Rishane Dassanayake

Rishane Dassanayake is a joint first author of Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework. The paper records equal first-author contributions, randomized author order and a Meridian Impact affiliation for this work.^[1]

The coauthored framework connects manipulation threats to Safety Case evidence and evaluation limitations such as Sandbagging. This stub records documented contributions rather than assigning sole credit or inferring a current role.