Identifying Adversarial Attacks on Text Classifiers. (arXiv:2201.08555v1 [cs.CL])

The landscape of adversarial attacks against text classifiers continues to
grow, with new attacks developed every year and many of them available in
standard toolkits, such as TextAttack and OpenAttack. In response, there is a
growing body of work on robust learning, which reduces vulnerability to these
attacks, though sometimes at a high cost in compute time or accuracy. In this
paper, we take an alternate approach -- we attempt to understand the attacker
by analyzing adversarial text to determine …

arxiv attacks text