Google has announced the launch of the Secure AI Framework (SAIF), a conceptual framework for securing AI systems. Google, owner of the generative AI chatbot Bard and parent company of AI research lab DeepMind, said a framework across the public and private sectors is essential for making sure that responsible actors safeguard the technology that supports AI advancements so that when AI models are implemented, they’re secure-by-default. Its new framework concept is an important step in that direction, the tech giant claimed.
The SAIF is designed to help mitigate risks specific to AI systems like model theft, poisoning of training data, malicious inputs through prompt injection, and the extraction of confidential information in training data. “As AI capabilities become increasingly integrated into products across the world, adhering to a bold and responsible framework will be even more critical,” Google wrote in a blog.
To read this article in full, please click here
More Stories
Quishing Attacks Jump Tenfold, Attachment Payloads Halve
The figures come from Egress’s latest report, which also suggests secure email gateways lag behind tech advancements Read More
Russia’s Sandworm Upgraded to APT44 by Google’s Mandiant
Mandiant has confirmed that Sandworm is responsible for many cyber-attacks against Ukraine has close ties with a Russian hacktivist group...
New Cyber-Threat MadMxShell Exploits Typosquatting and Google Ads
Zscaler also confirmed MadMxShell uses DLL sideloading and DNS tunneling for C2 communication Read More
Change Healthcare data for sale on dark web as fallout from ransomware attack spirals out of control
February's crippling ransomware attack against Change Healthcare, which saw prescription orders delayed across the United States, continues to have serious...
3.5 million Omni Hotel guest details held to ransom by Daixin Team
The international hotel chain Omni Hotels & Resorts has confirmed that a cyber attack last month saw it shut down...
Police smash LabHost international fraud network, 37 arrested
Police have successfully infiltrated and disrupted the fraud platform "LabHost", used by more than 2,000 criminals to defraud victims worldwide....