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

Penetration testing (PT) is an efficient network testing and vulnerabilitymining tool by simulating a hacker's attack for valuable information applied insome areas. Compared with manual PT, intelligent PT has become a dominatingmainstream due to less time-consuming and lower labor costs. Unfortunately,RL-based PT is still challenged in real exploitation scenarios because theagent's action space is usually high-dimensional discrete, thus leading toalgorithm convergence difficulty. Besides, most PT methods still rely on thedecisions of security experts. Addressing the challenges, for the first time,we introduce expert knowledge to guide the agent to make better decisions inRL-based PT and propose a Generative Adversarial Imitation Learning-basedgeneric intelligent Penetration testing framework, denoted as GAIL-PT, to solvethe problems of higher labor costs due to the involvement of security expertsand high-dimensional discrete action space. Specifically, first, we manuallycollect the state-action pairs to construct an expert knowledge base when thepre-trained RL / DRL model executes successful penetration testings. Second, weinput the expert knowledge and the state-action pairs generated online by thedifferent RL / DRL models into the discriminator of GAIL for training. At last,we apply the output reward of the discriminator to guide the agent to performthe action with a higher penetration success rate to improve PT's performance.Extensive experiments conducted on the real target host and simulated networkscenarios show that GAIL-PT achieves the SOTA penetration performance againstDeepExploit in exploiting actual target Metasploitable2 and Q-learning inoptimizing penetration path, not only in small-scale with or without honey-potnetwork environments but also in the large-scale virtual network environment.

GAIL-PT: A Generic Intelligent Penetration Testing Framework with Generative Adversarial Imitation Learning