English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Adversarial attacks against NLP Deep Learning models are a significantconcern. In particular, adversarial samples exploit the model's sensitivity tosmall input changes. While these changes appear insignificant on the semanticsof the input sample, they result in significant decay in model performance. Inthis paper, we propose Targeted Paraphrasing via RL (TPRL), an approach toautomatically learn a policy to generate challenging samples that most likelyimprove the model's performance. TPRL leverages FLAN T5, a language model, as agenerator and employs a self learned policy using a proximal policy gradient togenerate the adversarial examples automatically. TPRL's reward is based on theconfusion induced in the classifier, preserving the original text meaningthrough a Mutual Implication score. We demonstrate and evaluate TPRL'seffectiveness in discovering natural adversarial attacks and improving modelperformance through extensive experiments on four diverse NLP classificationtasks via Automatic and Human evaluation. TPRL outperforms strong baselines,exhibits generalizability across classifiers and datasets, and combines thestrengths of language modeling and reinforcement learning to generate diverseand influential adversarial examples.

Finding a Needle in the Adversarial Haystack: A Targeted Paraphrasing Approach For Uncovering Edge Cases with Minimal Distribution Distortion