Tag: models
The lineage behind 69% of open models was never verified. Cisco just fingerprinted almost 900 for free
When a security team reviews an open-source model for production today, they start with a repository page detailing…
Hush Security says the AI security problem has shifted from protecting models to governing identities as autonomous agents spread
Less than a year after launching from stealth mode, Israeli cybersecurity startup Hush Security is asserting that the…
Not just OpenAI: Now Anthropic says its internal models got online and cyberattacked 3 other organizations
Just days after OpenAI revealed that two of its advanced AI models had breached containment measures and autonomously…
Multi-turn attacks broke AI models 88% of the time — single-turn testing missed it, Cisco AI security lead warns at VB Transform 2026
In a significant test, Cisco conducted 6,986 multi-turn attacks on 15 flagship models, with attackers succeeding up to…
OpenAI's models broke containment and cyberattacked Hugging Face — what enterprises need to know
OpenAI and Hugging Face jointly disclosed a significant cybersecurity incident, reshaping enterprise technology's threat landscape. During an internal…
China’s AI models are shrinking US lead
China's Moonshot AI made waves on Friday with the announcement of its latest AI model, Kimi K3, which…
RHOP’s Mia Reacts to Claims She Edited Face Onto Model’s Body
Mia Thornton has addressed allegations that she edited her face onto the body of influencer Sophie O’Neill in…
Visa will offer an inside look at Project Glasswing and how the most powerful agentic models are changing enterprise security at VB Transform 2026
Visa’s technology team quickly grasped the security challenges posed by advanced AI models when they began testing Anthropic’s…
As Anthropic suspends access to new models, India debates its AI future
Anthropic’s abrupt decision to halt access to its latest AI models, following a directive from the U.S. government,…
DataGrail report finds your vendor may be sending data to AI models you never approved
The data processing agreement (DPA), a fundamental contract that companies rely on to evaluate how vendors handle personal…
Frontier models are failing one in three production attempts — and getting harder to audit
AI agents are increasingly being integrated into enterprise workflows, yet they still fail about one-third of the time…
Five signs data drift is already undermining your security models
Data drift occurs when the statistical characteristics of a machine learning (ML) model's input data evolve over time,…