Prompt Injection

Research 10.24.2024
October 24, 2024
Introduction Recently, Anthropic released an exciting new application of generative AI called Claude Computer Use as a public...
Research
Research 10.17.2024
October 17, 2024
Overview The HiddenLayer SAI team has discovered a method to manipulate digital watermarks generated by Amazon Web Services...
Research
Research 09.25.2024
September 25, 2024
Executive Summary This blog explores the vulnerabilities of Google’s Gemini for Workspace, a versatile AI assistant integrated...
Research
Research 06.25.2024
June 25, 2024
Executive Summary Many LLMs and LLM-powered apps deployed today use some form of prompt filter or alignment to protect their...
Research
Research 03.27.2024
March 27, 2024
Summary Generative AI has become immensely popular in the last few years, with large language models (LLMs) being integrated...
Research
Research 03.12.2024
March 12, 2024
Google Gemini Content and Usage Security Risks Discovered: LLM Prompt Leakage, Jailbreaks, & Indirect Injections. POC...
Research
Research 02.21.2024
February 21, 2024
Summary In this blog, we show how an attacker could compromise the Hugging Face Safetensors conversion space and its associated...
Research
Research 03.23.2023
March 23, 2023
Introduction Just like how the Internet dramatically changed the way we access information and connect with each other, AI...
Research