{"total":286,"rows":[{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429,"area":"safety"},{"id":"2308.03825","title":"\"Do Anything Now\": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models","created":"2023-08-07","cited_by_count":489,"area":"safety"},{"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":"2303.13408","title":"Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense","created":"2023-03-23","cited_by_count":429,"area":"safety"},{"id":"2105.03075","title":"A Survey of Data Augmentation Approaches for NLP","created":"2021-05-07","cited_by_count":409,"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":"2101.00288","title":"Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models","created":"2021-01-01","cited_by_count":222,"area":null},{"id":"2105.12400","title":"Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger","created":"2021-05-26","cited_by_count":222,"area":"safety"},{"id":"2310.10844","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","created":"2023-10-16","cited_by_count":194,"area":"safety"},{"id":"2110.07139","title":"Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer","created":"2021-10-14","cited_by_count":158,"area":"safety"},{"id":"2307.10490","title":"Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs","created":"2023-07-19","cited_by_count":124,"area":"mllm"},{"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":"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":"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":"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":"2407.20859","title":"Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification","created":"2024-07-30","cited_by_count":81,"area":"agents"},{"id":"2310.14542","title":"Evaluating Large Language Models on Controlled Generation Tasks","created":"2023-10-23","cited_by_count":73,"area":null},{"id":"2310.14735","title":"Unleashing the potential of prompt engineering for large language models","created":"2023-10-23","cited_by_count":72,"area":null},{"id":"2106.09898","title":"Bad Characters: Imperceptible NLP Attacks","created":"2021-06-18","cited_by_count":71,"area":null},{"id":"2107.13541","title":"Towards Robustness Against Natural Language Word Substitutions","created":"2021-07-28","cited_by_count":69,"area":null},{"id":"2107.07150","title":"Tailor: Generating and Perturbing Text with Semantic Controls","created":"2021-07-15","cited_by_count":68,"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":"2302.04237","title":"Black Box Adversarial Prompting for Foundation Models","created":"2023-02-08","cited_by_count":62,"area":"safety"},{"id":"2402.09179","title":"Instruction Backdoor Attacks Against Customized LLMs","created":"2024-02-14","cited_by_count":62,"area":"safety"},{"id":"2305.19713","title":"Red Teaming Language Model Detectors with Language Models","created":"2023-05-31","cited_by_count":55,"area":"safety"},{"id":"2104.15135","title":"Explanation-Based Human Debugging of NLP Models: A Survey","created":"2021-04-30","cited_by_count":53,"area":null},{"id":"2205.12700","title":"BITE: Textual Backdoor Attacks with Iterative Trigger Injection","created":"2022-05-25","cited_by_count":53,"area":"safety"},{"id":"2301.08881","title":"Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness","created":"2023-01-21","cited_by_count":53,"area":null},{"id":"2402.14872","title":"Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs","created":"2024-02-21","cited_by_count":53,"area":"safety"},{"id":"2107.00440","title":"CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language Understanding","created":"2021-07-01","cited_by_count":50,"area":null},{"id":"2402.16187","title":"No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices","created":"2024-02-25","cited_by_count":50,"area":"safety"},{"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":"2204.03031","title":"VALUE: Understanding Dialect Disparity in NLU","created":"2022-04-06","cited_by_count":47,"area":null},{"id":"2101.10579","title":"Generating Syntactically Controlled Paraphrases without Using Annotated Parallel Pairs","created":"2021-01-26","cited_by_count":45,"area":null},{"id":"2311.01967","title":"The language of prompting: What linguistic properties make a prompt successful?","created":"2023-11-03","cited_by_count":44,"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":"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":"2310.05280","title":"Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systems","created":"2023-10-08","cited_by_count":37,"area":null},{"id":"2109.13070","title":"Controllable Neural Dialogue Summarization with Personal Named Entity Planning","created":"2021-09-27","cited_by_count":36,"area":null},{"id":"2204.11790","title":"Can Rationalization Improve Robustness?","created":"2022-04-25","cited_by_count":36,"area":null},{"id":"2404.05530","title":"Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data","created":"2024-04-08","cited_by_count":35,"area":"alignment"},{"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":"2310.14480","title":"Attention-Enhancing Backdoor Attacks Against BERT-based Models","created":"2023-10-23","cited_by_count":32,"area":"safety"},{"id":"2203.10940","title":"Quality Controlled Paraphrase Generation","created":"2022-03-21","cited_by_count":31,"area":null},{"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":"2305.10235","title":"Assessing Hidden Risks of LLMs: An Empirical Study on Robustness, Consistency, and Credibility","created":"2023-05-15","cited_by_count":30,"area":null},{"id":"2109.05620","title":"RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition Models","created":"2021-09-12","cited_by_count":28,"area":null},{"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":"2212.09994","title":"Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table