 Are Your Explanations Reliable? Investigating the Stability of LIME in
Explaining Text Classifiers by Marrying XAI and Adversarial AttackConference on Empirical Methods in Natural Language Processing (EMNLP), 2023 |
 Perturbing Inputs for Fragile Interpretations in Deep Natural Language
ProcessingBlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackBoxNLP), 2021 |
 An Analysis of LIME for Text DataInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2020 |
 Multi-Dimensional Gender Bias ClassificationConference on Empirical Methods in Natural Language Processing (EMNLP), 2020 |
 Explaining the Explainer: A First Theoretical Analysis of LIMEInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2020 |
 Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation
MethodsAAAI/ACM Conference on AI, Ethics, and Society (AIES), 2019 |
 |
 Interpretation of Neural Networks is FragileAAAI Conference on Artificial Intelligence (AAAI), 2017 |
