Hello and welcome to my new blog post. Today I am going to discuss a future threat which is invisible. With greater power comes greater…

Converts ASCII Prompts to Unicode Generating “Invisible” Prompts - Unighost_Prompt_Injection.py

Learn about invisible prompt injection, which is a silent threat to secure AI.

Payloads All The Things, a list of useful payloads and bypasses for Web Application Security

Described as GenAIs greatest flaw, indirect prompt injection is a big problem, Mike Pound from University of Nottingham explains how it is like SQL Injection...

Large language model applications suffer from a few core novel issues that have been identified over the last two years. Let's see how Grok fares on those.

The controversy around DeepSeek's costs for training their R1 model shook up the markets, but it seems like there was a lot of deception.

Hey ChatGPT! How to build a botnet with compromised ChatGPT instances! AI botnet vulnerability

Anthropic created an AI jailbreaking algorithm that keeps tweaking prompts until it gets a harmful response.

Learn about visual prompt injections, their appearance, and top defense strategies against these attacks.

Emails, documents, and other untrusted content can plant malicious memories.

Automatically unfurling hyperlinks can lead to data exfiltration. This post shows how to mitigate this threat in Slack Apps

Andrej Karpathy explains something that's been confusing me for the best part of a year: The decision by LLM tokenizers to parse special tokens in the input string (``, …

Researchers at MIT have released the AI Risk Repository, a comprehensive database that can help organizations identify and mitigate AI risks.

New research analyzes the misuse of multimodal generative AI today, in order to help build safer and more responsible technologies

There are some fascinating new details in this lengthy report outlining the safety work carried out prior to the release of GPT-4o. A few highlights that stood out to me. …

Analyzing untrusted code with GitHub Copilot Chat can have malicious side effects and turn Copilot into Copirate!

By far the most detailed paper on prompt injection I've seen yet from OpenAI, published a few days ago and with six credited authors: Eric Wallace, Kai Xiao, Reimar Leike, …

While some other LLMs appear to flat-out suck

Good news. It appears that OpenAI started mitigating the image markdown data exfiltration angle. It remains vulnerable, but it's great to see a few first actions being taken to mitigate the problem.

Simply look out for libraries imagined by ML and make them real, with actual malicious code. No wait, don't do that

😼 The AI-native, open source alternative to Tines / Splunk SOAR. - TracecatHQ/tracecat

LLMs are trained to block harmful responses. Old-school images can override those rules.

Conditional Instructions open a powerful way for adversaries to target individual and delay detonation of malicious payloads for when certain conditions are met

Last November Google updated Bard to include the ability to solve math equations and draw charts based on data. It can be used to run small Python programs.

The privacy mess is troubling because the chatbots actively encourage you to share details that are far more personal than in a typical app.

ASCII Smuggling - Crafting Invisible Text and Decoding Hidden Secrets (with LLMs)

Aware uses AI to analyze companies' employee messages across Slack, Microsoft Teams, Zoom and other communications services.