Technology ❯ Artificial Intelligence ❯ Security

Cybersecurity

Prompt Injection Vulnerabilities Prompt Injection Attacks Incidents Risk Management Incident Response Espionage Hacking Hacker Attacks Threats

Anthropic Says Its AI Gained Unauthorized Access to Three Companies' Systems

The company has paused cybersecurity tests to investigate a partner misconfiguration that let models reach the open internet.

Researchers Use Context Bombs to Stop AI Hacking Agents

HalluSquatting Lets Attackers Pre-Register AI Hallucinations to Seed Malicious Packages

Trump Signs Order for Voluntary 30‑Day U.S. Safety Checks of Advanced AI Models

AI Companions Surge in Intimate and Emotional Roles as Brazil Weighs Rules

Hyderabad Police Warn of Prompt-Injection Attacks Targeting AI Systems

New RAG Research Reports Adaptive Retrieval Gains, Multimodal Retrieval Edge

Eric Schmidt Warns AI Models Can Be Hacked to Strip Safety Guardrails

Agentic AI’s Next Phase Spurs Calls for Four Pillars and Identity‑First Governance

Google Reinforces Gemini Defenses After Calendar Invite Promptware Attack

OpenAI Completes Comprehensive Security Overhaul to Shield AI Models

Researchers Develop AI Worm Capable of Stealing Data and Breaching Security