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…
New BIFROSE Linux Malware Variant Using Deceptive VMware Domain for Evasion Cybersecurity researchers have discovered a new Linux variant of a remote access trojan (RAT) called BIFROSE (aka Bifrost) that uses a deceptive domain mimicking VMware. “This latest version of Bifrost aims to bypass security measures and compromise targeted systems,” Read more…
PikaBot Resurfaces with Streamlined Code and Deceptive Tactics The threat actors behind the PikaBot malware have made significant changes to the malware in what has been described as a case of “devolution.” “Although it appears to be in a new development cycle and testing phase, the developers have reduced the Read more…