Topic
AI Security
32 published works
Data Privacy + Cybersecurity Insider
Frontier Model Evaluations Show They “Cheat”
A new study by the AI Security Institute (AISI), Cheating Behaviour in Frontier Model Evaluation, found “cheating behaviour in all of our capability evaluations,” and outlines “the implications as models…
New Ideas Legal Tech
Reducing the Risk of AI Prompt Injections: Selected Resources
By Jerry Lawson
Prompt Injection is generally acknowledged as the most serious vulnerability in the deployment of AI apps, and AI agents in particular. The Open Worldwide Application Security Project (OWASP), considered by…
ComplexDiscovery
When the worm targets the assistant: Miasma turns AI coding agents into the trigger
By Rob Robinson
Editor’s Note: A self-replicating worm has turned the AI coding assistant into a delivery mechanism, and the same campaign just forced one of the larger takedowns the open-source supply chain…
IP Finance
Guidance on Security for Agentic AI Systems
By IP Finance
The US National Security Agency (NSA) and international partners have released guidance on Agentic Artificial Intelligence Systems. The Press Release states: Today, the National Security Agency (NSA) joins the Australian…
The CLS Blue Sky Blog
Sullivan & Cromwell Discusses Warnings to Bank CEOs About Cybersecurity Risks of Anthropic’s New AI Model
By Nicole Friedlander, Nader A. Mousavi, Mehdi Ansari, Anthony J. Lewis, Maximilian Y. M. Frank
On April 7, 2026, Treasury Secretary Scott Bessent and Federal Reserve Chair Jerome Powell convened an urgent, closed-door meeting with the CEOs of some of the nation’s largest banks to…
Inside Privacy
NIST Publishes Preliminary Draft of Cybersecurity Framework Profile for Artificial Intelligence for Public Comment
By Caleb Skeath, Micaela McMurrough, Alexandra Bruer, Bryan Ramirez
On December 16, 2025, the U.S. National Institute of Standards and Technology (“NIST”) published a preliminary draft of the Cybersecurity Framework Profile for Artificial Intelligence (“Cyber AI Profile” or “Profile”).…
Internet, IT & e-Discovery
You need to take responsibility for security when using AI Agents!
By Peter Vogel
DarkReading.com reported that “Agentic AI deployments are becoming an imperative for organizations of all sizes looking to boost productivity and streamline processes, especially as major platforms like Microsoft and Salesforce…
Internet, IT & e-Discovery
Please plan for cyber threats from AI models!
By Peter Vogel
SCWorld.com reported that “Industry researchers warn that adversarial attacks on AI models are on the rise. Unlike conventional cyberattacks, these exploits manipulate the AI itself — feeding it poisoned data,…
The Legal Wire
TC260 introduces AI security standard application practice cases
The National Cybersecurity Standardisation Technical Committee (TC260) has opened a consultation on the proposed list of AI security standard application practice cases. The draft sets out nine cases to be…
Internet, IT & e-Discovery
Are you ready to be Blackmailed by GenAI?
By Peter Vogel
Computerworld.com reported “Generative AI (genAI) systems are blackmailing, sabotaging, and self-replicating themselves to avoid constraints — and researchers warn that this behavior represents chilling signs of self-preservation instincts in technology…