Papers with adversarial methods
Delete, Retrieve, Generate: a Simple Approach to Sentiment and Style Transfer (N18-1)
Copied to clipboard
| Challenge: | Previous work using adversarial methods has struggled to produce high-quality outputs. |
| Approach: | They propose a method that transforms a sentence to alter a specific attribute while preserving its attribute-independent content. |
| Outcome: | The proposed method generates grammatical and appropriate responses on 22% more inputs than the best previous system, averaged over three attribute transfer datasets. |
ART: Attention-Regularized Transformers for Multi-Modal Robustness (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing approaches to enhancing robustness are domain-specific or lack formal guarantees. |
| Approach: | They propose a framework that enhances robustness across modalities by regularizing attention maps under adversarial perturbations. |
| Outcome: | The proposed framework improves robustness across modalities and training on IMDB, QNLI, CIFAR-10, Cifar-100, and Imagenette. |
A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for learning disentangled representations of textual data are difficult to implement and suffer from the degeneracy of other losses in multi-class scenarios. |
| Approach: | They propose a variational upper bound to the mutual information between an attribute and the latent code of an encoder that controls the approximation error. |
| Outcome: | The proposed method is superior on fair classification and on textual style transfer tasks. |
StanceAttack: Adversarial Attack for Stance Detection (2026.findings-acl)
Copied to clipboard
| Challenge: | pretrained language models (PLMs) have greatly enhanced stance detection, but they remain vulnerable to adversarial attacks. |
| Approach: | They propose an adversarial attack method that uses ChatGPT to create adversarials that can mislead well-trained stance detection models. |
| Outcome: | The proposed method outperforms existing adversarial methods with higher success rates and fewer retries on two benchmark datasets. |