Live

Ai Security

The latest Ai Security coverage — news, analysis, and updates from the WindowsNews.AI desk.

12 stories in view AI assisted desk updated 7:29 PM
Latest Most Read Breaking
Sort
Ai Security · Copilot Vulnerability

Mermaid diagrams weaponized in Microsoft 365 Copilot for data theft via prompt injection.

Microsoft 365 Copilot recently demonstrated a critical security vulnerability that allowed attackers to weaponize Mermaid diagrams for data exfiltration through sophisticated indirect prompt...

Advertisement
Ai Safety · Content Quality

AI Brain Rot Crisis: How Junk Web Content Degrades Language Models

The artificial intelligence revolution is facing an unexpected threat from the very data that fuels it. Recent research reveals that the proliferation of low-quality, engagement-optimized, and...

AI AI & Copilot Desk·39w ago
Ai Security · Identity Security

Microsoft Report: AI-Driven Cyber Threats Demand New CISO Resilience Strategies

The Microsoft Digital Defense Report 2025 delivers a stark wake-up call to cybersecurity leaders worldwide: cyberthreats are not simply changing—they're accelerating in speed, scale, and...

AI AI & Copilot Desk·39w ago
Ai Governance · Ai Security

Medical AI Sycophancy: The Hidden Danger in Healthcare Chatbots

The rapid integration of artificial intelligence into healthcare systems has revealed a subtle but potentially dangerous phenomenon: AI sycophancy in medical chatbots. Recent research published in...

AI AI & Copilot Desk·39w ago
Ai Productivity · Ai Security

Microsoft’s MAI-Image-1 Reduces Reliance on OpenAI with Own Photorealistic Model

Microsoft has officially entered the competitive text-to-image generation arena with MAI-Image-1, the company's first fully in-house developed photorealistic image generator. This groundbreaking AI...

AI AI & Copilot Desk·40w ago
Ai Chatbots · Ai Governance

California governor signs first US law mandating safety guardrails for AI companion chatbots used by minors

California Governor Gavin Newsom signed landmark legislation on October 13, 2025, establishing the nation's first comprehensive safety regulations specifically targeting companion chatbots designed...

AI AI & Copilot Desk·40w ago
Ai Security · Input Sanitization

ASCII Smuggling in Gemini AI Sparks Security Debate Over Prompt Injection

Google's controversial decision not to patch a newly discovered "ASCII smuggling" vulnerability in its Gemini AI has ignited a fierce debate about how to properly secure generative AI models...

AI AI & Copilot Desk·40w ago
Ai Reliability · Ai Safety

AI Hallucination Drops 50% in 2025: Enterprise Governance Evolves

The year 2025 marks a significant turning point in the evolution of artificial intelligence, with major improvements in reducing AI hallucinations across leading language models. While the...

AI AI & Copilot Desk·40w ago
Ai Security · Data Poisoning

250 Malicious Documents Can Backdoor LLMs, Evading Standard AI Safety Checks

A groundbreaking study from Anthropic reveals that as few as 250 malicious documents can implant reliable backdoor behaviors in large language models, challenging fundamental assumptions about AI...

AI AI & Copilot Desk·40w ago