Google DeepMind Launches Gemini 3.5 Flash Cyber AI for Automated Vulnerability Discovery and Patching
Google's DeepMind has announced the release of Gemini 3.5 Flash Cyber, a specialized AI model designed to discover, validate, and patch software…
Tag: OpenAI
Bit2Watt Attack: Cloud Tenants Could Destabilize Power Grids Using Legitimate GPU Workloads
A new attack technique called Bit2Watt, detailed by researchers from Zhejiang University in a paper accepted to CHES 2026, demonstrates how a…
FakeGit Campaign Uses 7,600 GitHub Repositories to Spread SmartLoader Malware
Cybersecurity researchers have uncovered a large-scale campaign dubbed FakeGit, which leverages nearly 7,600 malicious GitHub repositories to distribute the SmartLoader malware. The…
GPT-5.2
GPT-5.2 is a large language model by OpenAI. It was tested and found vulnerable to Agent Data Injection (ADI) attacks.
GPT-5-mini
GPT-5-mini is a smaller language model by OpenAI. It was tested and found vulnerable to Agent Data Injection (ADI) attacks.
Agent Data Injection (ADI) Attack: How AI Agents Can Be Tricked Into Misclicking or Running Attacker Commands
A new class of attack called Agent Data Injection (ADI) has been disclosed by researchers from Seoul National University, the University of…
GPT-5.1: Model Vulnerable to Fake Chain-of-Thought Attacks
GPT-5.1 was found to be highly vulnerable to Fake Chain-of-Thought (CoT) attacks, with success rates above 95%, but now below 10% for…
OpenAI’s GPT-Red Automates Prompt Injection Testing to Harden GPT-5.6 Sol
OpenAI has disclosed details of GPT-Red, an internal automated red-teaming model that scales prompt injection vulnerability discovery to fix issues before tools…
GPT-Red: OpenAI’s Automated Red-Teaming Model
GPT-Red is an internal automated red-teaming model that scales prompt injection vulnerability discovery by iteratively sending prompts and monitoring responses to achieve…
Cursor Flaw Enables Code Execution via Malicious Cloned Repositories on Windows
A critical vulnerability in Cursor, an AI-powered code editor, allows arbitrary code execution on Windows when a user opens a cloned repository…