<p>This paper develops a binary optimization model with second-order uncertain dominance (SUD) constraints to address project portfolio selection problems under uncertainty. Unlike traditional stochastic dominance models based on probability theory, the proposed approach is built upon uncertainty theory, allowing decision-makers to evaluate uncertain variables through expert judgment when historical data are insufficient or unreliable. In the model, project returns and costs are treated as uncertain variables, and the SUD constraints are used to represent the risk-averse preferences of decision makers. Deterministic equivalent formulations are derived to enable computational implementation. A real-world case study is conducted to verify the effectiveness of the model and demonstrate that the binary optimization framework can support rational and risk-averse project portfolio decisions in uncertain environments.</p>