{"total":106,"rows":[{"id":"2310.19156","title":"Poisoning Retrieval Corpora by Injecting Adversarial Passages","created":"2023-10-29","cited_by_count":159,"area":null},{"id":"2103.11943","title":"BERT: A Review of Applications in Natural Language Processing and Understanding","created":"2021-03-22","cited_by_count":109,"area":null},{"id":"2305.11391","title":"A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation","created":"2023-05-19","cited_by_count":93,"area":null},{"id":"2108.12237","title":"Evaluating the Robustness of Neural Language Models to Input Perturbations","created":"2021-08-27","cited_by_count":87,"area":null},{"id":"2107.13541","title":"Towards Robustness Against Natural Language Word Substitutions","created":"2021-07-28","cited_by_count":69,"area":null},{"id":"2105.03743","title":"Certified Robustness to Text Adversarial Attacks by Randomized [MASK]","created":"2021-05-08","cited_by_count":57,"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":"2301.12868","title":"On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codex","created":"2023-01-30","cited_by_count":41,"area":null},{"id":"2106.01810","title":"Defending Against Backdoor Attacks in Natural Language Generation","created":"2021-06-03","cited_by_count":33,"area":"safety"},{"id":"2105.14553","title":"Defending Pre-trained Language Models from Adversarial Word Substitutions Without Performance Sacrifice","created":"2021-05-30","cited_by_count":30,"area":null},{"id":"2108.04990","title":"Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing","created":"2021-08-11","cited_by_count":30,"area":null},{"id":"2109.00520","title":"The Role of Explainability in Assuring Safety of Machine Learning in Healthcare","created":"2021-09-01","cited_by_count":26,"area":null},{"id":"2106.08361","title":"Adversarial Attacks on Deep Models for Financial Transaction Records","created":"2021-06-15","cited_by_count":24,"area":null},{"id":"2205.12331","title":"Certified Robustness Against Natural Language Attacks by Causal Intervention","created":"2022-05-24","cited_by_count":24,"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":"2109.04367","title":"Multi-granularity Textual Adversarial Attack with Behavior Cloning","created":"2021-09-09","cited_by_count":21,"area":null},{"id":"2306.15261","title":"A Survey on Out-of-Distribution Evaluation of Neural NLP Models","created":"2023-06-27","cited_by_count":20,"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":"2109.04775","title":"A Strong Baseline for Query Efficient Attacks in a Black Box Setting","created":"2021-09-10","cited_by_count":16,"area":null},{"id":"2112.07605","title":"The King is Naked: on the Notion of Robustness for Natural Language Processing","created":"2021-12-13","cited_by_count":16,"area":null},{"id":"2205.06439","title":"AEON: A Method for Automatic Evaluation of NLP Test Cases","created":"2022-05-13","cited_by_count":15,"area":null},{"id":"2208.13058","title":"Adversarial Robustness for Tabular Data through Cost and Utility Awareness","created":"2022-08-27","cited_by_count":15,"area":null},{"id":"2210.15221","title":"TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack","created":"2022-10-27","cited_by_count":15,"area":null},{"id":"2407.06992","title":"Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspective","created":"2024-07-09","cited_by_count":15,"area":null},{"id":"2402.01096","title":"Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance","created":"2024-02-02","cited_by_count":14,"area":null},{"id":"2101.11310","title":"Adversarial Stylometry in the Wild: Transferable Lexical Substitution Attacks on Author Profiling","created":"2021-01-27","cited_by_count":13,"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":"2203.12709","title":"Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretation","created":"2022-03-23","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":"2210.12813","title":"TAPE: Assessing Few-shot Russian Language Understanding","created":"2022-10-23","cited_by_count":11,"area":null},{"id":"2502.00837","title":"Explainability in Practice: A Survey of Explainable NLP Across Various Domains","created":"2025-02-02","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":"2406.19230","title":"Spiking Convolutional Neural Networks for Text Classification","created":"2024-06-27","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":"2203.04713","title":"Defending Black-box Skeleton-based Human Activity Classifiers","created":"2022-03-09","cited_by_count":9,"area":null},{"id":"2203.07860","title":"Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost","created":"2022-03-15","cited_by_count":9,"area":null},{"id":"2302.02568","title":"Less