How Google Sees and Defends Against AI-Driven Attacks

The useful part

How Google monitors AI threats and advances AI defenses | Google Cloud Blog Security & Identity Cloud CISO Perspectives: Today, Sandra Joyce shares the latest details on Google's visibility into how attackers are using AI, and how we're using AI to stop them. Joyce, VP, Google Threat Intelligence Anyone operating in security knows that speculation is a major liability during periods of technological disruption.

How it works

• While there is plenty of hype and understandable concern around how threats might use and target AI, a CISO's AI security strategy has to be anchored in ground truth.
• This dual vantage point allows us to understand how AI is built, and exactly how AI is being targeted in the wild.
• When we strip away the noise and look at the telemetry, the real threat landscape boils down to three structural shifts that CISOs must address: AI is reshaping how software is built.
• Across the industry, autonomous agents and AI workflows now push code into production at unprecedented speed.
• No single AI model can discover every vulnerability, and threat actors are already testing inputs that can blind specific LLM safety filters and scanners.

What to take from it

This creates exciting opportunities for innovation, yet CISOs are faced with the difficult task of mitigating enterprise risk while maintaining business momentum. By orchestrating several foundation models — including Gemini, commercial, and open-source — we cross-validate findings, strip out false positives, remediate code, and identify complex logic flaws that a single model misses. Don't treat agent access policies, model inventories (AI-BOMs) and shadow AI as separate challenges because these risks are deeply connected.

Example or evidence

• The solution to a machine-speed threat landscape isn't slowing developers down — it's building security natively into the AI pipeline.
• In Q2 2026, Mandiant investigated multiple data theft extortion operations where threat actors stole proprietary AI data, including models, skills, prompts, source code, and related research.
• The threat actor used an AI coding chatbot, a prompt, and a set of agent instructions to plan, build, and execute a mass credential harvesting campaign in less than six hours.
• Google operates at a rare intersection as both a frontier AI lab and a security company with a frontline view of global incidents.

Details worth keeping

To provide the operational realities that security and business leaders need in the AI era, Google Threat Intelligence Group (GTIG) recently released our latest AI Threat Tracker. Today, we're sharing details on Google's visibility into these three challenges, and our approach for solving them. We're seeing threat actors turn our greatest engineering shortcut against us by contaminating upstream packages that AI assistants are trained to suggest and trust.

Related coverage

• Google: Written by: Alex Tselevich, Michael Maturi Introduction Adversarial misuse of AI has increased the risk of data theft and extortion events, because when proprietary source code is exposed, defenders must...
• Google: AI agents are the ultimate insiders.
• Cm Alliance: Wiz is a leading cloud security platform, but an enterprise may still look for alternatives when cloud workload pricing grows, AppSec remains distributed across separate products or engineering teams...