Litcius/Paper detail

Gradient-based Analysis of NLP Models is Manipulable

Junlin Wang, Jens Tuyls, Eric Wallace, Sameer Singh

202043 citationsDOIOpen Access PDF

Abstract

Gradient-based analysis methods, such as saliency map visualizations and adversarial input perturbations, have found widespread use in interpreting neural NLP models due to their simplicity, flexibility, and most importantly, their faithfulness. In this paper, however, we demonstrate that the gradients of a model are easily manipulable, and thus bring into question the reliability of gradient-based analyses.

Topics & Concepts

Computer scienceMerge (version control)Artificial intelligenceAdversarial systemSimplicityNatural language processingFlexibility (engineering)Pattern recognition (psychology)Machine learningInformation retrievalMathematicsStatisticsEpistemologyPhilosophyAdversarial Robustness in Machine LearningExplainable Artificial Intelligence (XAI)Topic Modeling
Gradient-based Analysis of NLP Models is Manipulable | Litcius