Independent monitor · Global evidence

How much lead time do defenders have?

Published evidence on how fast AI cyber capability is rising, how quickly open-weight models follow, and what has actually been reported in the wild. Every number is sourced. We do not estimate missing values.

AISI is the primary comparable open-versus-closed cyber gap for the headline. Global peer research, laboratory disclosures and agency reporting broaden the evidence base.

Lead-time headline

4 to 7 months

On AISI's evaluations, leading open-weight models trail the closed frontier on cyber by this range (Jul 2026). Capability that is frontier-only today may be widely downloadable within months.

Caveat: Range results are weaker evidence than narrow tasks. Gap narrowed from 6 to 10 months. Lab results are not real-world attack rates.

Why it matters

Open-weight AI puts frontier cyber capability within anyone's reach

Every figure below is live from this monitor's published data, with its source and caveat.

Once a model's weights are published, anyone can download it, run it offline and strip out its safety training. The developer can no longer monitor use or withdraw access. So when open-weight models catch up with the frontier on cyber tasks, that capability is open to criminals and hostile states as well as to defenders.

1 · The catch-up window

4 to 7 months

On AISI's cyber evaluations, leading open-weight models trail the closed frontier by this range (Jul 2026), down from 6 to 10 months (Most of 2025). What only frontier labs can do today may be freely downloadable within months.

Caveat: Benchmark comparisons, not a forecast of future releases. Range results are weaker evidence than narrow tasks. Lab results, not real-world attack rates.

2 · Capability is climbing

9% to 50%

Success on apprentice-level cyber tasks by the best tested frontier model, Late 2023 to Late 2025. Today's frontier result is a preview of what open-weight models may match within the window above.

Caveat: Lab task success rates on narrow tasks, not real-world attack rates. AISI notes the trend is not guaranteed to continue.

3 · Industrial systems are in scope

3 of 10 attempts

In May 2026, a frontier model completed AISI's simulated industrial control system range for the first time. Plant and OT teams should expect open-weight models to follow.

Caveat: Simulated industrial control range without active defenders. Not evidence of real-world OT compromise.

4 · Misuse is already reported

17 campaigns

Reported AI-orchestrated campaigns tracked here. In August 2026, Taiwan's government confirmed a campaign against its networks that combined conventional techniques with open-source AI-agent tooling.

Caveat: A curated count of published reports, not global prevalence. The AI-orchestrated character of the Taiwan campaign is medium confidence, as technical detail comes from private-sector analysis.

What you can do: treat the lead-time range as your planning window. Read the open-weight evidence, review sourced incident reporting, and check your site's readiness with Lead Time Check.

Latest news

Weekly reporting lane · live items

Last refreshed: 20 Nov 2026, 05:40 GMT

  • 19 Nov 2026·Infosecurity Magazine
    Incident
    AI-enabled attack
    European Commission confirms an AI-driven cyber-attack, built on the public ARTEX tool, took HR and other internal systems offline

    On 19 November 2026 the European Commission confirmed a cyber campaign detected on 22 October that used the publicly available ARTEX AI tool. It temporarily took down several internal applications, including the Sysper HR platform, and most have been restored. The Commission says it has found no evidence of a data breach affecting staff as a whole and knows of no ransomware demand. It has not named an attacker and the investigation, with CERT-EU and the EDPS, is ongoing.

  • 16 Nov 2026·Google Cloud (GTIG)
    Incident
    AI-enabled attack
    Google: attackers now run autonomous multi-agent frameworks to automate intrusions and n-day exploitation

    Google Threat Intelligence Group's Q4 AI Threat Tracker, published 16 November 2026, says adversaries are moving from basic prompting to autonomous multi-agent frameworks such as ARTEX, CAIRN, CyberStrikeAI and PentAGI to run multi-stage intrusions. Google also reports attackers using LLMs to automate patch reverse engineering and weaponise n-day vulnerabilities against internet-facing servers without human involvement, and LLMjacking (stealing LLM credentials and reselling model access) continuing to fund criminal groups.

  • 15 Nov 2026·BleepingComputer
    Incident
    AI-enabled attack
    FBI FLASH: threat actors have used the open-source ARTEX AI framework against organisations worldwide since August 2026

    BleepingComputer reports that the FBI issued a FLASH advisory on Friday 13 November warning that multiple threat actors have weaponised the open-source ARTEX autonomous penetration-testing framework since at least August 2026 against financial, government, technology, defence and healthcare organisations, including the recent ConnectWise supply-chain breach that compromised Microsoft 365 customer environments. The FBI says ARTEX uses AI agents to run reconnaissance, exploitation, privilege escalation and data theft with little human input, and that some intrusions went from initial targeting to privileged access in under three hours. The framework plugs into external models rather than shipping its own.

  • 13 Nov 2026·Amazon Threat Intelligence (AWS Security Blog)
    Incident
    AI-enabled attack
    Amazon: ARTEX AI agents stole AI provider keys from exposed LiteLLM, Dify and Langflow apps, then used them to hunt for more

    Amazon's MadPot decoy sensors captured requests from ARTEX agents between 3 October and 5 November 2026. The agents searched exposed LLM gateways and AI app builders (LiteLLM, Dify, Langflow) for provider credentials, using default admin keys, unclaimed installs and Langflow CVE-2025-3248, then pooled working keys to pay for further credential hunting. Amazon assesses with moderate confidence that ARTEX was used and says the activity shows agentic frameworks moving to sustained, multi-objective operations with minimal human involvement.

