Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200025412> ?p ?o ?g. }
- W4200025412 abstract "Model extraction attacks aim to duplicate a machine learning model through query access to a target model. Early studies mainly focus on discriminative models. Despite the success, model extraction attacks against generative models are less well explored. In this paper, we systematically study the feasibility of model extraction attacks against generative adversarial networks (GANs). Specifically, we first define fidelity and accuracy on model extraction attacks against GANs. Then we study model extraction attacks against GANs from the perspective of fidelity extraction and accuracy extraction, according to the adversary’s goals and background knowledge. We further conduct a case study where the adversary can transfer knowledge of the extracted model which steals a state-of-the-art GAN trained with more than 3 million images to new domains to broaden the scope of applications of model extraction attacks. Finally, we propose effective defense techniques to safeguard GANs, considering a trade-off between the utility and security of GAN models." @default.
- W4200025412 created "2021-12-31" @default.
- W4200025412 creator A5012796533 @default.
- W4200025412 creator A5073684178 @default.
- W4200025412 date "2021-12-06" @default.
- W4200025412 modified "2023-09-25" @default.
- W4200025412 title "Stealing Machine Learning Models: Attacks and Countermeasures for Generative Adversarial Networks" @default.
- W4200025412 cites W1834627138 @default.
- W4200025412 cites W1971157729 @default.
- W4200025412 cites W2083610878 @default.
- W4200025412 cites W2117539524 @default.
- W4200025412 cites W2194775991 @default.
- W4200025412 cites W2296452361 @default.
- W4200025412 cites W2339754110 @default.
- W4200025412 cites W2473418344 @default.
- W4200025412 cites W2519536754 @default.
- W4200025412 cites W2535690855 @default.
- W4200025412 cites W2566832195 @default.
- W4200025412 cites W2603766943 @default.
- W4200025412 cites W2603777577 @default.
- W4200025412 cites W2887995258 @default.
- W4200025412 cites W2897830718 @default.
- W4200025412 cites W2911489562 @default.
- W4200025412 cites W2962770929 @default.
- W4200025412 cites W2962974533 @default.
- W4200025412 cites W2963201933 @default.
- W4200025412 cites W2963303354 @default.
- W4200025412 cites W2963378725 @default.
- W4200025412 cites W2963560987 @default.
- W4200025412 cites W2963703197 @default.
- W4200025412 cites W2963844355 @default.
- W4200025412 cites W2963857521 @default.
- W4200025412 cites W2964024144 @default.
- W4200025412 cites W2965527189 @default.
- W4200025412 cites W2969695741 @default.
- W4200025412 cites W2981721547 @default.
- W4200025412 cites W2985060393 @default.
- W4200025412 cites W2989855043 @default.
- W4200025412 cites W2996141621 @default.
- W4200025412 cites W2997146418 @default.
- W4200025412 cites W3011675874 @default.
- W4200025412 cites W3034431451 @default.
- W4200025412 cites W3035574324 @default.
- W4200025412 cites W3071470454 @default.
- W4200025412 cites W3081488247 @default.
- W4200025412 cites W3164111940 @default.
- W4200025412 cites W3164878287 @default.
- W4200025412 doi "https://doi.org/10.1145/3485832.3485838" @default.
- W4200025412 hasPublicationYear "2021" @default.
- W4200025412 type Work @default.
- W4200025412 citedByCount "2" @default.
- W4200025412 countsByYear W42000254122022 @default.
- W4200025412 countsByYear W42000254122023 @default.
- W4200025412 crossrefType "proceedings-article" @default.
- W4200025412 hasAuthorship W4200025412A5012796533 @default.
- W4200025412 hasAuthorship W4200025412A5073684178 @default.
- W4200025412 hasBestOaLocation W42000254121 @default.
- W4200025412 hasConcept C119857082 @default.
- W4200025412 hasConcept C120665830 @default.
- W4200025412 hasConcept C121332964 @default.
- W4200025412 hasConcept C153604712 @default.
- W4200025412 hasConcept C154945302 @default.
- W4200025412 hasConcept C167966045 @default.
- W4200025412 hasConcept C192209626 @default.
- W4200025412 hasConcept C195807954 @default.
- W4200025412 hasConcept C199360897 @default.
- W4200025412 hasConcept C2776459999 @default.
- W4200025412 hasConcept C2778012447 @default.
- W4200025412 hasConcept C37736160 @default.
- W4200025412 hasConcept C38652104 @default.
- W4200025412 hasConcept C39890363 @default.
- W4200025412 hasConcept C41008148 @default.
- W4200025412 hasConcept C41065033 @default.
- W4200025412 hasConcept C76155785 @default.
- W4200025412 hasConcept C97931131 @default.
- W4200025412 hasConceptScore W4200025412C119857082 @default.
- W4200025412 hasConceptScore W4200025412C120665830 @default.
- W4200025412 hasConceptScore W4200025412C121332964 @default.
- W4200025412 hasConceptScore W4200025412C153604712 @default.
- W4200025412 hasConceptScore W4200025412C154945302 @default.
- W4200025412 hasConceptScore W4200025412C167966045 @default.
- W4200025412 hasConceptScore W4200025412C192209626 @default.
- W4200025412 hasConceptScore W4200025412C195807954 @default.
- W4200025412 hasConceptScore W4200025412C199360897 @default.
- W4200025412 hasConceptScore W4200025412C2776459999 @default.
- W4200025412 hasConceptScore W4200025412C2778012447 @default.
- W4200025412 hasConceptScore W4200025412C37736160 @default.
- W4200025412 hasConceptScore W4200025412C38652104 @default.
- W4200025412 hasConceptScore W4200025412C39890363 @default.
- W4200025412 hasConceptScore W4200025412C41008148 @default.
- W4200025412 hasConceptScore W4200025412C41065033 @default.
- W4200025412 hasConceptScore W4200025412C76155785 @default.
- W4200025412 hasConceptScore W4200025412C97931131 @default.
- W4200025412 hasFunder F4320321038 @default.
- W4200025412 hasLocation W42000254121 @default.
- W4200025412 hasLocation W42000254122 @default.
- W4200025412 hasOpenAccess W4200025412 @default.
- W4200025412 hasPrimaryLocation W42000254121 @default.
- W4200025412 hasRelatedWork W1576360539 @default.
- W4200025412 hasRelatedWork W2093104230 @default.