Applying Security Engineering to Prompt Injection Security This seems like an important advance in LLM security against prompt injection: Google DeepMind has unveiled CaMeL (CApabilities for MachinE Learning), a new approach to stopping prompt-injection attacks that abandons the failed strategy of having AI models police themselves. Instead, CaMeL treats language models as fundamentally untrusted components … Read more
Paris, France, Mar. 24, 2025, CyberNewswire — Arsen, a leading cybersecurity company specializing in social engineering defense, today announced the full release of Conversational Phishing, a groundbreaking feature embedded in its phishing simulation platform. This AI-powered tool introduces dynamic, adaptive phishing conversations to train employees against evolving threats more effectively than ever before. Advanced phishing … Read more
Social engineering is advancing fast, at the speed of generative AI. This is offering bad actors multiple new tools and techniques for researching, scoping, and exploiting organizations. In a recent communication, the FBI pointed out: ‘As technology continues to evolve, so do cybercriminals’ tactics.’ This article explores some of the impacts of this GenAI-fueled acceleration. … Read more
In the wake of cyber attacks targeting casino giants MGM and Caesars, social engineering remains one of the most effective techniques cyber criminals employ. In these incidents, threat actors used a phone-based impersonation tactic, known as vishing, to manipulate an outsourced IT help desk into providing critical access, which paved the way for ransomware attacks … Read more
Dec 09, 2024Ravie LakshmananThreat Intelligence / Malware The threat actors linked to the Black Basta ransomware have been observed switching up their social engineering tactics, distributing a different set of payloads such as Zbot and DarkGate since early October 2024. “Users within the target environment will be email bombed by the threat actor, which is … Read more