{"total":136,"rows":[{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463,"area":null},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333,"area":null},{"id":"2305.08283","title":"From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models","created":"2023-05-15","cited_by_count":260,"area":null},{"id":"2104.13733","title":"Gradient-based Adversarial Attacks against Text Transformers","created":"2021-04-15","cited_by_count":234,"area":null},{"id":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222,"area":null},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107,"area":null},{"id":"2210.10683","title":"Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP","created":"2022-10-19","cited_by_count":102,"area":null},{"id":"2303.14822","title":"MGTBench: Benchmarking Machine-Generated Text Detection","created":"2023-03-26","cited_by_count":93,"area":null},{"id":"2305.01904","title":"Robust Multi-bit Natural Language Watermarking through Invariant Features","created":"2023-05-03","cited_by_count":82,"area":"safety"},{"id":"2109.00544","title":"Towards Improving Adversarial Training of NLP Models","created":"2021-09-01","cited_by_count":79,"area":null},{"id":"2112.02721","title":"NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation","created":"2021-12-06","cited_by_count":73,"area":null},{"id":"2310.04655","title":"VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models","created":"2023-10-07","cited_by_count":68,"area":null},{"id":"2111.07970","title":"Triggerless Backdoor Attack for NLP Tasks with Clean Labels","created":"2021-11-15","cited_by_count":66,"area":"safety"},{"id":"2205.12700","title":"BITE: Textual Backdoor Attacks with Iterative Trigger Injection","created":"2022-05-25","cited_by_count":53,"area":"safety"},{"id":"2205.01287","title":"SemAttack: Natural Textual Attacks via Different Semantic Spaces","created":"2022-05-03","cited_by_count":42,"area":null},{"id":"2406.19470","title":"Changing Answer Order Can Decrease MMLU Accuracy","created":"2024-06-27","cited_by_count":42,"area":null},{"id":"2303.11470","title":"Did You Train on My Dataset? Towards Public Dataset Protection with Clean-Label Backdoor Watermarking","created":"2023-03-20","cited_by_count":37,"area":null},{"id":"2305.09859","title":"Smaller Language Models are Better Black-box Machine-Generated Text Detectors","created":"2023-05-17","cited_by_count":35,"area":null},{"id":"2307.16630","title":"Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks","created":"2023-07-31","cited_by_count":34,"area":null},{"id":"2108.06332","title":"FlipDA: Effective and Robust Data Augmentation for Few-Shot Learning","created":"2021-08-13","cited_by_count":32,"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":"2306.13103","title":"Evaluating the Robustness of Text-to-image Diffusion Models against Real-world Attacks","created":"2023-06-16","cited_by_count":24,"area":"diffusion"},{"id":"2405.11930","title":"Data Contamination Calibration for Black-box LLMs","created":"2024-05-20","cited_by_count":24,"area":null},{"id":"2104.05062","title":"Achieving Model Robustness through Discrete Adversarial Training","created":"2021-04-11","cited_by_count":23,"area":null},{"id":"2203.07653","title":"Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness","created":"2022-03-15","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":"2305.15587","title":"How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attacks","created":"2023-05-24","cited_by_count":18,"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":"2110.11589","title":"Text Counterfactuals via Latent Optimization and Shapley-Guided Search","created":"2021-10-22","cited_by_count":16,"area":null},{"id":"2206.11724","title":"BERT Rankers are Brittle: a Study using Adversarial Document Perturbations","created":"2022-06-23","cited_by_count":16,"area":null},{"id":"2402.01806","title":"HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text","created":"2024-02-02","cited_by_count":16,"area":null},{"id":"2404.12274","title":"Advancing the Robustness of Large Language Models through Self-Denoised Smoothing","created":"2024-04-18","cited_by_count":16,"area":"safety"},{"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":"2210.15221","title":"TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack","created":"2022-10-27","cited_by_count":15,"area":null},{"id":"2406.04755","title":"LLM