{"list":"other","total":71,"rows":[{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"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":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"1608.04644","title":"Towards Evaluating the Robustness of Neural Networks","created":"2016-08-16","cited_by_count":2998},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2307.13854","title":"WebArena: A Realistic Web Environment for Building Autonomous Agents","created":"2023-07-25","cited_by_count":2006},{"id":"2405.15793","title":"SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering","created":"2024-05-06","cited_by_count":1737},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1901.08573","title":"Theoretically Principled Trade-off between Robustness and Accuracy","created":"2019-01-24","cited_by_count":1517},{"id":"1802.00420","title":"Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples","created":"2018-02-01","cited_by_count":1268},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"1602.02697","title":"Practical Black-Box Attacks against Machine Learning","created":"2016-02-08","cited_by_count":903},{"id":"1511.04508","title":"Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks","created":"2015-11-14","cited_by_count":678},{"id":"2010.09670","title":"RobustBench: a standardized adversarial robustness benchmark","created":"2020-10-19","cited_by_count":661},{"id":"2002.08347","title":"On Adaptive Attacks to Adversarial Example Defenses","created":"2020-02-19","cited_by_count":555},{"id":"1705.07263","title":"Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods","created":"2017-05-20","cited_by_count":546},{"id":"1711.00117","title":"Countering Adversarial Images using Input Transformations","created":"2017-10-31","cited_by_count":520},{"id":"1704.01155","title":"Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks","created":"2017-04-04","cited_by_count":486},{"id":"1902.06705","title":"On Evaluating Adversarial Robustness","created":"2019-02-18","cited_by_count":447},{"id":"1901.09960","title":"Using Pre-Training Can Improve Model Robustness and Uncertainty","created":"2019-01-28","cited_by_count":373},{"id":"1801.02613","title":"Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality","created":"2018-01-08","cited_by_count":282},{"id":"1705.09064","title":"MagNet: a Two-Pronged Defense against Adversarial Examples","created":"2017-05-25","cited_by_count":269},{"id":"2411.04872","title":"FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI","created":"2024-11-07","cited_by_count":243},{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222},{"id":"2411.15114","title":"RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts","created":"2024-11-22","cited_by_count":175},{"id":"1803.01442","title":"Stochastic Activation Pruning for Robust Adversarial Defense","created":"2018-03-05","cited_by_count":171},{"id":"2406.13352","title":"AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents","created":"2024-06-19","cited_by_count":145},{"id":"2106.06041","title":"Adversarial purification with Score-based generative models","created":"2021-06-11","cited_by_count":134},{"id":"2410.20285","title":"SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement","created":"2024-10-26","cited_by_count":132},{"id":"2409.11363","title":"CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark","created":"2024-09-17","cited_by_count":123},{"id":"2402.06664","title":"LLM Agents can Autonomously Hack Websites","created":"2024-02-06","cited_by_count":109},{"id":"2412.04604","title":"ARC Prize 2024: Technical Report","created":"2024-12-05","cited_by_count":104},{"id":"1803.05787","title":"Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples","created":"2018-03-14","cited_by_count":99},{"id":"2308.06782","title":"PentestGPT: An LLM-empowered Automatic Penetration Testing Tool","created":"2023-08-13","cited_by_count":97},{"id":"2406.05590","title":"NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security","created":"2024-06-08","cited_by_count":93},{"id":"2110.12976","title":"Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attacks","created":"2021-10-25","cited_by_count":91},{"id":"2404.13161","title":"CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models","created":"2024-04-19","cited_by_count":89},{"id":"2308.00121","title":"Getting