Microsoft releases PyRIT red teaming tool to help identify risks in generative AI through automation.
The post Microsoft Releases Red Teaming Tool for Generative AI appeared first on SecurityWeek.
New Google Initiative to Foster AI in Cybersecurity
Google’s new AI Cyber Defense Initiative focuses on boosting cybersecurity through artificial intelligence.
The post New Google Initiative to Foster AI in Cybersecurity appeared first on SecurityWeek.
Tech Companies Sign Accord to Combat AI-Generated Election Trickery
Executives from Adobe, Amazon, Google, IBM, Meta, Microsoft, OpenAI and TikTok gathered at the Munich Security Conference to announce a framework for how they respond to AI-generated deepfakes that deliberately trick voters.
The post Tech Companies Sign Accord to Combat AI-Generated Election Trickery appeared first on SecurityWeek.
Meta Says It Will Label AI-Generated Images on Facebook and Instagram
Facebook and Instagram users will start seeing labels on AI-generated images that appear on their social media feeds, as the tech industry aims to sort between what’s real and not.
The post Meta Says It Will Label AI-Generated Images on Facebook and Instagram appeared first on SecurityWeek.
Google Open Sources AI-Aided Fuzzing Framework
Google has released its fuzzing framework in open source to boost the ability of developers and researchers to identify vulnerabilities.
The post Google Open Sources AI-Aided Fuzzing Framework appeared first on SecurityWeek.
Reken Emerges From Stealth With $10 Million Seed Funding
Reken, an AI-defense cybersecurity startup, emerged from stealth – but without a publicly demonstrable product.
The post Reken Emerges From Stealth With $10 Million Seed Funding appeared first on SecurityWeek.
AI Testing Startup RagaAI Emerges From Stealth With $4.7M in Seed Funding
AI testing platform RagaAI raises $4.7 million in seed funding to help identify AI issues and improve security and reliability.
The post AI Testing Startup RagaAI Emerges From Stealth With $4.7M in Seed Funding appeared first on SecurityWeek.
Critical Vulnerabilities Found in Open Source AI/ML Platforms
Security researchers flag multiple severe vulnerabilities in open source AI/ML solutions MLflow, ClearML, Hugging Face.
The post Critical Vulnerabilities Found in Open Source AI/ML Platforms appeared first on SecurityWeek.
AI Data Exposed to ‘LeftoverLocals’ Attack via Vulnerable AMD, Apple, Qualcomm GPUs
Researchers show how a new attack named LeftoverLocals, which impacts GPUs from AMD, Apple and Qualcomm, can be used to obtain AI data.
The post AI Data Exposed to ‘LeftoverLocals’ Attack via Vulnerable AMD, Apple, Qualcomm GPUs appeared first on SecurityWeek.
NIST: No Silver Bullet Against Adversarial Machine Learning Attacks
NIST has published guidance on adversarial machine learning (AML) attacks and mitigations, warning that there is no silver bullet.
The post NIST: No Silver Bullet Against Adversarial Machine Learning Attacks appeared first on SecurityWeek.