Whisperer: An Inconspicuous Attack to Bias LLM Responses","created":"2024-06-07","cited_by_count":15,"area":null},{"id":"2108.06665","title":"Accurate, yet inconsistent? Consistency Analysis on Language Understanding Models","created":"2021-08-15","cited_by_count":13,"area":null},{"id":"2307.02514","title":"Exploring Multimodal Approaches for Alzheimer's Disease Detection Using Patient Speech Transcript and Audio Data","created":"2023-07-05","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":"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":"2305.07406","title":"Two-in-One: A Model Hijacking Attack Against Text Generation Models","created":"2023-05-12","cited_by_count":12,"area":null},{"id":"2112.10424","title":"Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction","created":"2021-12-20","cited_by_count":11,"area":null},{"id":"2305.04557","title":"Toward Adversarial Training on Contextualized Language Representation","created":"2023-05-08","cited_by_count":10,"area":null},{"id":"2402.11083","title":"VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models","created":"2024-02-16","cited_by_count":10,"area":null},{"id":"2104.07284","title":"Consistency Training with Virtual Adversarial Discrete Perturbation","created":"2021-04-15","cited_by_count":9,"area":null},{"id":"2110.07165","title":"Semantically Distributed Robust Optimization for Vision-and-Language Inference","created":"2021-10-14","cited_by_count":9,"area":null},{"id":"2308.00319","title":"LimeAttack: Local Explainable Method for Textual Hard-Label Adversarial Attack","created":"2023-08-01","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":"2302.02023","title":"TextShield: Beyond Successfully Detecting Adversarial Sentences in Text Classification","created":"2023-02-03","cited_by_count":8,"area":null},{"id":"2410.15107","title":"Toward Robust RALMs: Revealing the Impact of Imperfect Retrieval on Retrieval-Augmented Language Models","created":"2024-10-19","cited_by_count":8,"area":"rag"},{"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":"2302.09665","title":"CitySpec with Shield: A Secure Intelligent Assistant for Requirement Formalization","created":"2023-02-19","cited_by_count":7,"area":null},{"id":"2304.10727","title":"RoCOCO: Robustness Benchmark of MS-COCO to Stress-test Image-Text Matching Models","created":"2023-04-21","cited_by_count":7,"area":"mllm"},{"id":"2104.08453","title":"R&R: Metric-guided Adversarial Sentence Generation","created":"2021-04-17","cited_by_count":6,"area":null},{"id":"2305.08146","title":"ParaLS: Lexical Substitution via Pretrained Paraphraser","created":"2023-05-14","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":"2306.04535","title":"PromptAttack: Probing Dialogue State Trackers with Adversarial Prompts","created":"2023-06-07","cited_by_count":6,"area":"safety"},{"id":"2308.11284","title":"LEAP: Efficient and Automated Test Method for NLP Software","created":"2023-08-22","cited_by_count":6,"area":null},{"id":"2405.14646","title":"Unveiling the Achilles' Heel of NLG Evaluators: A Unified Adversarial Framework Driven by Large Language Models","created":"2024-05-23","cited_by_count":6,"area":null},{"id":"2406.14545","title":"Unmasking Database Vulnerabilities: Zero-Knowledge Schema Inference Attacks in Text-to-SQL Systems","created":"2024-06-20","cited_by_count":6,"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":"2109.06950","title":"Automatically Exposing Problems with Neural Dialog Models","created":"2021-09-14","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":"2211.04205","title":"Preserving Semantics in Textual Adversarial Attacks","created":"2022-11-08","cited_by_count":5,"area":null},{"id":"2212.10258","title":"In and Out-of-Domain Text Adversarial Robustness via Label Smoothing","created":"2022-12-20","cited_by_count":5,"area":null},{"id":"2303.07199","title":"BeamAttack: Generating High-quality Textual Adversarial Examples through Beam Search and Mixed Semantic Spaces","created":"2023-03-09","cited_by_count":5,"area":null},{"id":"2304.08767","title":"Masked Language Model Based Textual Adversarial Example Detection","created":"2023-04-18","cited_by_count":5,"area":null},{"id":"2310.16955","title":"Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attacks","created":"2023-10-25","cited_by_count":5,"area":null},{"id":"2311.00508","title":"Robustness