is More: Understanding Word-level Textual Adversarial Attack via n-gram Frequency Descend","created":"2023-02-06","cited_by_count":9,"area":null},{"id":"2403.11297","title":"A Modified Word Saliency-Based Adversarial Attack on Text Classification Models","created":"2024-03-17","cited_by_count":9,"area":null},{"id":"2103.10133","title":"Evaluating Document Coherence Modelling","created":"2021-03-18","cited_by_count":8,"area":null},{"id":"2106.01538","title":"PDPGD: Primal-Dual Proximal Gradient Descent Adversarial Attack","created":"2021-06-03","cited_by_count":8,"area":null},{"id":"2109.05698","title":"Detecting Textual Adversarial Examples through Randomized Substitution and Vote","created":"2021-09-13","cited_by_count":8,"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":"2204.03592","title":"Testing the limits of natural language models for predicting human language judgments","created":"2022-04-07","cited_by_count":7,"area":null},{"id":"2308.07847","title":"Robustness Over Time: Understanding Adversarial Examples' Effectiveness on Longitudinal Versions of Large Language Models","created":"2023-08-15","cited_by_count":7,"area":"safety"},{"id":"2104.08453","title":"R&R: Metric-guided Adversarial Sentence Generation","created":"2021-04-17","cited_by_count":6,"area":null},{"id":"2106.05261","title":"We Can Always Catch You: Detecting Adversarial Patched Objects WITH or WITHOUT Signature","created":"2021-06-09","cited_by_count":6,"area":null},{"id":"2210.09658","title":"ROSE: Robust Selective Fine-tuning for Pre-trained Language Models","created":"2022-10-18","cited_by_count":6,"area":null},{"id":"2305.17055","title":"Counterfactuals of Counterfactuals: a back-translation-inspired approach to analyse counterfactual editors","created":"2023-05-26","cited_by_count":6,"area":null},{"id":"2305.17440","title":"Modeling Adversarial Attack on Pre-trained Language Models as Sequential Decision Making","created":"2023-05-27","cited_by_count":6,"area":null},{"id":"2308.11284","title":"LEAP: Efficient and Automated Test Method for NLP Software","created":"2023-08-22","cited_by_count":6,"area":null},{"id":"2102.00238","title":"ShufText: A Simple Black Box Approach to Evaluate the Fragility of Text Classification Models","created":"2021-01-30","cited_by_count":5,"area":null},{"id":"2102.07164","title":"Adversarial Attack on Network Embeddings via Supervised Network Poisoning","created":"2021-02-14","cited_by_count":5,"area":null},{"id":"2104.08139","title":"Towards Variable-Length Textual Adversarial Attacks","created":"2021-04-16","cited_by_count":5,"area":null},{"id":"2104.12847","title":"Morph Call: Probing Morphosyntactic Content of Multilingual Transformers","created":"2021-04-26","cited_by_count":5,"area":null},{"id":"2111.01528","title":"Effective and Imperceptible Adversarial Textual Attack via Multi-objectivization","created":"2021-11-02","cited_by_count":5,"area":null},{"id":"2208.10251","title":"Rethinking Textual Adversarial Defense for Pre-trained Language Models","created":"2022-07-21","cited_by_count":5,"area":null},{"id":"2410.23182","title":"ProTransformer: Robustify Transformers via Plug-and-Play Paradigm","created":"2024-10-30","cited_by_count":5,"area":null},{"id":"2104.00312","title":"Normal vs. Adversarial: Salience-based Analysis of Adversarial Samples for Relation Extraction","created":"2021-04-01","cited_by_count":4,"area":null},{"id":"2204.13309","title":"Improving robustness of language models from a geometry-aware perspective","created":"2022-04-28","cited_by_count":4,"area":null},{"id":"2302.00094","title":"The Impacts of Unanswerable Questions on the Robustness of Machine Reading Comprehension Models","created":"2023-01-31","cited_by_count":4,"area":null},{"id":"2305.18503","title":"From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework","created":"2023-05-29","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":"2402.03477","title":"Arabic Synonym BERT-based Adversarial Examples for Text Classification","created":"2024-02-05","cited_by_count":3,"area":null},{"id":"2404.09481","title":"SpamDam: Towards Privacy-Preserving and Adversary-Resistant SMS Spam Detection","created":"2024-04-15","cited_by_count":3,"area":null},{"id":"2407.21073","title":"Enhancing Adversarial Text Attacks on BERT Models with Projected Gradient Descent","created":"2024-07-29","cited_by_count":3,"area":null},{"id":"2101.08675","title":"Adversarial Machine Learning in Text Analysis and Generation","created":"2021-01-14","cited_by_count":2,"area":null},{"id":"2201.03829","title":"Quantifying