{"total":953,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744,"area":"wm"},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104,"area":"alignment"},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802,"area":null},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"id":"2305.16934","title":"On Evaluating Adversarial Robustness of Large Vision-Language Models","created":"2023-05-26","cited_by_count":284,"area":"mllm"},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283,"area":null},{"id":"2102.01356","title":"Recent Advances in Adversarial Training for Adversarial Robustness","created":"2021-02-02","cited_by_count":279,"area":null},{"id":"2107.13034","title":"Dataset Distillation with Infinitely Wide Convolutional Networks","created":"2021-07-27","cited_by_count":218,"area":null},{"id":"2302.12095","title":"On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective","created":"2023-02-22","cited_by_count":211,"area":null},{"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":"2101.04898","title":"Unlearnable Examples: Making Personal Data Unexploitable","created":"2021-01-13","cited_by_count":193,"area":null},{"id":"2202.00622","title":"Datamodels: Predicting Predictions from Training Data","created":"2022-02-01","cited_by_count":189,"area":null},{"id":"2306.09301","title":"OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detection","created":"2023-06-15","cited_by_count":179,"area":null},{"id":"2310.01469","title":"LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples","created":"2023-10-02","cited_by_count":177,"area":null},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176,"area":null},{"id":"2106.15590","title":"The Values Encoded in Machine Learning Research","created":"2021-06-29","cited_by_count":172,"area":null},{"id":"2110.14051","title":"A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges","created":"2021-10-26","cited_by_count":154,"area":null},{"id":"2408.15221","title":"LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet","created":"2024-08-27","cited_by_count":151,"area":"safety"},{"id":"2411.00816","title":"CycleResearcher: Improving Automated Research via Automated Review","created":"2024-10-28","cited_by_count":148,"area":null},{"id":"2103.08896","title":"Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation","created":"2021-03-16","cited_by_count":134,"area":null},{"id":"2105.14368","title":"Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation","created":"2021-05-29","cited_by_count":132,"area":null},{"id":"2104.11315","title":"SPECTRE: Defending Against Backdoor Attacks Using Robust Statistics","created":"2021-04-22","cited_by_count":130,"area":null},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129,"area":null},{"id":"2103.01050","title":"Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical World","created":"2021-03-01","cited_by_count":127,"area":null},{"id":"2107.14185","title":"Feature Importance-aware Transferable Adversarial Attacks","created":"2021-07-29","cited_by_count":127,"area":null},{"id":"2108.00401","title":"Advances in adversarial attacks and defenses in computer vision: A survey","created":"2021-08-01","cited_by_count":127,"area":null},{"id":"2105.14111","title":"Goal Misgeneralization in Deep Reinforcement Learning","created":"2021-05-28","cited_by_count":123,"area":null},{"id":"2106.10807","title":"Adversarial Examples Make Strong Poisons","created":"2021-06-21","cited_by_count":119,"area":null},{"id":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118,"area":null},{"id":"2106.11230","title":"Can contrastive learning avoid shortcut solutions?","created":"2021-06-21","cited_by_count":114,"area":null},{"id":"2202.10103","title":"Robustness and Accuracy Could Be Reconcilable by (Proper) Definition","created":"2022-02-21","cited_by_count":111,"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":"2103.15670","title":"On the Adversarial Robustness of Vision Transformers","created":"2021-03-29","cited_by_count":106,"area":null},{"id":"2306.04618","title":"Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations","created":"2023-06-07","cited_by_count":97,"area":null},{"id":"2401.08573","title":"WAVES: Benchmarking the Robustness of Image Watermarks","created":"2024-01-16","cited_by_count":97,"area":null},{"id":"2103.00887","title":"Counterfactual Zero-Shot and Open-Set Visual Recognition","created":"2021-03-01","cited_by_count":95,"area":null},{"id":"2203.06616","title":"LAS-AT: Adversarial Training with Learnable Attack Strategy","created":"2022-03-13","cited_by_count":95,"area":null},{"id":"2507.14805","title":"Subliminal Learning: Language models transmit behavioral traits via hidden signals in data","created":"2025-07-20","cited_by_count":95,"area":null},{"id":"2405.13954","title":"What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions","created":"2024-05-22","cited_by_count":94,"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":"2403.05030","title":"Defending Against Unforeseen Failure Modes with Latent Adversarial Training","created":"2024-03-08","cited_by_count":88,"area":"safety"},{"id":"2208.11857","title":"Shortcut Learning of Large Language Models in Natural Language Understanding","created":"2022-08-25","cited_by_count":85,"area":null},{"id":"2302.14301","title":"A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking","created":"2023-02-28","cited_by_count":85,"area":null},{"id":"2105.04857","title":"Leveraging Sparse Linear Layers for Debuggable Deep