Back alphasignal.ai

Artex Wins Baidu S Security Challenge Using Linked Graphs To Coordinate Ai

alphasignal.ai • October 22, 2026

Share: View original

ARTEX is an open source autonomous pentest system that won Baidu's agent+ offense/defense challenge.

Go backend with embedded .js frontend, PostgreSQL, and the norma agent SDK.

Dual-graph design separates a global asset graph from per-task exploration graphs, linked by anchors.

Planner keeps a shared todolist across wakeups to run multi-step attack chains in order without race conditions.

Workers can other workers' step-level execution traces to avoid redoing discovery work.

AGPL-3.0 licensed and restricted by the author to local study only, see the repo .

ARTEX is a source-available reference design for autonomous penetration testing agents. Its repository became public after the project won Baidu’s Agent+ Offense and Defense Challenge. The repository advertises AGPL-3.0, although separate use restrictions create a licensing conflict discussed below.

The stack combines a monolithic Go backend, an embedded .js frontend, PostgreSQL, and agent capabilities from the norma SDK. Its main architectural contribution is persistent coordination: multiple agents can pursue a long attack chain, discoveries, preserve dependencies, and produce an inspectable record of their decisions.

Linked graphs keep state legible

ARTEX stores the target inventory and the agents’ reasoning in separate graphs, then joins them through database anchors. This separation gives stable identities to assets and preserves the lineage of each test.

Application code computes asset deduplication keys, removing that choice from model output. Exploration edges such as spawns , derived_from , yields , and proves preserve the path from an initial goal to supporting evidence and confirmed findings.

The exploration_anchors table connects intents, facts, and findings to specific assets. A developer can inspect which assets an exploration path touched or select an asset and retrieve every intent that tested it during the current task. ARTEX also derives coverage from these links across the represented in-scope surface; that metric describes graph coverage, with exhaustive security testing remaining a broader question.

This story is for Pro members

You've reached the end of the free preview. Upgrade to AlphaSignal Pro to read the full article - and everything else behind the paywall.

The full story

This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.

Chinese Hackers Use AI to Breach ConnectWise, Targeting 2,250 Microsoft 365 Tenants A Chinese state-aligned hacking group known as Storm-0940 exploited the ConnectWise Cloud Backup service to compromise over 2,250 Microsoft 365 tenants. Utilizing the ARTEX AI penetration testing framework, the attackers automated their operations, achieving privileged access in under three hours in some cases. The campaign, which began in September 2026, involved rapid sign-in attempts reaching 2,900 per minute, allowing the group to bypass multi-factor authentication by leveraging pre-authorized applications. Microsoft confirmed that the attack targeted various sectors, including defense, finance, and technology. ConnectWise has since disabled affected services and is in the process of restoring them, while advising customers to review their logs for unauthorized access. The incident highlights the growing threat of AI-driven cyberattacks and the vulnerabilities within third-party application integrations. 38 sources 78

Extracted Entities

Artex Wins Baidu S Security Challenge Using Linked Graphs To Coordinate Ai

The full story

Extracted Entities

Campaigns (1)

Platforms (1)

Tools (1)