{"total":84,"rows":[{"id":"2211.09527","title":"Ignore Previous Prompt: Attack Techniques For Language Models","created":"2022-11-17","cited_by_count":832,"area":null},{"id":"2111.02840","title":"Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models","created":"2021-11-04","cited_by_count":232,"area":null},{"id":"2305.14710","title":"Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models","created":"2023-05-24","cited_by_count":110,"area":"safety"},{"id":"2101.04840","title":"Robustness Gym: Unifying the NLP Evaluation Landscape","created":"2021-01-13","cited_by_count":108,"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":"2106.07499","title":"An Empirical Survey of Data Augmentation for Limited Data Learning in NLP","created":"2021-06-14","cited_by_count":101,"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":"2211.01452","title":"MPCFormer: fast, performant and private Transformer inference with MPC","created":"2022-11-02","cited_by_count":69,"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":"2205.05256","title":"Evaluation Gaps in Machine Learning Practice","created":"2022-05-11","cited_by_count":49,"area":null},{"id":"2304.08979","title":"In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT","created":"2023-04-18","cited_by_count":37,"area":null},{"id":"2312.05491","title":"Using Captum to Explain Generative Language Models","created":"2023-12-09","cited_by_count":33,"area":null},{"id":"2304.14475","title":"ChatGPT as an Attack Tool: Stealthy Textual Backdoor Attack via Blackbox Generative Model Trigger","created":"2023-04-27","cited_by_count":31,"area":"safety"},{"id":"2110.15317","title":"Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework","created":"2021-10-28","cited_by_count":28,"area":null},{"id":"2210.03535","title":"From plane crashes to algorithmic harm: applicability of safety engineering frameworks for responsible ML","created":"2022-10-06","cited_by_count":27,"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":"2109.04367","title":"Multi-granularity Textual Adversarial Attack with Behavior Cloning","created":"2021-09-09","cited_by_count":21,"area":null},{"id":"2302.09457","title":"Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective","created":"2023-02-19","cited_by_count":20,"area":null},{"id":"2304.09563","title":"On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training","created":"2023-04-19","cited_by_count":20,"area":null},{"id":"2212.06385","title":"TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities","created":"2022-12-13","cited_by_count":19,"area":null},{"id":"2112.12310","title":"Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Art","created":"2021-12-23","cited_by_count":18,"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":"2106.01452","title":"BERT-Defense: A Probabilistic Model Based on BERT to Combat Cognitively Inspired Orthographic Adversarial Attacks","created":"2021-06-02","cited_by_count":17,"area":null},{"id":"2202.09817","title":"$\\mathcal{Y}$-Tuning: An Efficient Tuning Paradigm for Large-Scale Pre-Trained Models via Label Representation Learning","created":"2022-02-20","cited_by_count":15,"area":null},{"id":"2203.10378","title":"On Robust Prefix-Tuning for Text Classification","created":"2022-03-19","cited_by_count":15,"area":null},{"id":"2203.11131","title":"Towards Explainable Evaluation Metrics for Natural Language Generation","created":"2022-03-21","cited_by_count":15,"area":null},{"id":"2305.03655","title":"White-Box Multi-Objective Adversarial Attack on Dialogue Generation","created":"2023-05-05","cited_by_count":14,"area":null},{"id":"2501.16750","title":"HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns","created":"2025-01-28","cited_by_count":14,"area":null},{"id":"2203.10346","title":"Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defense","created":"2022-03-19","cited_by_count":13,"area":null},{"id":"2408.15488","title":"Legilimens: Practical and Unified Content Moderation for Large Language Model Services","created":"2024-08-28","cited_by_count":13,"area":"safety"},{"id":"2311.11861","title":"Generating Valid and Natural Adversarial Examples with Large Language Models","created":"2023-11-20","cited_by_count":12,"area":null},{"id":"2310.05592","title":"InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations","created":"2023-10-09","cited_by_count":11,"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":"2303.08032","title":"Verifying the Robustness of Automatic Credibility Assessment","created":"2023-03-14","cited_by_count":8,"area":null},{"id":"2311.07553","title":"An Extensive Study on Adversarial Attack against Pre-trained Models of Code","created":"2023-11-13","cited_by_count":8,"area":null},{"id":"2503.19540","title":"FLEX: A Benchmark for Evaluating Robustness of Fairness in Large Language Models","created":"2025-03-25","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":"2306.15164","title":"DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization","created":"2023-06-27","cited_by_count":7,"area":null},{"id":"2104.08453","title":"R&R: Metric-guided Adversarial Sentence Generation","created":"2021-04-17","cited_by_count":6,"area":null},{"id":"2108.12242","title":"Deep learning models are not robust against noise in clinical text","created":"2021-08-27","cited_by_count":6,"area":null},{"id":"2208.08010","title":"ShortcutLens: A Visual Analytics Approach for Exploring Shortcuts in Natural Language Understanding Dataset","created":"2022-08-17","cited_by_count":6,"area":null},{"id":"2401.03514","title":"ROIC-DM: Robust Text Inference and Classification via Diffusion Model","created":"2024-01-07","cited_by_count":5,"area":"diffusion"},{"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":"2201.08555","title":"Identifying