Perturbation","created":"2022-12-20","cited_by_count":28,"area":null},{"id":"2303.02242","title":"TrojText: Test-time Invisible Textual Trojan Insertion","created":"2023-03-03","cited_by_count":28,"area":null},{"id":"2310.12516","title":"ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks","created":"2023-10-19","cited_by_count":28,"area":"rag"},{"id":"2302.02213","title":"CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks","created":"2023-02-04","cited_by_count":27,"area":null},{"id":"2402.11638","title":"Stumbling Blocks: Stress Testing the Robustness of Machine-Generated Text Detectors Under Attacks","created":"2024-02-18","cited_by_count":26,"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":"2106.04823","title":"Taxonomy of Machine Learning Safety: A Survey and Primer","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2202.00535","title":"Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning","created":"2022-02-01","cited_by_count":25,"area":"rag"},{"id":"2106.05532","title":"How Robust are Model Rankings: A Leaderboard Customization Approach for Equitable Evaluation","created":"2021-06-10","cited_by_count":24,"area":null},{"id":"2110.08514","title":"Analyzing Dynamic Adversarial Training Data in the Limit","created":"2021-10-16","cited_by_count":24,"area":null},{"id":"2204.04636","title":"\"That Is a Suspicious Reaction!\": Interpreting Logits Variation to Detect NLP Adversarial Attacks","created":"2022-04-10","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":"2302.05096","title":"Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information","created":"2023-02-10","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":"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":"2104.05115","title":"Disentangling Semantics and Syntax in Sentence Embeddings with Pre-trained Language Models","created":"2021-04-11","cited_by_count":22,"area":null},{"id":"2105.15053","title":"Factorising Meaning and Form for Intent-Preserving Paraphrasing","created":"2021-05-31","cited_by_count":22,"area":null},{"id":"2110.07280","title":"P-Adapters: Robustly Extracting Factual Information from Language Models with Diverse Prompts","created":"2021-10-14","cited_by_count":22,"area":"moe"},{"id":"2203.03463","title":"Hierarchical Sketch Induction for Paraphrase Generation","created":"2022-03-07","cited_by_count":22,"area":null},{"id":"2104.08645","title":"Improving Zero-Shot Cross-Lingual Transfer Learning via Robust Training","created":"2021-04-17","cited_by_count":21,"area":null},{"id":"2104.15114","title":"Paraphrastic Representations at Scale","created":"2021-04-30","cited_by_count":21,"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":"2110.07385","title":"Few-shot Controllable Style Transfer for Low-Resource Multilingual Settings","created":"2021-10-14","cited_by_count":21,"area":null},{"id":"2311.09763","title":"Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations","created":"2023-11-16","cited_by_count":21,"area":"safety"},{"id":"2305.01812","title":"Post-Abstention: Towards Reliably Re-Attempting the Abstained Instances in QA","created":"2023-05-02","cited_by_count":20,"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":"2206.05395","title":"Why is constrained neural language generation particularly challenging?","created":"2022-06-11","cited_by_count":19,"area":null},{"id":"2210.14353","title":"RoMQA: A Benchmark for Robust, Multi-evidence, Multi-answer Question Answering","created":"2022-10-25","cited_by_count":19,"area":null},{"id":"2211.02878","title":"Textual Manifold-based Defense Against Natural Language Adversarial Examples","created":"2022-11-05","cited_by_count":19,"area":null},{"id":"2102.07818","title":"Certified Robustness to Programmable Transformations in LSTMs","created":"2021-02-15","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":"2109.02229","title":"Efficient Combinatorial Optimization for Word-level Adversarial Textual Attack","created":"2021-09-06","cited_by_count":17,"area":null},{"id":"2206.05511","title":"Improving the Adversarial Robustness of NLP Models by Information Bottleneck","created":"2022-06-11","cited_by_count":17,"area":null},{"id":"2504.02733","title":"Enhancing LLM Robustness to Perturbed Instructions: An Empirical Study","created":"2025-04-03","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":"2203.10378","title":"On Robust Prefix-Tuning for Text Classification","created":"2022-03-19","cited_by_count":15,"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":"2210.15221","title":"TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack","created":"2022-10-27","cited_by_count":15,"area":null},{"id":"2505.12567","title":"A Survey of Attacks on Large Language Models","created":"2025-05-18","cited_by_count":15,"area":"agents"},{"id":"2506.21521","title":"Potemkin Understanding in Large Language Models","created":"2025-06-26","cited_by_count":15,"area":null},{"id":"2104.08639","title":"AM2iCo: Evaluating Word Meaning in Context across Low-Resource Languages with Adversarial Examples","created":"2021-04-17","cited_by_count":14,"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":"2305.11140","title":"Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model","created":"2023-05-18","cited_by_count":14,"area":null},{"id":"2311.07167","title":"STEER: Unified Style Transfer with Expert Reinforcement","created":"2023-11-13","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":"2106.04102","title":"Swords: A Benchmark for Lexical Substitution with Improved Data Coverage and Quality","created":"2021-06-08","cited_by_count":13,"area":null},{"id":"2109.00363","title":"ConRPG: Paraphrase Generation using Contexts as Regularizer","created":"2021-09-01","cited_by_count":13,"area":null}],"next_cursor":"100"}