English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep reinforcement learning (DRL) policies are vulnerable to unauthorizedreplication attacks, where an adversary exploits imitation learning toreproduce target policies from observed behavior. In this paper, we proposeConstrained Randomization of Policy (CRoP) as a mitigation technique againstsuch attacks. CRoP induces the execution of sub-optimal actions at random underperformance loss constraints. We present a parametric analysis of CRoP, addressthe optimality of CRoP, and establish theoretical bounds on the adversarialbudget and the expectation of loss. Furthermore, we report the experimentalevaluation of CRoP in Atari environments under adversarial imitation, whichdemonstrate the efficacy and feasibility of our proposed method against policyreplication attacks.

Mitigation of Adversarial Policy Imitation via Constrained Randomization of Policy (CRoP)