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 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.
While AI can significantly bolster defense mechanisms, it also equips adversaries with powerful tools to launch sophisticated cyberattacks.
The post The Emerging Landscape of AI-Driven Cybersecurity Threats: A Look Ahead appeared first on SecurityWeek.
Researchers have warned that powerful AI models could be used to supercharge online disinformation, cyberattacks or creation of bioweapons.
The post Europe Reaches a Deal on the World’s First Comprehensive AI Rules appeared first on SecurityWeek.
The Bank of England will make an assessment next year about the risks posed by artificial intelligence and machine learning.
The post Bank of England Will Review the Risks That AI Poses to UK Financial Stability appeared first on SecurityWeek.
Virtual conference on December 6th will explore cybersecurity use-cases for artificial intelligence (AI) technology and the race to protect LLM algorithms from adversarial use.
The post Virtual Event Today: Cyber AI & Automation Summit appeared first on SecurityWeek.
Researchers found that a ‘silly’ attack method could have been used to trick ChatGPT into handing over training data.
The post Simple Attack Allowed Extraction of ChatGPT Training Data appeared first on SecurityWeek.
A critical issue in open source AI framework Ray could provide attackers with operating system access to all nodes.
The post Critical Vulnerability Found in Ray AI Framework appeared first on SecurityWeek.
New guidance from US and UK cybersecurity agencies provides recommendations for secure AI system development.
The post US, UK Cybersecurity Agencies Publish AI Development Guidance appeared first on SecurityWeek.
Interview with Craig Martell, Chief Digital and AI Officer (CDAO) for the U.S. Department of Defense, about AI use in the military.
The post Insider Q&A: Pentagon AI Chief on Network-Centric Warfare, Generative AI Challenges appeared first on SecurityWeek.
