Concept Enhancement Engineering: a Lightweight and Efficient Robust Defense against Jailbreak Attacks in Embodied AI

Embodied Intelligence EI systems integrated with large language models LLMs face significant security risks, particularly from jailbreak attacks that manipulate models into generating harmful outputs or executing unsafe physical actions. Traditional defense strategies, such as input filtering and...

Simplify, then Add Lightness – Consolidating the Technology to Better Defend Ourselves

One of the biggest consequences of the rapidly evolving cybersecurity threat landscape is that defenses must constantly build bigger systems to defend themselves. This leads to both more complex systems and often less communication between them. More importantly, it can lead companies to invest i...