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 …

This survey paper provides an overview of the current state of AI attacks and risks for AI
security and privacy as artificial intelligence becomes more prevalent in various applications …

Deep neural networks exhibit vulnerability to word-level adversarial attacks in natural
language processing. Most of these attack methods adopt synonymous substitutions to …

Recent works in relation extraction (RE) have achieved promising benchmark accuracy;
however, our adversarial attack experiments show that these works excessively rely on …

Adversarial attack aims to perturb input sequences and mislead a trained model for false
predictions. To enhance the model robustness, defensing methods are accordingly …

The field of textual adversarial defenses has gained considerable attention in recent years
due to the increasing vulnerability of natural language processing (NLP) models to …

Adversarial attacks insert small, imperceptible perturbations to input samples that cause
large, undesired changes to the output of deep learning models. Despite extensive research …

Recent studies have revealed the vulnerability of pre-trained language models to
adversarial attacks. Existing adversarial defense techniques attempt to reconstruct …

Adversarial attack research in natural language processing (NLP) has made significant
progress in designing powerful attack methods and defence approaches. However, few …

Recent research has found that deep neural networks are vulnerable and easily been
attacked by adversarial samples. Improving the success rate of attacks against adversarial …