LLM Security

May 16, 20251110
Unauthorized Changes Lead xAI’s Grok to Extremist Content
On May 14, 2025, users of xAI’s Grok language model encountered an alarming series ...

May 13, 2025870
Hijacking Crypto: Attackers’ Tactics to Manipulate AI Memories
Introduction Imagine an AI-powered agent autonomously executing smart-contract calls, rebalancing DeFi portfolios, or settling ...

March 29, 20251070
LLMs and Information Fabrication Insights
One of the enduring frustrations in using large language models (LLMs) has been their ...

March 28, 2025710
Gemini Tech: Unleashing the Advent of Algorithmic Prompt Injection Attacks
The landscape of AI security is rapidly evolving as researchers unveil a groundbreaking technique ...