Google Gemini for Education brings free AI tools to every classroom. Learn about LearnLM, Gems, Classroom integration, ...

As LLMs and diffusion models power more applications, their safety alignment becomes critical. Our research shows that even minimal downstream fine‑tuning can weaken safeguards, raising a key question ...

That helpful “Summarize with AI” button? It might be secretly manipulating what your AI recommends. Microsoft security researchers have discovered a growing trend of AI memory poisoning attacks used ...

Mastercard's Decision Intelligence Pro uses recurrent neural networks to analyze 160 billion yearly transactions in under 50 ...

The GRP‑Obliteration technique reveals that even mild prompts can reshape internal safety mechanisms, raising oversight ...

The Central Bank Governor’s recent remarks projecting 4–5 percent growth in 2026 and highlighting improving reserves, lower ...

The International Security and Arms Control (CISAC) is a permanent committee to bring the resources of the Academy to bear on ...

Explores LPCI, a new security vulnerability in agentic AI, its lifecycle, attack methods, and proposed defenses.

In today’s rapidly evolving digital world, where Artificial Intelligence (AI) and deepfakes have blurred the lines bet ...

Chaos-inciting fake news right this way A single, unlabeled training prompt can break LLMs' safety behavior, according to Microsoft Azure CTO Mark Russinovich and colleagues. They published a research ...

The global spread of health misinformation is endangering public health, from false information about vaccinations to the peddling of unproven and potentially dangerous cancer treatments.1,2 The ...