Google：攻击者正利用提示注入攻击编程 Agent

Google 如何防范 AI 滥用

Google 采用多层次防御策略，保护用户和基础设施免受 AI 滥用影响。该策略整合了主动式模型级安全措施、专业威胁情报、定向遏制协议，以及主动开展的红队测试，以模拟并防范各类威胁。

主动式模型与平台防御

我们持续强化 AI 模型，防止其被滥用，并将活跃威胁监测获得的洞见直接纳入安全分类器和护栏。例如，针对模型提取（即“蒸馏”）攻击，我们已部署实时防御机制，旨在降低未经授权的“学生”模型性能，并检测试图复制专有逻辑的行为。一旦识别出不法行为者，我们会采取直接行动，通过禁用相关项目和账户来扰乱其运营。

例如，2026 年 6 月，Google 打击了“Outsider Enterprise”。这是一个总部位于中国的网络犯罪服务组织，提供可用于大规模冒充 Google 及其他可信品牌的钓鱼工具包。与该网络有关的运营者曾使用 Gemini 生成底层代码，并大规模开展活动。这是 Google 首次针对 Gemini 滥用采取法律行动，为平台提供商如何应对自身 AI 工具被用于欺诈活动树立了先例。

为将这些保护措施扩展至企业客户，我们开发了 Google AI Threat Defense（AITD）。这套自主架构通过整合 Gemini 及其他前沿模型的推理能力、Wiz 的风险优先级排序能力、Gemini 和 CodeMender 的自动化修复能力，以及 Mandiant 提供的一线情报，将安全能力落地实施。AITD 采用多模型策略，在成本与覆盖范围之间取得平衡：使用轻量级模型进行持续扫描，并针对高风险漏洞使用专门的前沿模型。

除主动平台防御外，我们最近还推出了 Gemini 3.8 Flash Cyber。这是我们能力最强的网络安全模型，在漏洞检测和自动化补丁修复方面具备前沿级性能。

安全且负责任地构建 AI

Google 的 AI 方法以大胆创新和负责任开发为指导原则。在AI 原则的指导下，Google 在设计 AI 系统时部署了强健的安全与保障护栏，并持续对其进行测试，以确保系统韧性。

我们的政策指南和禁止使用政策是保障安全的基础。我们的政策制定流程旨在预见新兴趋势，并从底层开始进行安全设计，从而使我们能够增强对全球用户的保护。

在 Google，威胁情报是安全态势的核心组成部分。我们积极调查对平台的滥用行为，包括由政府支持的威胁行为者实施的恶意网络活动，并在适当情况下与执法部门合作。关键在于，我们从实施的每一项应对措施中获得的经验，都会反馈到产品开发中，以提升 AI 模型的安全性。持续迭代分类器和模型级护栏，对于在不断演变的威胁面前保持敏捷至关重要。

我们的 AI 开发团队和信任与安全团队，也持续与威胁情报、安全及建模专家紧密协作，以有效遏制滥用行为。

关于作者

Google 威胁情报团队专注于识别、分析、缓解和消除针对 Alphabet、我们的用户及客户的各类网络威胁。我们的工作包括应对政府支持行为者带来的威胁、定向零日漏洞利用、协同信息行动（IO）以及严重网络犯罪网络。我们将情报应用于提升 Google 的防御能力，并保护用户和客户。

How Google Protects Against AI Abuse

Google uses a multifaceted defense strategy to protect our users and infrastructure against AI abuse, integrating proactive model-level safeguards, specialized threat intelligence, targeted containment protocols, and proactive red teaming to simulate and protect against threats.

Proactive Model and Platform Defenses

We continuously harden our AI models against misuse by feeding insights from active threat monitoring directly into our safety classifiers and guardrails. For instance, in response to model extraction—or “distillation”—attacks, we have deployed real-time defenses designed to degrade the performance of unauthorized "student" models and detect attempts to clone proprietary logic. When we identify bad actors, we take direct action to disrupt their operations by disabling associated projects and accounts. For example, in June 2026, Google disrupted "Outsider Enterprise", a China-based cyber crime service providing phishing kits that enable mass impersonation of Google and other trusted brands. Operators associated with this network used Gemini to generate underlying code and run campaigns at scale. This marks the first time Google has pursued legal action over Gemini misuse, establishing a precedent for how platform providers can act against abuse of their own AI tools in fraud operations.

To extend these protections to enterprise customers, we developed Google AI Threat Defense (AITD). This autonomous architecture operationalizes security by bringing together the reasoning power of Gemini and other frontier models, the risk prioritization of Wiz, the automated remediation capabilities of Gemini and CodeMender, and frontline intelligence from Mandiant. AITD employs a multi-model strategy that balances cost and coverage, using light models for continuous scanning and specialized frontier models for high-risk vulnerabilities.

In addition to our proactive platform defenses, we’ve recently introduced Gemini 3.8 Flash Cyber, our most capable cybersecurity model with frontier-level performance in vulnerability detection and automated patching.

Building AI Safely and Responsibly

Google’s approach to AI is guided by a commitment to bold innovation and responsible development. Guided by our AI Principles, Google designs AI systems with robust security and safety guardrails, which are continuously tested to ensure resilience.

Our policy guidelines and prohibited use policies are foundational to ensuring safety. Our policy development process is built to anticipate emerging trends and design for security from the ground up, allowing us to enhance protections for users globally.

At Google, threat intelligence is a core component of our security posture. We actively investigate abuse of our platforms—including malicious cyber activities by government-backed threat actors—and collaborate with law enforcement when appropriate. Crucially, our learnings from every countermeasure we implement is fed back into our product development to improve the security for our AI models. These iterative improvements to our classifiers and model-level safeguards are vital to maintaining agility against evolving threats.

Our AI development and Trust & Safety teams also work in constant concert with our threat intelligence, security, and modelling experts to effectively stem misuse.

About the Authors

Google Threat Intelligence Group focuses on identifying, analyzing, mitigating, and eliminating entire classes of cyber threats against Alphabet, our users, and our customers. Our work includes countering threats from government-backed actors, targeted zero-day exploits, coordinated IO, and serious cyber crime networks. We apply our intelligence to improve Google's defenses and protect our users and customers.