Researchers Reveal ‘Deceptive Delight’ Method to Jailbreak AI Models Oct 23, 2024Ravie LakshmananArtificial Intelligence / Vulnerability Cybersecurity researchers have shed light on a new adversarial technique that could be used to jailbreak large language models (LLMs) during the course of an interactive conversation by sneaking in an undesirable instruction between Read more…
Lynx ransomware analyses reveal similarities to INC Ransom Lynx ransomware, a newer ransomware-as-a-service (RaaS) that emerged around July may have stemmed from the INC Ransom source code that was reportedly sold in May, according to multiple analyses of the Lynx strain. The Lynx gang maintains both clear web and dark Read more…
Experts Reveal New Details on Zero-Click Outlook RCE Exploits Dec 18, 2023NewsroomEmail Security / Vulnerability Technical details have emerged about two now-patched security flaws in Microsoft Windows that could be chained by threat actors to achieve remote code execution on the Outlook email service sans any user interaction. “An attacker Read more…