Adversarial Attacks on Text Classifiers","created":"2022-01-21","cited_by_count":4,"area":null},{"id":"2205.10238","title":"Visualizing and Explaining Language Models","created":"2022-04-30","cited_by_count":4,"area":null},{"id":"2308.03558","title":"Mondrian: Prompt Abstraction Attack Against Large Language Models for Cheaper API Pricing","created":"2023-08-07","cited_by_count":4,"area":null},{"id":"2402.02078","title":"Exploring the Robustness of Task-oriented Dialogue Systems for Colloquial German Varieties","created":"2024-02-03","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":"2412.02323","title":"Pay Attention to the Robustness of Chinese Minority Language Models! Syllable-level Textual Adversarial Attack on Tibetan Script","created":"2024-12-03","cited_by_count":4,"area":null},{"id":"2412.10807","title":"Towards Action Hijacking of Large Language Model-based Agent","created":"2024-12-14","cited_by_count":4,"area":"agents"},{"id":"2603.26105","title":"Are LLM-Enhanced Graph Neural Networks Robust against Poisoning Attacks?","created":"2026-03-27","cited_by_count":4,"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":"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":"2310.14001","title":"Toward Stronger Textual Attack Detectors","created":"2023-10-21","cited_by_count":3,"area":null},{"id":"2505.22355","title":"Look Within or Look Beyond? A Theoretical Comparison Between Parameter-Efficient and Full Fine-Tuning","created":"2025-05-28","cited_by_count":3,"area":null},{"id":"2205.00047","title":"Logically Consistent Adversarial Attacks for Soft Theorem Provers","created":"2022-04-29","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":"2302.11412","title":"Data Augmentation for Neural NLP","created":"2023-02-22","cited_by_count":2,"area":null},{"id":"2306.15705","title":"On the Universal Adversarial Perturbations for Efficient Data-free Adversarial Detection","created":"2023-06-27","cited_by_count":2,"area":null},{"id":"2406.10950","title":"E-Bench: Towards Evaluating the Ease-of-Use of Large Language Models","created":"2024-06-16","cited_by_count":2,"area":null},{"id":"2407.08839","title":"A Survey on the Application of Generative Adversarial Networks in Cybersecurity: Prospective, Direction and Open Research Scopes","created":"2024-07-11","cited_by_count":2,"area":null},{"id":"2407.19216","title":"EaTVul: ChatGPT-based Evasion Attack Against Software Vulnerability Detection","created":"2024-07-27","cited_by_count":2,"area":null},{"id":"2412.12478","title":"Human-in-the-Loop Generation of Adversarial Texts: A Case Study on Tibetan Script","created":"2024-12-17","cited_by_count":2,"area":null},{"id":"2501.02654","title":"Tougher Text, Smarter Models: Raising the Bar for Adversarial Defence Benchmarks","created":"2025-01-05","cited_by_count":2,"area":null},{"id":"2502.05225","title":"BitAbuse: A Dataset of Visually Perturbed Texts for Defending Phishing Attacks","created":"2025-02-06","cited_by_count":2,"area":null},{"id":"2504.06669","title":"NLP Security and Ethics, in the Wild","created":"2025-04-09","cited_by_count":2,"area":null},{"id":"2506.08188","title":"GradEscape: A Gradient-Based Evader Against AI-Generated Text Detectors","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2110.04413","title":"Robustness Evaluation of Transformer-based Form Field Extractors via Form Attacks","created":"2021-10-08","cited_by_count":1,"area":null},{"id":"2302.07324","title":"READIN: A Chinese Multi-Task Benchmark with Realistic and Diverse Input Noises","created":"2023-02-14","cited_by_count":1,"area":null},{"id":"2307.08327","title":"Analyzing the Impact of Adversarial Examples on Explainable Machine Learning","created":"2023-07-17","cited_by_count":1,"area":null},{"id":"2402.02695","title":"Exploiting Class Probabilities for Black-box Sentence-level Attacks","created":"2024-02-05","cited_by_count":1,"area":null},{"id":"2409.19788","title":"Exploring Adversarial Robustness in Classification tasks using DNA Language Models","created":"2024-09-29","cited_by_count":1,"area":null},{"id":"2504.13551","title":"Q-FAKER: Query-free Hard Black-box Attack via Controlled Generation","created":"2025-04-18","cited_by_count":1,"area":null},{"id":"2507.10330","title":"Bridging Robustness and Generalization Against Word Substitution Attacks in NLP via the Growth Bound Matrix Approach","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2103.11441","title":"TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing","created":"2021-03-21","cited_by_count":0,"area":null},{"id":"2110.00425","title":"HAT4RD: Hierarchical Adversarial Training for Rumor Detection on Social Media","created":"2021-08-29","cited_by_count":0,"area":null},{"id":"2208.14488","title":"Constraining Representations Yields Models That Know What They Don't Know","created":"2022-08-30","cited_by_count":0,"area":null},{"id":"2211.04973","title":"Accelerating Adversarial Perturbation by 50% with Semi-backward Propagation","created":"2022-11-09","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":"2405.18741","title":"Genshin: General Shield for Natural Language Processing with Large Language Models","created":"2024-05-29","cited_by_count":0,"area":null},{"id":"2510.13570","title":"Selective Adversarial Attacks on LLM Benchmarks","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2511.12423","title":"GRAPHTEXTACK: A Realistic Black-Box Node Injection Attack on LLM-Enhanced GNNs","created":"2025-11-16","cited_by_count":0,"area":null},{"id":"2606.13439","title":"S-GBT: Smooth Growth Bound Tensor for Certified Robustness Against Word Substitution Attacks in NLP","created":"2026-06-11","cited_by_count":0,"area":null}],"next_cursor":null}