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

We study automated intrusion response and formulate the interaction betweenan attacker and a defender as an optimal stopping game where attack and defensestrategies evolve through reinforcement learning and self-play. Thegame-theoretic modeling enables us to find defender strategies that areeffective against a dynamic attacker, i.e. an attacker that adapts its strategyin response to the defender strategy. Further, the optimal stopping formulationallows us to prove that optimal strategies have threshold properties. To obtainnear-optimal defender strategies, we develop Threshold Fictitious Self-Play(T-FP), a fictitious self-play algorithm that learns Nash equilibria throughstochastic approximation. We show that T-FP outperforms a state-of-the-artalgorithm for our use case. The experimental part of this investigationincludes two systems: a simulation system where defender strategies areincrementally learned and an emulation system where statistics are collectedthat drive simulation runs and where learned strategies are evaluated. We arguethat this approach can produce effective defender strategies for a practical ITinfrastructure.

Learning Near-Optimal Intrusion Responses Against Dynamic Attackers