cites W2997618889 @default.
- W3126451824 cites W2998835636 @default.
- W3126451824 cites W3003221871 @default.
- W3126451824 cites W3004298045 @default.
- W3126451824 cites W3005576178 @default.
- W3126451824 cites W3006335454 @default.
- W3126451824 cites W3006834354 @default.
- W3126451824 cites W3033210711 @default.
- W3126451824 cites W3034488700 @default.
- W3126451824 cites W3034537217 @default.
- W3126451824 cites W3034842981 @default.
- W3126451824 cites W3037742886 @default.
- W3126451824 cites W3038319179 @default.
- W3126451824 cites W3039230418 @default.
- W3126451824 cites W3049066126 @default.
- W3126451824 cites W3089560030 @default.
- W3126451824 cites W3100451902 @default.
- W3126451824 cites W3104032928 @default.
- W3126451824 cites W3113477609 @default.
- W3126451824 cites W3175863095 @default.
- W3126451824 doi "https://doi.org/10.48550/arxiv.2102.01356" @default.
- W3126451824 hasPublicationYear "2021" @default.
- W3126451824 type Work @default.
- W3126451824 sameAs 3126451824 @default.
- W3126451824 citedByCount "8" @default.
- W3126451824 countsByYear W31264518242021 @default.
- W3126451824 countsByYear W31264518242023 @default.
- W3126451824 crossrefType "posted-content" @default.
- W3126451824 hasAuthorship W3126451824A5024709593 @default.
- W3126451824 hasAuthorship W3126451824A5029733098 @default.
- W3126451824 hasAuthorship W3126451824A5046225712 @default.