Robustness to Adversarial Word Substitutions","created":"2022-01-11","cited_by_count":2,"area":null},{"id":"2211.02245","title":"Unintended Memorization and Timing Attacks in Named Entity Recognition Models","created":"2022-11-04","cited_by_count":2,"area":"safety"},{"id":"2212.05327","title":"Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classification","created":"2022-12-10","cited_by_count":2,"area":null},{"id":"2302.10479","title":"Tell Model Where to Attend: Improving Interpretability of Aspect-Based Sentiment Classification via Small Explanation Annotations","created":"2023-02-21","cited_by_count":2,"area":null},{"id":"2305.18933","title":"A Multilingual Evaluation of NER Robustness to Adversarial Inputs","created":"2023-05-30","cited_by_count":2,"area":null},{"id":"2307.12520","title":"Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation","created":"2023-07-24","cited_by_count":2,"area":null},{"id":"2208.08029","title":"A Context-Aware Approach for Textual Adversarial Attack through Probability Difference Guided Beam Search","created":"2022-08-17","cited_by_count":1,"area":null},{"id":"2305.10766","title":"Adversarial Amendment is the Only Force Capable of Transforming an Enemy into a Friend","created":"2023-05-18","cited_by_count":1,"area":null},{"id":"2306.15826","title":"MAT: Mixed-Strategy Game of Adversarial Training in Fine-tuning","created":"2023-06-27","cited_by_count":1,"area":null},{"id":"2402.09874","title":"Camouflage is all you need: Evaluating and Enhancing Language Model Robustness Against Camouflage Adversarial Attacks","created":"2024-02-15","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":"2104.09978","title":"Robustness Tests of NLP Machine Learning Models: Search and Semantically Replace","created":"2021-04-20","cited_by_count":0,"area":null},{"id":"2104.11729","title":"Evaluating Deception Detection Model Robustness To Linguistic Variation","created":"2021-04-23","cited_by_count":0,"area":null},{"id":"2108.05490","title":"Attacks against Ranking Algorithms with Text Embeddings: a Case Study on Recruitment Algorithms","created":"2021-08-12","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":"2112.03007","title":"How to Build Robust FAQ Chatbot with Controllable Question Generator?","created":"2021-11-18","cited_by_count":0,"area":null},{"id":"2112.11660","title":"AED: An black-box NLP classifier model attacker","created":"2021-12-22","cited_by_count":0,"area":null},{"id":"2207.11500","title":"Catch Me If You Can: Deceiving Stance Detection and Geotagging Models to Protect Privacy of Individuals on Twitter","created":"2022-07-23","cited_by_count":0,"area":null},{"id":"2303.05575","title":"Evaluating the Robustness of Conversational Recommender Systems by Adversarial Examples","created":"2023-03-09","cited_by_count":0,"area":null},{"id":"2305.08929","title":"AF2-Mutation: Adversarial Sequence Mutations against AlphaFold2 on Protein Tertiary Structure Prediction","created":"2023-05-15","cited_by_count":0,"area":null},{"id":"2305.15119","title":"Another Dead End for Morphological Tags? Perturbed Inputs and Parsing","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2309.08999","title":"Context-aware Adversarial Attack on Named Entity Recognition","created":"2023-09-16","cited_by_count":0,"area":null},{"id":"2401.05338","title":"STR-Cert: Robustness Certification for Deep Text Recognition on Deep Learning Pipelines and Vision Transformers","created":"2023-11-28","cited_by_count":0,"area":null},{"id":"2403.01118","title":"Adversarial Testing for Visual Grounding via Image-Aware Property Reduction","created":"2024-03-02","cited_by_count":0,"area":null},{"id":"2403.02581","title":"VEglue: Testing Visual Entailment Systems via Object-Aligned Joint Erasing","created":"2024-03-05","cited_by_count":0,"area":"lr"},{"id":"2403.14731","title":"Reversible Jump Attack to Textual Classifiers with Modification Reduction","created":"2024-03-21","cited_by_count":0,"area":null},{"id":"2404.02660","title":"Adversarial Attacks and Dimensionality in Text Classifiers","created":"2024-04-03","cited_by_count":0,"area":null},{"id":"2404.05159","title":"Semantic Stealth: Adversarial Text Attacks on NLP Using Several Methods","created":"2024-04-08","cited_by_count":0,"area":null},{"id":"2404.11538","title":"GenFighter: A Generative and Evolutive Textual Attack Removal","created":"2024-04-17","cited_by_count":0,"area":null},{"id":"2410.12759","title":"Unitary Multi-Margin BERT for Robust Natural Language Processing","created":"2024-10-16","cited_by_count":0,"area":null}],"next_cursor":"100"}