6 papers · 1 filter
USAD: Uncertainty-aware Statistical Adversarial Detection
Zhijian Zhou, Xunye Tian, Jiacheng Zhang +5
Statistical adversarial detection (SAD) treats detection as a two-sample test. Given a reference set of clean examples (CEs) and a batch of queries, potentially containing an unkno…
CELEUS: Certifiable and Efficient LLM Evaluation via E-Processes
Zhijian Zhou, Zesheng Ye, Zhaorun Chen +2
Can we trust evaluation scores to capture an LLM's true real-world performance? Certifiable evaluation answers this question by providing guarantee for LLM evaluation. In particula…
Semantic Robustness Certification for Vision-Language Models
Peiyu Yang, Paul Montague, Feng Liu +4
Vision-language models (VLMs) are now widely used in downstream tasks. However, real-world applications often expose VLMs to distribution shifts induced by semantic variation (e.g.…
Anchor-based Maximum Discrepancy for Relative Similarity Testing
Zhijian Zhou, Liuhua Peng, Xunye Tian +1
The relative similarity testing aims to determine which of the distributions, P or Q, is closer to an anchor distribution U. Existing kernel-based approaches often test the relativ…
Are Two Datasets Close Enough With Statistical Significance? A Kernel Distributional Closeness Testing Approach
Zhijian Zhou, Liuhua Peng, Xunye Tian +2
Are two distributions close to each other with statistical significance? Distribution closeness testing (DCT) formalizes this question by testing whether the distance between a dis…
A Unified Data Representation Learning for Non-parametric Two-sample Testing
Xunye Tian, Liuhua Peng, Zhijian Zhou +3
Learning effective data representations has been crucial in non-parametric two-sample testing. Common approaches will first split data into training and test sets and then learn da…