Measure the different level of risk inherent to all gen-AI foundational models and use that to fine-tune the operation of in-house AI deployments.
The post New AI Security Tool Helps Organizations Set Trust Zones for Gen-AI Models appeared first on SecurityWeek.
Two Microsoft researchers have devised a new jailbreak method that bypasses the safety mechanisms of most AI systems.
The post New CCA Jailbreak Method Works Against Most AI Models appeared first on SecurityWeek.
AIceberg has launched a solution that helps governments and enterprises with the safe, secure and compliant adoption of AI.
The post AIceberg Gets $10 Million in Seed Funding for AI Security Platform appeared first on SecurityWeek.
In a lawsuit targeting cybercriminals who abuse AI services, Microsoft has named individuals from Iran, the UK, China and Vietnam.
The post Microsoft Names Suspects in Lawsuit Against AI Hackers appeared first on SecurityWeek.
Microsoft has unveiled a new AI-based web content analysis tool, underscoring safety and security to address potential concerns.
The post Microsoft Unveils Copilot Vision AI Tool, but Highlights Security After Recall Debacle appeared first on SecurityWeek.
Few people understand AI, nor how to use nor control it, nor where it is going. Yet politicians wish to regulate it.
The post Can AI be Meaningfully Regulated, or is Regulation a Deceitful Fudge? appeared first on SecurityWeek.
The US and allies blame Russian state-sponsored threat actors for using Meliorator AI software to create a social media bot farm.
The post US Disrupts AI-Powered Russian Bot Farm on X appeared first on SecurityWeek.
Microsoft has tricked several gen-AI models into providing forbidden information using a jailbreak technique named Skeleton Key.
The post Microsoft Details ‘Skeleton Key’ AI Jailbreak Technique appeared first on SecurityWeek.
Mozilla has announced a 0Day Investigative Network (0Din) bug bounty program for LLMs and other deep learning tech.
The post Mozilla Launches 0Din Gen-AI Bug Bounty Program appeared first on SecurityWeek.
Averson secures seed funding to build technology that uses AI to identify cloud security weaknesses and counter cyberattacks.
The post Averlon Emerges From Stealth Mode With $8 Million in Funding appeared first on SecurityWeek.
