Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework

Frontier AI systems are rapidly advancing in their capabilities to persuade, deceive, and influence human behaviour, with current models already demonstrating human-level persuasion and strategic deception in specific contexts. Humans are often the weakest link in cybersecurity systems, and a...

Cyber Essentials and the New Normal

TL;DR Cyber Essentials has changed and aspects of the new normal are catching many by surprise. Increased levels of evidence and stricter controls determining a pass or a fail are in place. Be prepared for the increased hurdles Ask for assistance before starting the process if you are uncertain o...