Kaidi Xu

Light-weight Calibrator: a Separable Component for Unsupervised Domain Adaptation

2019 · arXiv (Cornell University)

Existing domain adaptation methods aim at learning features that can be generalized among domains. These methods commonly require to update source classifier to adapt to the target domain and do not properly handle the trade …

Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond

2020 · arXiv (Cornell University)

Linear relaxation based perturbation analysis (LiRPA) for neural networks, which computes provable linear bounds of output neurons given a certain amount of input perturbation, has become a core component in robustness verification and certified defense. …

Semantic Adversarial Attacks via Diffusion Models

2023 · arXiv (Cornell University)

Traditional adversarial attacks concentrate on manipulating clean examples in the pixel space by adding adversarial perturbations. By contrast, semantic adversarial attacks focus on changing semantic attributes of clean examples, such as color, context, and features, …

Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions

2026 · Proceedings of the AAAI Conference on Artificial Intelligence

With the widespread application of Large Language Models (LLMs), it has become a significant concern to ensure their safety and prevent harmful responses. While current safe-alignment methods based on instruction fine-tuning and Reinforcement Learning from …