Rui Xu

User-in-a-context: A blueprint for context-aware identification

2016

In human history, the dependency on secret phrases - passwords - known to only a selected few in a group has mostly ensured that only those are authorised to access certain resources or information. However, …

Fault Injection Attack on Salsa20 and ChaCha and a Lightweight Countermeasure

2017

We propose a fault injection attack on Salsa20 and ChaCha stream ciphers. In these stream ciphers, the initial matrix X, which consists of constants, a key, a block counter, and a nonce, is added to …

E-KAR: A Benchmark for Rationalizing Natural Language Analogical Reasoning

2022 · Findings of the Association for Computational Linguistics: ACL 2022

The ability to recognize analogies is fundamental to human cognition. Existing benchmarks to test word analogy do not reveal the underneath process of analogical reasoning of neural models. Holding the belief that models capable of …

Converge to the Truth: Factual Error Correction via Iterative Constrained Editing

2023 · Proceedings of the AAAI Conference on Artificial Intelligence

Given a possibly false claim sentence, how can we automatically correct it with minimal editing? Existing methods either require a large number of pairs of false and corrected claims for supervised training or do not …

Robust Conformal Prediction under Distribution Shift via Physics-Informed Structural Causal Model

2024 · arXiv (Cornell University)

Uncertainty is critical to reliable decision-making with machine learning. Conformal prediction (CP) handles uncertainty by predicting a set on a test input, hoping the set to cover the true label with at least $(1-α)$ confidence. …