Securing the future of AI agents
Google DeepMind presents its AI Control Roadmap, a defense-in-depth system that treats internal agents as potentially misaligned and grants permissions based on verified behaviour.
Research / Sources
Google DeepMind Safety Research
Safety research from Google DeepMind. deepmindsafetyresearch.medium.com
Responsibility & Safety (19)ai (1)ai-assistance (1)ai-training (1)alignment-problem (1)amplified-oversight (1)complementarity (1)google-gemini (1)hybridization (1)jailbreak (1)language-model (1)sycophancy (1)
Focus All
Topic Agents
Date Any time
Investing in multi-agent AI safety research
Announces up to $10M in funding for research on safety risks from emergent collective behaviour in large-scale multi-agent AI systems, which current single-model evaluations do not cover.
Advancing Gemini's security safeguards
DeepMind white paper on defending Gemini 2.5 against indirect prompt injection in agentic tools, using automated red-teaming to probe and harden defenses.