Tests for Automatic Machine Translation Metrics with Adversarial Attacks","created":"2023-11-01","cited_by_count":5,"area":null},{"id":"2512.04838","title":"DAMASHA: Detecting AI in Mixed Adversarial Texts via Segmentation with Human-interpretable Attribution","created":"2025-12-04","cited_by_count":5,"area":null},{"id":"2201.08555","title":"Identifying Adversarial Attacks on Text Classifiers","created":"2022-01-21","cited_by_count":4,"area":null},{"id":"2210.02844","title":"Are Synonym Substitution Attacks Really Synonym Substitution Attacks?","created":"2022-10-06","cited_by_count":4,"area":null},{"id":"2211.02646","title":"Robustness of Fusion-based Multimodal Classifiers to Cross-Modal Content Dilutions","created":"2022-11-04","cited_by_count":4,"area":null},{"id":"2303.01234","title":"Frauds Bargain Attack: Generating Adversarial Text Samples via Word Manipulation Process","created":"2023-03-01","cited_by_count":4,"area":null},{"id":"2305.05253","title":"Attack Named Entity Recognition by Entity Boundary Interference","created":"2023-05-09","cited_by_count":4,"area":null},{"id":"2308.15246","title":"A Classification-Guided Approach for Adversarial Attacks against Neural Machine Translation","created":"2023-08-29","cited_by_count":4,"area":null},{"id":"2310.19152","title":"BERT Lost Patience Won't Be Robust to Adversarial Slowdown","created":"2023-10-29","cited_by_count":4,"area":null},{"id":"2406.19413","title":"Saliency Attention and Semantic Similarity-Driven Adversarial Perturbation","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2409.02649","title":"OpenFact at CheckThat! 2024: Combining Multiple Attack Methods for Effective Adversarial Text Generation","created":"2024-09-04","cited_by_count":4,"area":null},{"id":"2104.07623","title":"Sometimes We Want Translationese","created":"2021-04-15","cited_by_count":3,"area":null},{"id":"2203.11199","title":"Distinguishing Non-natural from Natural Adversarial Samples for More Robust Pre-trained Language Model","created":"2022-03-19","cited_by_count":3,"area":null},{"id":"2205.01714","title":"Don't sweat the small stuff, classify the rest: Sample Shielding to protect text classifiers against adversarial attacks","created":"2022-05-03","cited_by_count":3,"area":null},{"id":"2210.09917","title":"Controllable Fake Document Infilling for Cyber Deception","created":"2022-10-18","cited_by_count":3,"area":null},{"id":"2210.11498","title":"Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP Models","created":"2022-10-20","cited_by_count":3,"area":null},{"id":"2303.11143","title":"Adversarial Attacks against Binary Similarity Systems","created":"2023-03-20","cited_by_count":3,"area":null},{"id":"2305.04067","title":"The Best Defense is Attack: Repairing Semantics in Textual Adversarial Examples","created":"2023-05-06","cited_by_count":3,"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":"2306.11065","title":"Cross-Modal Attribute Insertions for Assessing the Robustness of Vision-and-Language Learning","created":"2023-06-19","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":"2308.07937","title":"Automated Testing and Improvement of Named Entity Recognition Systems","created":"2023-08-14","cited_by_count":3,"area":null},{"id":"2310.14001","title":"Toward Stronger Textual Attack Detectors","created":"2023-10-21","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":"2406.17104","title":"Automated Adversarial Discovery for Safety Classifiers","created":"2024-06-24","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":"2505.01900","title":"CAMOUFLAGE: Exploiting Misinformation Detection Systems Through LLM-driven Adversarial Claim Transformation","created":"2025-05-03","cited_by_count":3,"area":null},{"id":"2204.13853","title":"Detecting Textual Adversarial Examples Based on Distributional Characteristics of Data Representations","created":"2022-04-29","cited_by_count":2,"area":null},{"id":"2205.11551","title":"Learning to Ignore Adversarial Attacks","created":"2022-05-23","cited_by_count":2,"area":null},{"id":"2210.12233","title":"TCAB: A Large-Scale Text Classification Attack Benchmark","created":"2022-10-21","cited_by_count":2,"area":null},{"id":"2306.12043","title":"Sample Attackability in Natural Language Adversarial Attacks","created":"2023-06-21","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}],"next_cursor":"100"}