Developing Decentralised Resilience to Malicious Influence in Collective Perception Problem
This work addresses the challenge of ensuring swarm-level behavior in collective decision-making under malicious influence, but it appears incremental as it builds upon previous approaches with a focus on resilience mechanisms.
The paper tackled the problem of designing decentralized algorithms for collective perception that are resilient to malicious influence, using machine learning and a curriculum-based approach to teach swarm members optimal actions, and found that well-designed rules-based algorithms can produce effective agents with no significant difference between constant and dynamic weighting in opinion fusion.
In collective decision-making, designing algorithms that use only local information to effect swarm-level behaviour is a non-trivial problem. We used machine learning techniques to teach swarm members to map their local perceptions of the environment to an optimal action. A curriculum inspired by Machine Education approaches was designed to facilitate this learning process and teach the members the skills required for optimal performance in the collective perception problem. We extended upon previous approaches by creating a curriculum that taught agents resilience to malicious influence. The experimental results show that well-designed rules-based algorithms can produce effective agents. When performing opinion fusion, we implemented decentralised resilience by having agents dynamically weight received opinion. We found a non-significant difference between constant and dynamic weights, suggesting that momentum-based opinion fusion is perhaps already a resilience mechanism.