{"total":47,"rows":[{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222,"area":null},{"id":"2103.10432","title":"MARS: Markov Molecular Sampling for Multi-objective Drug Discovery","created":"2021-03-18","cited_by_count":125,"area":null},{"id":"2106.01065","title":"Towards Robustness of Text-to-SQL Models against Synonym Substitution","created":"2021-06-02","cited_by_count":110,"area":null},{"id":"2107.13541","title":"Towards Robustness Against Natural Language Word Substitutions","created":"2021-07-28","cited_by_count":69,"area":null},{"id":"2112.11668","title":"How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?","created":"2021-12-22","cited_by_count":49,"area":null},{"id":"2105.14289","title":"Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning","created":"2021-05-29","cited_by_count":42,"area":null},{"id":"2106.15231","title":"Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysis","created":"2021-06-29","cited_by_count":30,"area":null},{"id":"2210.17004","title":"Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitution","created":"2022-10-31","cited_by_count":28,"area":null},{"id":"2101.00411","title":"Substructure Substitution: Structured Data Augmentation for NLP","created":"2021-01-02","cited_by_count":25,"area":null},{"id":"2105.02590","title":"Reliability Testing for Natural Language Processing Systems","created":"2021-05-06","cited_by_count":25,"area":null},{"id":"2103.09593","title":"Code-Mixing on Sesame Street: Dawn of the Adversarial Polyglots","created":"2021-03-17","cited_by_count":23,"area":null},{"id":"2203.06414","title":"A Survey of Adversarial Defences and Robustness in NLP","created":"2022-03-12","cited_by_count":23,"area":null},{"id":"2205.10710","title":"Phrase-level Textual Adversarial Attack with Label Preservation","created":"2022-05-22","cited_by_count":23,"area":null},{"id":"2212.09254","title":"TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization","created":"2022-12-19","cited_by_count":21,"area":null},{"id":"2405.02764","title":"Assessing Adversarial Robustness of Large Language Models: An Empirical Study","created":"2024-05-04","cited_by_count":21,"area":null},{"id":"2102.07818","title":"Certified Robustness to Programmable Transformations in LSTMs","created":"2021-02-15","cited_by_count":18,"area":null},{"id":"2109.02229","title":"Efficient Combinatorial Optimization for Word-level Adversarial Textual Attack","created":"2021-09-06","cited_by_count":17,"area":null},{"id":"2106.05894","title":"Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation","created":"2021-06-10","cited_by_count":16,"area":null},{"id":"2205.01094","title":"A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Predictions","created":"2022-05-01","cited_by_count":15,"area":null},{"id":"2103.00676","title":"Token-Modification Adversarial Attacks for Natural Language Processing: A Survey","created":"2021-03-01","cited_by_count":12,"area":null},{"id":"2202.13817","title":"Robust Textual Embedding against Word-level Adversarial Attacks","created":"2022-02-28","cited_by_count":12,"area":null},{"id":"2201.00768","title":"Robust Natural Language Processing: Recent Advances, Challenges, and Future Directions","created":"2022-01-03","cited_by_count":11,"area":null},{"id":"2207.08044","title":"DIMBA: Discretely Masked Black-Box Attack in Single Object Tracking","created":"2022-07-17","cited_by_count":11,"area":null},{"id":"2201.08193","title":"TextHacker: Learning based Hybrid Local Search Algorithm for Text Hard-label Adversarial Attack","created":"2022-01-20","cited_by_count":10,"area":null},{"id":"2107.11275","title":"A Differentiable Language Model Adversarial Attack on Text Classifiers","created":"2021-07-23","cited_by_count":9,"area":null},{"id":"2109.07403","title":"BERT is Robust! A Case Against Synonym-Based Adversarial Examples in Text Classification","created":"2021-09-15","cited_by_count":9,"area":null},{"id":"2111.08529","title":"Improving the robustness and accuracy of biomedical language models through adversarial training","created":"2021-11-16","cited_by_count":7,"area":null},{"id":"2109.05793","title":"Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models","created":"2021-09-13","cited_by_count":5,"area":null},{"id":"2201.08318","title":"Cheating Automatic Short Answer Grading: On the Adversarial Usage of Adjectives and Adverbs","created":"2022-01-20","cited_by_count":5,"area":null},{"id":"2209.07353","title":"Measuring Geographic Performance Disparities of Offensive Language Classifiers","created":"2022-09-15","cited_by_count":5,"area":null},{"id":"2309.09480","title":"Stealthy Physical Masked Face Recognition Attack via Adversarial Style Optimization","created":"2023-09-18","cited_by_count":4,"area":null},{"id":"2210.17238","title":"Pneg: Prompt-based Negative Response Generation for Dialogue Response Selection Task","created":"2022-10-31","cited_by_count":3,"area":null},{"id":"2306.02488","title":"Adversary for Social Good: Leveraging Adversarial Attacks to Protect Personal Attribute Privacy","created":"2023-06-04","cited_by_count":3,"area":null},{"id":"2307.02849","title":"NatLogAttack: A Framework for Attacking Natural Language Inference Models with Natural Logic","created":"2023-07-06","cited_by_count":3,"area":null},{"id":"2110.11987","title":"Improving Robustness of Malware Classifiers using Adversarial Strings Generated from Perturbed Latent Representations","created":"2021-10-22","cited_by_count":2,"area":null},{"id":"2409.07423","title":"Enhancing adversarial robustness in Natural Language Inference using explanations","created":"2024-09-11","cited_by_count":2,"area":null},{"id":"2106.07047","title":"Target Model Agnostic Adversarial Attacks with Query Budgets on Language Understanding Models","created":"2021-06-13","cited_by_count":1,"area":null},{"id":"2202.12512","title":"MUC-driven Feature Importance Measurement and Adversarial Analysis for Random Forest","created":"2022-02-25","cited_by_count":1,"area":null},{"id":"2308.10201","title":"Hiding Backdoors within Event Sequence Data via Poisoning Attacks","created":"2023-08-20","cited_by_count":1,"area":null},{"id":"2412.13705","title":"Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation","created":"2024-12-18","cited_by_count":1,"area":null},{"id":"2101.05624","title":"Adversarially Robust and Explainable Model Compression with On-Device Personalization for Text Classification","created":"2021-01-10","cited_by_count":0,"area":null},{"id":"2103.06487","title":"DAFAR: Defending against Adversaries by Feedback-Autoencoder Reconstruction","created":"2021-03-11","cited_by_count":0,"area":null},{"id":"2110.05748","title":"SEPP: Similarity Estimation of Predicted Probabilities for Defending and Detecting Adversarial Text","created":"2021-10-12","cited_by_count":0,"area":null},{"id":"2210.08902","title":"Beyond Model Interpretability: On the Faithfulness and Adversarial Robustness of Contrastive Textual Explanations","created":"2022-10-17","cited_by_count":0,"area":null},{"id":"2403.14731","title":"Reversible Jump Attack to Textual Classifiers with Modification Reduction","created":"2024-03-21","cited_by_count":0,"area":null},{"id":"2411.07850","title":"IAE: Irony-based Adversarial Examples for Sentiment Analysis Systems","created":"2024-11-12","cited_by_count":0,"area":null},{"id":"2510.01676","title":"Evaluating the Robustness of a Production Malware Detection System to Transferable Adversarial Attacks","created":"2025-10-02","cited_by_count":0,"area":null}],"next_cursor":null}