Wenjie Ruan

6

Papers

13

Total Citations

Papers (6)

Boosting Adversarial Training via Fisher-Rao Norm-based Regularization

FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model

Adversarial Training for Probabilistic Robustness

A Black-Box Evaluation Framework for Semantic Robustness in Bird’s Eye View Detection

Towards Fairness-Aware Adversarial Learning

Position: Building Guardrails for Large Language Models Requires Systematic Design