{"list":"other","total":66,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1901.08573","title":"Theoretically Principled Trade-off between Robustness and Accuracy","created":"2019-01-24","cited_by_count":1517},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1902.02918","title":"Certified Adversarial Robustness via Randomized Smoothing","created":"2019-02-08","cited_by_count":1340},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939},{"id":"1805.12152","title":"Robustness May Be at Odds with Accuracy","created":"2018-05-30","cited_by_count":880},{"id":"2001.03994","title":"Fast is better than free: Revisiting adversarial training","created":"2020-01-12","cited_by_count":727},{"id":"1708.06131","title":"Evasion Attacks against Machine Learning at Test Time","created":"2017-08-21","cited_by_count":689},{"id":"2010.09670","title":"RobustBench: a standardized adversarial robustness benchmark","created":"2020-10-19","cited_by_count":661},{"id":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651},{"id":"1904.12843","title":"Adversarial Training for Free!","created":"2019-04-29","cited_by_count":643},{"id":"2104.04473","title":"Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM","created":"2021-04-09","cited_by_count":632},{"id":"1711.00851","title":"Provable defenses against adversarial examples via the convex outer adversarial polytope","created":"2017-11-02","cited_by_count":567},{"id":"2002.08347","title":"On Adaptive Attacks to Adversarial Example Defenses","created":"2020-02-19","cited_by_count":555},{"id":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531},{"id":"1802.03471","title":"Certified Robustness to Adversarial Examples with Differential Privacy","created":"2018-02-09","cited_by_count":468},{"id":"1805.12018","title":"Generalizing to Unseen Domains via Adversarial Data Augmentation","created":"2018-05-30","cited_by_count":451},{"id":"2001.09768","title":"Artificial Intelligence, Values and Alignment","created":"2020-01-13","cited_by_count":448},{"id":"1804.07998","title":"Generating Natural Language Adversarial Examples","created":"2018-04-21","cited_by_count":424},{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422},{"id":"1812.05271","title":"TextBugger: Generating Adversarial Text Against Real-world Applications","created":"2018-12-13","cited_by_count":381},{"id":"2304.05335","title":"Toxicity in ChatGPT: Analyzing Persona-assigned Language Models","created":"2023-04-11","cited_by_count":360},{"id":"1906.04584","title":"Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers","created":"2019-06-09","cited_by_count":330},{"id":"2306.15447","title":"Are aligned neural networks adversarially aligned?","created":"2023-06-26","cited_by_count":315},{"id":"1801.09344","title":"Certified Defenses against Adversarial Examples","created":"2018-01-29","cited_by_count":306},{"id":"1906.04893","title":"Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks","created":"2019-06-12","cited_by_count":293},{"id":"1605.07725","title":"Adversarial Training Methods for Semi-Supervised Text Classification","created":"2016-05-25","cited_by_count":280},{"id":"2308.09662","title":"Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment","created":"2023-08-18","cited_by_count":223},{"id":"1905.11268","title":"Combating Adversarial Misspellings with Robust Word Recognition","created":"2019-05-27","cited_by_count":163},{"id":"2008.04859","title":"BREEDS: Benchmarks for Subpopulation Shift","created":"2020-08-11","cited_by_count":155},{"id":"2002.08118","title":"Randomized Smoothing of All Shapes and Sizes","created":"2020-02-19","cited_by_count":147},{"id":"2006.12655","title":"Perceptual Adversarial Robustness: Defense Against Unseen Threat Models","created":"2020-06-22","cited_by_count":137},{"id":"2206.10550","title":"(Certified!!) Adversarial Robustness for Free!","created":"2022-06-21","cited_by_count":132},{"id":"2010.08001","title":"Maximum-Entropy Adversarial Data Augmentation for Improved Generalization and Robustness","created":"2020-10-15","cited_by_count":121},{"id":"1912.11188","title":"Adversarial AutoAugment","created":"2019-12-24","cited_by_count":111},{"id":"2004.08994","title":"Adversarial Training for Large Neural Language Models","created":"2020-04-20","cited_by_count":111},{"id":"2002.03018","title":"Certified Robustness to Label-Flipping Attacks via Randomized Smoothing","created":"2020-02-07","cited_by_count":108},{"id":"2102.11436","title":"Model-Based Domain Generalization","created":"2021-02-23","cited_by_count":104},{"id":"2302.02337","title":"Regulating ChatGPT and other Large Generative AI Models","created":"2023-02-05","cited_by_count":104},{"id":"2002.10733","title":"(De)Randomized Smoothing for Certifiable Defense against Patch Attacks","created":"2020-02-25","cited_by_count":98},{"id":"2110.13771","title":"AugMax: Adversarial Composition of Random Augmentations for Robust Training","created":"2021-10-26","cited_by_count":90},{"id":"2002.10477","title":"Precise Tradeoffs in Adversarial Training for Linear Regression","created":"2020-02-24","cited_by_count":77},{"id":"2207.09944","title":"Probable Domain Generalization via Quantile Risk Minimization","created":"2022-07-20","cited_by_count":66},{"id":"2202.13711","title":"Evaluating the Adversarial Robustness of Adaptive Test-time Defenses","created":"2022-02-28","cited_by_count":64},{"id":"2305.14950","title":"Adversarial Demonstration Attacks on Large Language Models","created":"2023-05-24","cited_by_count":63},{"id":"2002.12463","title":"Certified Defense to Image Transformations via Randomized Smoothing","created":"2020-02-27","cited_by_count":51},{"id":"2007.08450","title":"Learning perturbation sets for robust machine learning","created":"2020-07-16","cited_by_count":48},{"id":"1909.06723","title":"Natural Language Adversarial Defense through Synonym Encoding","created":"2019-09-15","cited_by_count":40},{"id":"2006.05161","title":"Provable tradeoffs in adversarially robust classification","created":"2020-06-09","cited_by_count":40},{"id":"2110.15767","title":"Adversarial Robustness with Semi-Infinite Constrained Learning","created":"2021-10-29","cited_by_count":39},{"id":"2202.01136","title":"Probabilistically Robust Learning: Balancing Average- and Worst-case Performance","created":"2022-02-02","cited_by_count":37},{"id":"2209.05980","title":"Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation","created":"2022-09-13","cited_by_count":16},{"id":"2307.05902","title":"Stability Guarantees for Feature Attributions with Multiplicative Smoothing","created":"2023-07-12","cited_by_count":14},{"id":"2306.11035","title":"Adversarial Training Should Be Cast as a Non-Zero-Sum Game","created":"2023-06-19","cited_by_count":13},{"id":"2203.09739","title":"Do Deep Networks Transfer Invariances Across Classes?","created":"2022-03-18","cited_by_count":12},{"id":"2110.10024","title":"Risks of AI Foundation Models in Education","created":"2021-10-19","cited_by_count":6},{"id":"2010.01039","title":"Query complexity of adversarial attacks","created":"2020-10-02","cited_by_count":5}],"next_cursor":null}