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.
More Stories
Moldovan Behind E-Root Marketplace Gets US Federal Prison Term
Sandu Boris Diaconu was involved in conspiracy to commit access device and computer fraud Read More
FCC Agrees to Cyber Trust Mark for IoT Products
The voluntary FCC program will allow smart device manufacturers to demonstrate to consumers that their product has met robust cybersecurity...
Over 50,000 Vulnerabilities Discovered in DoD Systems Through Bug Bounty Program
Seven years into its ethical hacking program, the Pentagon received its 50,000th vulnerability report on March 15 Read More
Three New Critical Vulnerabilities Uncovered in Argo
The flaws, identified by KTrust, enable attackers to bypass rate limits and brute force protection mechanisms Read More
Fujitsu hack raises questions, after firm confirms customer data breach
Fujitsu has warned that cybercriminals may have stolen files with personal and customer data after it discovering malware on its...
Microsoft: 87% of UK Organizations Vulnerable to Costly Cyber-Attacks
A Microsoft report found that 87% of UK organizations are either vulnerable or at high-risk of cyber-attacks, and urged investment...