Google publishes AI agent privacy and security report
Google has published a report on privacy and security challenges faced by autonomous AI agents. The workshop, held in New York in late 2025, brought together over 50 experts to map out how agents—AI systems capable of making decisions and accessing user data—pose new risks. The report highlights that existing techniques don't translate well, since agents handle unstructured input, act probabilistically, and may need to delegate tasks.
- Over 50 academics and industry leaders contributed
- Agents face unique risks from dynamic decision-making
- Traditional software security methods aren't enough
- The report urges context-driven privacy approaches
Sources covering this
More in AI
OpenAI trials visual ads in ChatGPT's image generator
OpenAI will start testing visual ads in ChatGPT this month, showing paid product images while users generate AI images.
Reflection launches Beam, a large open AI model with cheaper compute
Reflection, a well-funded US AI startup, released Beam, a massive open-weight AI model it claims rivals China’s best open models in…
OpenAI speeds up GPT-6 Astra and Sol models
OpenAI made its GPT-6 Astra and Sol models about 50% faster, now generating around 50 tokens per second instead of 30.
Professor swaps coding tests for AI-guided interviews
A university professor has replaced traditional coding exams with interviews that test how students use AI tools like Gemini in Google…