Embrace The Red embracethered.com

Microsoft Copilot: From Prompt Injection to Exfiltration of Personal Information

embracethered.com·90w

Google AI Studio: LLM-Powered Data Exfiltration Hits Again! Quickly Fixed.

embracethered.com·91w

Protect Your Copilots: Preventing Data Leaks in Copilot Studio

embracethered.com·94w

Google Colab AI: Data Leakage Through Image Rendering Fixed. Some Risks Remain.

embracethered.com·95w

Breaking Instruction Hierarchy in OpenAI's gpt-4o-mini

embracethered.com·95w

Sorry, ChatGPT Is Under Maintenance: Persistent Denial of Service through Prompt Injection and Memory Attacks

embracethered.com·97w

GitHub Copilot Chat: From Prompt Injection to Data Exfiltration

embracethered.com·100w

Automatic Tool Invocation when Browsing with ChatGPT - Threats and Mitigations

embracethered.com·103w

ChatGPT: Hacking Memories with Prompt Injection

embracethered.com·104w

Machine Learning Attack Series: Backdooring Keras Models and How to Detect It

embracethered.com·104w

Pivot to the Clouds: Cookie Theft in 2024

embracethered.com·105w

Bobby Tables but with LLM Apps - Google NotebookLM Data Exfiltration

embracethered.com·109w

HackSpaceCon 2024: Short Trip Report, Slides and Rocket Launch

embracethered.com·109w

Google AI Studio Data Exfiltration via Prompt Injection - Possible Regression and Fix

embracethered.com·110w

The dangers of AI agents unfurling hyperlinks and what to do about it

embracethered.com·111w

ASCII Smuggler - Improvements

embracethered.com·115w

Who Am I? Conditional Prompt Injection Attacks with Microsoft Copilot

embracethered.com·115w

Google Gemini: Planting Instructions For Delayed Automatic Tool Invocation

embracethered.com·116w

ChatGPT: Lack of Isolation between Code Interpreter sessions of GPTs

embracethered.com·118w

Video: ASCII Smuggling and Hidden Prompt Instructions

embracethered.com·118w

Log in to enable infinite scrolling