Matches in SemOpenAlex for { <https://semopenalex.org/work/W3197018685> ?p ?o ?g. }
- W3197018685 abstract "While significant research advances have been made in the field of deep reinforcement learning, a major challenge to widespread industrial adoption of deep reinforcement learning that has recently surfaced but little explored is the potential vulnerability to privacy breaches. In particular, there have been no concrete adversarial attack strategies in literature tailored for studying the vulnerability of deep reinforcement learning algorithms to membership inference attacks. To address this gap, we propose an adversarial attack framework tailored for testing the vulnerability of deep reinforcement learning algorithms to membership inference attacks. More specifically, we design a series of experiments to investigate the impact of temporal correlation, which naturally exists in reinforcement learning training data, on the probability of information leakage. Furthermore, we study the differences in the performance of emph{collective} and emph{individual} membership attacks against deep reinforcement learning algorithms. Experimental results show that the proposed adversarial attack framework is surprisingly effective at inferring the data used during deep reinforcement training with an accuracy exceeding $84%$ in individual and $97%$ in collective mode on two different control tasks in OpenAI Gym, which raises serious privacy concerns in the deployment of models resulting from deep reinforcement learning. Moreover, we show that the learning state of a reinforcement learning algorithm significantly influences the level of the privacy breach." @default.
- W3197018685 created "2021-09-13" @default.
- W3197018685 creator A5020639820 @default.
- W3197018685 creator A5034161060 @default.
- W3197018685 creator A5065836447 @default.
- W3197018685 creator A5073908576 @default.
- W3197018685 creator A5076661689 @default.
- W3197018685 date "2021-09-08" @default.
- W3197018685 modified "2023-09-27" @default.
- W3197018685 title "Where Did You Learn That From? Surprising Effectiveness of Membership Inference Attacks Against Temporally Correlated Data in Deep Reinforcement Learning." @default.
- W3197018685 cites W1569296262 @default.
- W3197018685 cites W1686810756 @default.
- W3197018685 cites W1903029394 @default.
- W3197018685 cites W2073384958 @default.
- W3197018685 cites W2109553965 @default.
- W3197018685 cites W2121863487 @default.
- W3197018685 cites W2141559645 @default.
- W3197018685 cites W2145339207 @default.
- W3197018685 cites W2170505850 @default.
- W3197018685 cites W2173248099 @default.
- W3197018685 cites W2194775991 @default.
- W3197018685 cites W2520881573 @default.
- W3197018685 cites W2535690855 @default.
- W3197018685 cites W2593493160 @default.
- W3197018685 cites W2766447205 @default.
- W3197018685 cites W2772721022 @default.
- W3197018685 cites W2792764867 @default.
- W3197018685 cites W2795435272 @default.
- W3197018685 cites W2884367402 @default.
- W3197018685 cites W2887995258 @default.
- W3197018685 cites W2921693358 @default.
- W3197018685 cites W2940572873 @default.
- W3197018685 cites W2952604841 @default.
- W3197018685 cites W2963079702 @default.
- W3197018685 cites W2963120839 @default.
- W3197018685 cites W2963378725 @default.
- W3197018685 cites W2963446712 @default.
- W3197018685 cites W2963704132 @default.
- W3197018685 cites W2963923407 @default.
- W3197018685 cites W2964151798 @default.
- W3197018685 cites W2965527189 @default.
- W3197018685 cites W3017747210 @default.
- W3197018685 cites W3034971196 @default.
- W3197018685 cites W3043638540 @default.
- W3197018685 cites W3096692244 @default.
- W3197018685 cites W3106051020 @default.
- W3197018685 cites W3113688645 @default.
- W3197018685 cites W3123212791 @default.
- W3197018685 cites W3126232929 @default.
- W3197018685 cites W3132455321 @default.
- W3197018685 cites W3138815606 @default.
- W3197018685 cites W3164762628 @default.
- W3197018685 hasPublicationYear "2021" @default.
- W3197018685 type Work @default.
- W3197018685 sameAs 3197018685 @default.
- W3197018685 citedByCount "1" @default.
- W3197018685 countsByYear W31970186852021 @default.
- W3197018685 crossrefType "posted-content" @default.
- W3197018685 hasAuthorship W3197018685A5020639820 @default.
- W3197018685 hasAuthorship W3197018685A5034161060 @default.
- W3197018685 hasAuthorship W3197018685A5065836447 @default.
- W3197018685 hasAuthorship W3197018685A5073908576 @default.
- W3197018685 hasAuthorship W3197018685A5076661689 @default.
- W3197018685 hasConcept C108583219 @default.
- W3197018685 hasConcept C119857082 @default.
- W3197018685 hasConcept C154945302 @default.
- W3197018685 hasConcept C15744967 @default.
- W3197018685 hasConcept C2776214188 @default.
- W3197018685 hasConcept C37736160 @default.
- W3197018685 hasConcept C38652104 @default.
- W3197018685 hasConcept C41008148 @default.
- W3197018685 hasConcept C67203356 @default.
- W3197018685 hasConcept C77805123 @default.
- W3197018685 hasConcept C95713431 @default.
- W3197018685 hasConcept C97541855 @default.
- W3197018685 hasConceptScore W3197018685C108583219 @default.
- W3197018685 hasConceptScore W3197018685C119857082 @default.
- W3197018685 hasConceptScore W3197018685C154945302 @default.
- W3197018685 hasConceptScore W3197018685C15744967 @default.
- W3197018685 hasConceptScore W3197018685C2776214188 @default.
- W3197018685 hasConceptScore W3197018685C37736160 @default.
- W3197018685 hasConceptScore W3197018685C38652104 @default.
- W3197018685 hasConceptScore W3197018685C41008148 @default.
- W3197018685 hasConceptScore W3197018685C67203356 @default.
- W3197018685 hasConceptScore W3197018685C77805123 @default.
- W3197018685 hasConceptScore W3197018685C95713431 @default.
- W3197018685 hasConceptScore W3197018685C97541855 @default.
- W3197018685 hasLocation W31970186851 @default.
- W3197018685 hasOpenAccess W3197018685 @default.
- W3197018685 hasPrimaryLocation W31970186851 @default.
- W3197018685 hasRelatedWork W2019357403 @default.
- W3197018685 hasRelatedWork W2795435272 @default.
- W3197018685 hasRelatedWork W2883567023 @default.
- W3197018685 hasRelatedWork W2897178640 @default.
- W3197018685 hasRelatedWork W2952391091 @default.
- W3197018685 hasRelatedWork W2963557365 @default.
- W3197018685 hasRelatedWork W2964464273 @default.
- W3197018685 hasRelatedWork W2971919016 @default.
- W3197018685 hasRelatedWork W2984869362 @default.
- W3197018685 hasRelatedWork W2990162188 @default.