Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384024269> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4384024269 abstract "We study a Stackelberg game between one attacker and one defender in a configurable environment. The defender picks a specific environment configuration. The attacker observes the configuration and attacks via Reinforcement Learning (RL trained against the observed environment). The defender's goal is to find the environment with minimum achievable reward for the attacker. We apply Evolutionary Diversity Optimization (EDO) to generate diverse population of environments for training. Environments with clearly high rewards are killed off and replaced by new offsprings to avoid wasting training time. Diversity not only improves training quality but also fits well with our RL scenario: RL agents tend to improve gradually, so a slightly worse environment earlier on may become better later. We demonstrate the effectiveness of our approach by focusing on a specific application, Active Directory (AD). AD is the default security management system for Windows domain networks. AD environment describes an attack graph, where nodes represent computers/accounts/etc., and edges represent accesses. The attacker aims to find the best attack path to reach the highest-privilege node. The defender can change the graph by removing a limited number of edges (revoke accesses). Our approach generates better defensive plans than the existing approach and scales better." @default.
- W4384024269 created "2023-07-13" @default.
- W4384024269 creator A5019911052 @default.
- W4384024269 creator A5056718700 @default.
- W4384024269 creator A5061189766 @default.
- W4384024269 creator A5084412291 @default.
- W4384024269 creator A5089531887 @default.
- W4384024269 date "2023-07-12" @default.
- W4384024269 modified "2023-10-18" @default.
- W4384024269 title "Evolving Reinforcement Learning Environment to Minimize Learner's Achievable Reward: An Application on Hardening Active Directory Systems" @default.
- W4384024269 cites W2105899518 @default.
- W4384024269 cites W2158934842 @default.
- W4384024269 cites W3094271017 @default.
- W4384024269 cites W4223411023 @default.
- W4384024269 cites W4225631948 @default.
- W4384024269 cites W4294876381 @default.
- W4384024269 cites W4309284213 @default.
- W4384024269 cites W4382239480 @default.
- W4384024269 cites W4383221437 @default.
- W4384024269 doi "https://doi.org/10.1145/3583131.3590436" @default.
- W4384024269 hasPublicationYear "2023" @default.
- W4384024269 type Work @default.
- W4384024269 citedByCount "0" @default.
- W4384024269 crossrefType "proceedings-article" @default.
- W4384024269 hasAuthorship W4384024269A5019911052 @default.
- W4384024269 hasAuthorship W4384024269A5056718700 @default.
- W4384024269 hasAuthorship W4384024269A5061189766 @default.
- W4384024269 hasAuthorship W4384024269A5084412291 @default.
- W4384024269 hasAuthorship W4384024269A5089531887 @default.
- W4384024269 hasBestOaLocation W43840242691 @default.
- W4384024269 hasConcept C120314980 @default.
- W4384024269 hasConcept C144024400 @default.
- W4384024269 hasConcept C144237770 @default.
- W4384024269 hasConcept C149923435 @default.
- W4384024269 hasConcept C154945302 @default.
- W4384024269 hasConcept C199510392 @default.
- W4384024269 hasConcept C2775896111 @default.
- W4384024269 hasConcept C2908647359 @default.
- W4384024269 hasConcept C31258907 @default.
- W4384024269 hasConcept C33923547 @default.
- W4384024269 hasConcept C38652104 @default.
- W4384024269 hasConcept C41008148 @default.
- W4384024269 hasConcept C97541855 @default.
- W4384024269 hasConceptScore W4384024269C120314980 @default.
- W4384024269 hasConceptScore W4384024269C144024400 @default.
- W4384024269 hasConceptScore W4384024269C144237770 @default.
- W4384024269 hasConceptScore W4384024269C149923435 @default.
- W4384024269 hasConceptScore W4384024269C154945302 @default.
- W4384024269 hasConceptScore W4384024269C199510392 @default.
- W4384024269 hasConceptScore W4384024269C2775896111 @default.
- W4384024269 hasConceptScore W4384024269C2908647359 @default.
- W4384024269 hasConceptScore W4384024269C31258907 @default.
- W4384024269 hasConceptScore W4384024269C33923547 @default.
- W4384024269 hasConceptScore W4384024269C38652104 @default.
- W4384024269 hasConceptScore W4384024269C41008148 @default.
- W4384024269 hasConceptScore W4384024269C97541855 @default.
- W4384024269 hasFunder F4320334704 @default.
- W4384024269 hasLocation W43840242691 @default.
- W4384024269 hasLocation W43840242692 @default.
- W4384024269 hasOpenAccess W4384024269 @default.
- W4384024269 hasPrimaryLocation W43840242691 @default.
- W4384024269 hasRelatedWork W2118026548 @default.
- W4384024269 hasRelatedWork W260766989 @default.
- W4384024269 hasRelatedWork W2761465998 @default.
- W4384024269 hasRelatedWork W2782802862 @default.
- W4384024269 hasRelatedWork W2959276766 @default.
- W4384024269 hasRelatedWork W3074294383 @default.
- W4384024269 hasRelatedWork W3139193008 @default.
- W4384024269 hasRelatedWork W4206669594 @default.
- W4384024269 hasRelatedWork W4295941380 @default.
- W4384024269 hasRelatedWork W4307206142 @default.
- W4384024269 isParatext "false" @default.
- W4384024269 isRetracted "false" @default.
- W4384024269 workType "article" @default.