3 papers
cs.CL2023
IntenDD: A Unified Contrastive Learning Approach for Intent Detection and Discovery
Bhavuk Singhal, Ashim Gupta, Shivasankaran V P +1
Identifying intents from dialogue utterances forms an integral component of task-oriented dialogue systems. Intent-related tasks are typically formulated either as a classification…
cs.CL2023
Adversarial Clean Label Backdoor Attacks and Defenses on Text Classification Systems
Ashim Gupta, Amrith Krishna
Clean-label (CL) attack is a form of data poisoning attack where an adversary modifies only the textual input of the training data, without requiring access to the labeling functio…
cs.CL2023
Don't Retrain, Just Rewrite: Countering Adversarial Perturbations by Rewriting Text
Ashim Gupta, Carter Wood Blum, Temma Choji +4
Can language models transform inputs to protect text classifiers against adversarial attacks? In this work, we present ATINTER, a model that intercepts and learns to rewrite advers…