New AI-Powered Mirai Botnet Unleashes Unstoppable Large-Scale DDoS Attacks
The Mirai botnet is actively exploiting known web vulnerabilities to compromise over 1,200 sites across 780 customer accounts, as researchers have identified over 200...
Microsoft Unveils AI Jailbreak: Execute Malicious Instructions!
Microsoft identified a novel generative AI jailbreak technique named Skeleton Key which bypasses AI models' safety guards by exploiting user prompts to manipulate the...
Ollama AI infrastructure platform Flaw Let Attackers Execute Remote Code
A critical RCE vulnerability (CVE-2024-37032) was found in Ollama, a popular open-source project for running AI models, allowing attackers to take over exposed Ollama...
Critical Vulnerability in AI-as-a-Service provider Let Attackers Access Sensitive Data
A vulnerability in Replicate's AI-as-a-service platform allowed unauthorized access to customer AI models and prompts due to insufficient tenant separation, which could have exposed...
How to Start Threat Hunting: A Beginner’s Guide in 2024
Threat hunting is a proactive approach to cybersecurity that involves actively searching for potential threats or indicators of compromise within an organization's network and...