The Real-World Attacks Behind OWASP Agentic AI Top 10

OWASP's new Agentic AI Top 10 highlights real-world attacks already targeting autonomous AI systems, from goal hijacking to ...
Techlicious

OpenAI Confirms AI-Powered Browsers Leave You Vulnerable to Hackers

So-called prompt injections can trick chatbots into actions like sending emails or making purchases on your behalf. OpenAI ...

Your AI browser can be hijacked by prompt injection, OpenAI just patched Atlas

OpenAI says it has patched ChatGPT Atlas after internal red teaming found new prompt injection attacks that can hijack AI ...
IEEE

Investigating NoSQL Injection Attacks on MongoDB Web Applications

Abstract: Modern web applications are increasingly data-intensive and handle a wide variety of semi-structured and unstructured data. Traditional relational databases were not designed to manage such ...
IEEE

False Data Injection Attacks on Unmanned Aerial Vehicles used for Package Delivery

Abstract: This paper studies GPS and LiDAR spoofing attacks in UAV-based package delivery scenarios. An experimental testbed integrates PX4 autopilot, Gazebo simulator, and ROS to launch attacks on ...

OpenAI says prompt injections that can trick AI browsers like ChatGPT Atlas may never be fully solved—experts say risks are a feature not a bug

“Prompt injection, much like scams and social engineering on the web, is unlikely to ever be fully ‘solved,'” OpenAI wrote in ...