Meta Llama: Everything you need to know about the open generative AI model

Meta's Llama models are open generative AI models designed to run on a range of hardware and perform a range of different ...
NDTV Profit on MSN

'Shadow Escape': New Agentic Attack That Can Exploit ChatGPT, Claude, Gemini, Other AI Agents

Popular AI agents and assistants, including ChatGPT, Claude, and Gemini, can be exploited by a powerful zero-click attack, ...

Data Poison in LLMs: A Fixed Number of Poisoned Documents Suffices for an Attack

A new study refutes an old security assumption. It's not the percentage, but a small, fixed number of poisoned data that ...
Techzine Europe

Small amount of poisoned data can influence AI models

Researchers from Anthropic, the UK AI Security Institute, and the Alan Turing Institute discovered that LLMs can be made ...