Over the last few years, the adoption of machine learning in a wide range of domains has
been remarkable. Deep learning, in particular, has been extensively used to drive …

Machine learning (ML) provides effective means to learn from spectrum data and solve
complex tasks involved in wireless communications. Supported by recent advances in …

Recent advances in large language models (LLMs) and the intensifying popularity of
ChatGPT-like applications have blurred the boundary of high-quality text generation …

Adversarial attacks for discrete data (such as texts) have been proved significantly more
challenging than continuous data (such as images) since it is difficult to generate adversarial …

As NLP models achieved state-of-the-art performances over benchmarks and gained wide
applications, it has been increasingly important to ensure the safe deployment of these …

Abstract Leave-One-Out (LOO) scores provide estimates of feature importance in neural
networks, for adversarial attacks. In this work, we present context-free word scores as a …

Recent efforts have shown that neural text processing models are vulnerable to adversarial
examples, but the nature of these examples is poorly understood. In this work, we show that …

Very recently, few certified defense methods have been developed to provably guarantee
the robustness of a text classifier to adversarial synonym substitutions. However, all the …

Deep neural networks are vulnerable to adversarial examples-small input perturbations that
result in incorrect predictions. We study this problem for models of source code, where we …

Active learning, which effectively collects informative unlabeled data for annotation, reduces
the demand for labeled data. In this work, we propose to retrieve unlabeled samples with a …