Microsoft has expanded the capabilities of Security Copilot with AI agents tackling data security, phishing, and identity management.
The post Microsoft Adds AI Agents to Security Copilot appeared first on SecurityWeek.
New Jailbreak Technique Uses Fictional World to Manipulate AI
Cato Networks discovers a new LLM jailbreak technique that relies on creating a fictional world to bypass a model’s security controls.
The post New Jailbreak Technique Uses Fictional World to Manipulate AI appeared first on SecurityWeek.
ChatGPT Vulnerability Exploited Against US Government Organizations
A year-old vulnerability in ChatGPT is being exploited against financial entities and US government organizations.
The post ChatGPT Vulnerability Exploited Against US Government Organizations appeared first on SecurityWeek.
Nvidia Riva Vulnerabilities Allow Unauthorized Use of AI Services
Vulnerabilities in Nvidia Riva could allow hackers to abuse speech and translation AI services that are typically expensive.
The post Nvidia Riva Vulnerabilities Allow Unauthorized Use of AI Services appeared first on SecurityWeek.
New AI Security Tool Helps Organizations Set Trust Zones for Gen-AI Models
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.
New CCA Jailbreak Method Works Against Most AI Models
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.
DeepSeek’s Malware-Generation Capabilities Put to Test
Researchers have analyzed the ability of the Chinese gen-AI DeepSeek to create malware such as ransomware and keyloggers.
The post DeepSeek’s Malware-Generation Capabilities Put to Test appeared first on SecurityWeek.
Beware of DeepSeek Hype: It’s a Breeding Ground for Scammers
Exploiting trust in the DeepSeek brand, scammers attempt to harvest personal information or steal user credentials.
The post Beware of DeepSeek Hype: It’s a Breeding Ground for Scammers appeared first on SecurityWeek.
Webinar Today: Protecting Executives and Enterprises from Digital, Narrative and Physical Attacks
How hyper agenda-driven threat actors, cybercriminals, and nation-states integrate digital, narrative, and physical attacks to target organizations through their executives.
The post Webinar Today: Protecting Executives and Enterprises from Digital, Narrative and Physical Attacks appeared first on SecurityWeek.
New AI Protection from Google Cloud Tackles AI Risks, Threats, and Compliance
Google Cloud’s AI Protection helps discover AI inventory, secure AI assets, and manage threats with detect, investigate, and respond capabilities.
The post New AI Protection from Google Cloud Tackles AI Risks, Threats, and Compliance appeared first on SecurityWeek.