pwn'd by AI: Penetration Testing with Large Language Models","created":"2023-07-24","cited_by_count":83},{"id":"1612.07767","title":"Adversarial Examples Detection in Deep Networks with Convolutional Filter Statistics","created":"2016-12-22","cited_by_count":77},{"id":"2202.13711","title":"Evaluating the Adversarial Robustness of Adaptive Test-time Defenses","created":"2022-02-28","cited_by_count":64},{"id":"2209.07399","title":"A Light Recipe to Train Robust Vision Transformers","created":"2022-09-15","cited_by_count":64},{"id":"2305.13948","title":"Decoupled Kullback-Leibler Divergence Loss","created":"2023-05-23","cited_by_count":58},{"id":"1909.11515","title":"Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks","created":"2019-09-25","cited_by_count":54},{"id":"1905.10510","title":"Enhancing Adversarial Defense by k-Winners-Take-All","created":"2019-05-25","cited_by_count":51},{"id":"1910.07629","title":"A New Defense Against Adversarial Images: Turning a Weakness into a Strength","created":"2019-10-16","cited_by_count":49},{"id":"2103.14222","title":"Adversarial Attacks are Reversible with Natural Supervision","created":"2021-03-26","cited_by_count":47},{"id":"1904.08554","title":"Gotta Catch 'Em All: Using Honeypots to Catch Adversarial Attacks on Neural Networks","created":"2019-04-18","cited_by_count":40},{"id":"2212.05630","title":"DISCO: Adversarial Defense with Local Implicit Functions","created":"2022-12-11","cited_by_count":34},{"id":"2106.04938","title":"Attacking Adversarial Attacks as A Defense","created":"2021-06-09","cited_by_count":32},{"id":"2004.10162","title":"EMPIR: Ensembles of Mixed Precision Deep Networks for Increased Robustness against Adversarial Attacks","created":"2020-04-21","cited_by_count":28},{"id":"2103.14347","title":"Combating Adversaries with Anti-Adversaries","created":"2021-03-26","cited_by_count":27},{"id":"1903.09799","title":"Improving Adversarial Robustness via Guided Complement Entropy","created":"2019-03-23","cited_by_count":15},{"id":"2305.14188","title":"The Best Defense is a Good Offense: Adversarial Augmentation against Adversarial Attacks","created":"2023-05-23","cited_by_count":15},{"id":"2307.15008","title":"A LLM Assisted Exploitation of AI-Guardian","created":"2023-07-20","cited_by_count":15},{"id":"2112.01601","title":"Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness?","created":"2021-12-02","cited_by_count":12},{"id":"2408.05446","title":"Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness","created":"2024-08-08","cited_by_count":12},{"id":"2009.08233","title":"Label Smoothing and Adversarial Robustness","created":"2020-09-17","cited_by_count":10},{"id":"2107.04401","title":"Improving Model Robustness with Latent Distribution Locally and Globally","created":"2021-07-08","cited_by_count":9},{"id":"2305.03173","title":"New Adversarial Image Detection Based on Sentiment Analysis","created":"2023-05-03","cited_by_count":6},{"id":"1906.09525","title":"Defending Against Adversarial Examples with K-Nearest Neighbor","created":"2019-06-23","cited_by_count":5},{"id":"2303.14077","title":"Improved Adversarial Training Through Adaptive Instance-wise Loss Smoothing","created":"2023-03-24","cited_by_count":5},{"id":"2405.15942","title":"Can Implicit Bias Imply Adversarial Robustness?","created":"2024-05-24","cited_by_count":5},{"id":"2305.01139","title":"Stratified Adversarial Robustness with Rejection","created":"2023-05-02","cited_by_count":4},{"id":"2009.10975","title":"A Partial Break of the Honeypots Defense to Catch Adversarial Attacks","created":"2020-09-23","cited_by_count":3},{"id":"2105.00495","title":"BAARD: Blocking Adversarial Examples by Testing for Applicability, Reliability and Decidability","created":"2021-05-02","cited_by_count":2},{"id":"2202.02595","title":"Memory Defense: More Robust Classification via a Memory-Masking Autoencoder","created":"2022-02-05","cited_by_count":2}],"next_cursor":null}