HiddenLayer has discovered that Google Gemini for Workspace is prone to indirect prompt injection attacks.
The post AI Security Firm Shows How Threat Actors Could Abuse Google Gemini for Workspace appeared first on SecurityWeek.
AI-Generated Malware Found in the Wild
HP has intercepted an email campaign comprising a standard malware payload delivered by an AI-generated dropper.
The post AI-Generated Malware Found in the Wild appeared first on SecurityWeek.
The AI Threat: Deepfake or Deep Fake? Unraveling the True Security Risks
When it comes to adversarial use of AI, the real question is whether the AI threat is a deep fake, or whether the deepfake is the AI threat.
The post The AI Threat: Deepfake or Deep Fake? Unraveling the True Security Risks appeared first on SecurityWeek.
Operant AI Lands $10M Investment to Boost Runtime Protection for Cloud and AI
Operant AI, a startup specializing in runtime protection for cloud applications, APIs, and AI systems, secures new $10 million investment.
The post Operant AI Lands $10M Investment to Boost Runtime Protection for Cloud and AI appeared first on SecurityWeek.
Google’s AI Model Faces European Union Scrutiny From Privacy Watchdog
Ireland’s Data Protection Commission said it has opened an inquiry into Google’s Pathways Language Model 2, also known as PaLM2.
The post Google’s AI Model Faces European Union Scrutiny From Privacy Watchdog appeared first on SecurityWeek.
Epic AI Fails And What We Can Learn From Them
Large language models (LLMs) are trained on vast amounts of data to learn patterns and recognize relationships in language usage. But they can’t discern fact from fiction.
The post Epic AI Fails And What We Can Learn From Them appeared first on SecurityWeek.
The AI Convention: Lofty Goals, Legal Loopholes, and National Security Caveats
Signed on September 5, 2024, the AI Convention is a laudable intent but suffers from the usual exclusions and exemptions necessary to satisfy multiple nations.
The post The AI Convention: Lofty Goals, Legal Loopholes, and National Security Caveats appeared first on SecurityWeek.
The AI Wild West: Unraveling the Security and Privacy Risks of GenAI Apps
GenAI users are uploading data to over eight apps every month – what are the security and privacy concerns?
The post The AI Wild West: Unraveling the Security and Privacy Risks of GenAI Apps appeared first on SecurityWeek.
Acuvity Raises $9 Million Seed Funding for Gen-AI Governance and In-house Development
Activity emerged from stealth with $9 million seed funding to provide solutions for enterprises to safely adopt GenAI.
The post Acuvity Raises $9 Million Seed Funding for Gen-AI Governance and In-house Development appeared first on SecurityWeek.
How Do You Know When AI is Powerful Enough to be Dangerous? Regulators Try to Do the Math
An AI model trained on 10 to the 26th floating-point operations per second must now be reported to the U.S. government and could soon trigger even stricter requirements in California.
The post How Do You Know When AI is Powerful Enough to be Dangerous? Regulators Try to Do the Math appeared first on SecurityWeek.
