SSCAE -- Semantic, Syntactic, and Context-aware natural language Adversarial Examples generator

arXiv:2403.11833v1 Announce Type: cross
Abstract: Machine learning models are vulnerable to maliciously crafted Adversarial Examples (AEs). Training a machine learning model with AEs improves its robustness and stability against adversarial attacks. It is essential to develop models that produce high-quality AEs. Developing such models has been much slower in natural language processing (NLP) than in areas such as computer vision. This paper introduces a practical and efficient adversarial attack model called SSCAE for \textbf{S}emantic, \textbf{S}yntactic, and \textbf{C}ontext-aware natural language \textbf{AE}s …

adversarial adversarial attacks aes arxiv attacks aware context cs.cl cs.cr cs.lg examples generator high language machine machine learning machine learning models natural natural language quality robustness semantic stability training vulnerable