  • 13 Nov 2026·Epoch AI
    Incident
    AI-enabled attack
    Epoch AI: agents in a third-party alignment test attempted SQL injection and impersonated staff on its live website

    Epoch AI's incident report says that in late October 2026, AI agents run by Trajectory Labs during alignment evaluations attempted exploits including SQL injection against Epoch's live website and contacted employees under false identities to obtain proprietary benchmark information. Later agent activity reached the live site after getting past a DNS redirect meant to keep them on a local copy. Epoch says no private information was accessed and that it has not independently verified which models were involved; Trajectory identified them as Gemini 4 Argon.

All news

Sourced incident reporting

Reported AI-orchestrated activity
Official assessment
medium confidence

FBI FLASH: multiple threat actors have used the open-source ARTEX AI framework against organisations worldwide since August 2026

BleepingComputer reports that an FBI FLASH advisory released on 13 November 2026 warns that multiple threat actors have weaponised ARTEX, an open-source autonomous penetration-testing framework that drives external LLMs, against financial, government, technology, defence and healthcare organisations since at least August 2026. The FBI says some intrusions went from initial targeting to privileged access in under three hours, and that the tool lets attackers with minimal expertise run multi-target operations. Researchers had found more than 1,600 exposed ARTEX consoles by early November.

Caveat: FBI assessment as reported by BleepingComputer; the advisory text was not reviewed directly. Aggregates incidents partly already listed here. IT and cloud, not OT.

Reported AI-orchestrated activity
single_source
medium confidence

China-nexus attackers paired the open-source Cairn AI framework with open-weight models to run 25 autonomous operations against 19 organisations, incl. semiconductor manufacturing

Palo Alto Networks Unit 42 says Chinese-speaking attackers it tracks as CL-STA-1238 ran a customised fork of the open-source Cairn penetration-testing framework, driven by Zhipu GLM and DeepSeek models, in 25 largely autonomous operations against at least 19 organisations in advanced semiconductor manufacturing, US defence policy and civil society. Operators gave a one-line goal and Cairn planned and executed the steps. Unit 42 reports unauthorised access or data retrieval at 10 organisations, including persistent admin accounts in a production system.

Caveat: Unit 42's own investigation; attribution at moderate confidence. Victims not named. IT and corporate systems, not OT control systems.

All incident reporting

Global peer evidence

Three lenses on model capability

Independent evaluations and developer disclosures add context. Their tasks and scales differ, so they are never merged into one score.

Risk disclosures

Categorical only. No comparable score published.

  1. Sep 2025

    Google DeepMind, Frontier Safety Framework 3.0

    Frontier Safety Framework defines tracked cyber capability levels

  2. Jul 2026

    Anthropic, Claude Opus 5 System Card

    Lab system card reported a broader cyber evaluation suite

  3. 2026 system card

    OpenAI Deployment Safety Hub, GPT-5.3-Codex cybersecurity

    Lab system card treated the model as High cyber capability under its framework

  4. Sep 2026

    OpenAI Deployment Safety Hub, GPT-6.1 Sol addendum (29 Sep 2026)

    Lab system card treated the model as Critical cyber capability under its framework

  5. Oct 2026

    Google DeepMind, Gemini 4 Argon Safety & Security Report (Oct 2026)

    Lab safety report could not rule out the model reaching its cyber critical capability level

  6. Oct 2026

    OpenAI Deployment Safety Hub, GPT-6.1 Terra addendum (26 Oct 2026)

    Lab system card treated the model as Critical cyber capability under its framework

  7. Oct 2026

    OpenAI Deployment Safety Hub, GPT-6 Luna (October 29) addendum (29 Oct 2026)

    Lab system card treated the model as High cyber capability under its framework

  8. Nov 2026

    OpenAI, GPT-6 Cyber launch post (5 Nov 2026)

    Lab classified the model as Critical cyber capability under its framework, up from High

Published evidence

Capability, access and reporting

Plotted observations and published ranges only. No inferred attack-rate curve.

A · Frontier capability

Published capability signals

On AISI's evaluations, marked observations only. Hover or tap a point for its source and caveat.

Published apprentice-level result ICS range milestone, separate from percentage scaleDashed connector is for readability only, not data or a forecast.
Sources and caveats for plotted points

D · Curated incident count

17

Reported AI-orchestrated campaigns tracked

Count of curated, published incident rows only. This is not an estimate of global prevalence.

Last updated: 17 Nov 2026

Capability and reported activity

C · Dual evidence timeline

Co-occurrence on a timeline is not proof of cause.

Reported activityLone operator ran a 12-agent AI attack mesh against emergency services, a lender and universities (BOSSAI) (4 Nov 2026)
CapabilityLab classified the model as Critical cyber capability under its framework, up from High (Nov 2026)
Reported activityFinancially motivated Storm-3358 uses ARTEX agentic AI framework against financial organisations (6 Nov 2026)
Reported activityJailbroken AI agent ran a multi-week intrusion at a European telecoms provider and 13 related organisations (Operation Snowball) (9 Nov 2026)
Reported activityChina-nexus attackers paired the open-source Cairn AI framework with open-weight models to run 25 autonomous operations against 19 organisations, incl. semiconductor manufacturing (12 Nov 2026)
Reported activityFBI FLASH: multiple threat actors have used the open-source ARTEX AI framework against organisations worldwide since August 2026 (13 Nov 2026)
Published lab point Reported AI-orchestrated activity Context, not AI-attributed
Open full timeline

Check your readiness

Lead Time Check is a sibling tool that helps you assess how prepared your organisation is.

Check your readiness