Networks","created":"2021-05-11","cited_by_count":82,"area":null},{"id":"2108.08782","title":"Causal Attention for Unbiased Visual Recognition","created":"2021-08-19","cited_by_count":80,"area":null},{"id":"2108.07969","title":"Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better","created":"2021-08-18","cited_by_count":79,"area":"distill"},{"id":"2103.06922","title":"Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models","created":"2021-03-11","cited_by_count":78,"area":null},{"id":"2405.05967","title":"Distilling Diffusion Models into Conditional GANs","created":"2024-05-09","cited_by_count":78,"area":"diffusion"},{"id":"2103.08307","title":"Improving Adversarial Robustness via Channel-wise Activation Suppressing","created":"2021-03-11","cited_by_count":76,"area":null},{"id":"2110.03825","title":"Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks","created":"2021-10-07","cited_by_count":74,"area":null},{"id":"2103.02325","title":"On the effectiveness of adversarial training against common corruptions","created":"2021-03-03","cited_by_count":71,"area":null},{"id":"2104.03149","title":"Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering","created":"2021-04-07","cited_by_count":71,"area":null},{"id":"2108.08487","title":"Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain","created":"2021-08-19","cited_by_count":71,"area":null},{"id":"2110.03051","title":"Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation","created":"2021-10-06","cited_by_count":71,"area":null},{"id":"2201.08531","title":"Black-box Prompt Learning for Pre-trained Language Models","created":"2022-01-21","cited_by_count":70,"area":null},{"id":"2202.04414","title":"Agree to Disagree: Diversity through Disagreement for Better Transferability","created":"2022-02-09","cited_by_count":70,"area":null},{"id":"2305.17256","title":"Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning","created":"2023-05-26","cited_by_count":69,"area":null},{"id":"2301.11578","title":"Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers","created":"2023-01-27","cited_by_count":67,"area":"safety"},{"id":"2103.14641","title":"On Generating Transferable Targeted Perturbations","created":"2021-03-26","cited_by_count":65,"area":null},{"id":"2111.00956","title":"Robot Learning from Randomized Simulations: A Review","created":"2021-11-01","cited_by_count":63,"area":null},{"id":"2107.08221","title":"Visual Representation Learning Does Not Generalize Strongly Within the Same Domain","created":"2021-07-17","cited_by_count":61,"area":null},{"id":"2101.11073","title":"Property Inference From Poisoning","created":"2021-01-26","cited_by_count":60,"area":null},{"id":"2205.01663","title":"Adversarial Training for High-Stakes Reliability","created":"2022-05-03","cited_by_count":60,"area":null},{"id":"2102.04716","title":"Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training","created":"2021-02-09","cited_by_count":59,"area":null},{"id":"2103.01498","title":"A Survey On Universal Adversarial Attack","created":"2021-03-02","cited_by_count":59,"area":null},{"id":"2204.06974","title":"Planting Undetectable Backdoors in Machine Learning Models","created":"2022-04-14","cited_by_count":59,"area":null},{"id":"2110.12899","title":"No One Representation to Rule Them All: Overlapping Features of Training Methods","created":"2021-10-20","cited_by_count":58,"area":null},{"id":"2105.03743","title":"Certified Robustness to Text Adversarial Attacks by Randomized [MASK]","created":"2021-05-08","cited_by_count":57,"area":null},{"id":"2106.07904","title":"Probabilistic Margins for Instance Reweighting in Adversarial Training","created":"2021-06-15","cited_by_count":57,"area":null},{"id":"2110.02797","title":"Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs","created":"2021-10-06","cited_by_count":57,"area":null},{"id":"2506.19676","title":"A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures","created":"2025-06-24","cited_by_count":57,"area":"agents"},{"id":"2106.04928","title":"Reliable Adversarial Distillation with Unreliable Teachers","created":"2021-06-09","cited_by_count":56,"area":"distill"},{"id":"2108.09034","title":"AdvDrop: Adversarial Attack to DNNs by Dropping Information","created":"2021-08-20","cited_by_count":56,"area":null},{"id":"2105.06422","title":"Causally motivated Shortcut Removal Using Auxiliary Labels","created":"2021-05-13","cited_by_count":55,"area":null},{"id":"2102.12781","title":"Do Input Gradients Highlight Discriminative Features?","created":"2021-02-25","cited_by_count":52,"area":null},{"id":"2105.00203","title":"Adversarial Example Detection for DNN Models: A Review and Experimental Comparison","created":"2021-05-01","cited_by_count":52,"area":null},{"id":"2210.04871","title":"Certified Training: Small Boxes are All You Need","created":"2022-10-10","cited_by_count":52,"area":null},{"id":"2206.10843","title":"Learning Debiased Classifier with Biased Committee","created":"2022-06-22","cited_by_count":51,"area":null},{"id":"2402.15555","title":"Deep Networks Always Grok and Here is Why","created":"2024-02-23","cited_by_count":51,"area":null},{"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":"2110.15255","title":"Self-Supervised Learning Disentangled Group Representation as Feature","created":"2021-10-28","cited_by_count":47,"area":null},{"id":"2303.09962","title":"Adversarial Counterfactual Visual Explanations","created":"2023-03-17","cited_by_count":47,"area":"diffusion"},{"id":"2206.03693","title":"Autoregressive Perturbations for Data Poisoning","created":"2022-06-08","cited_by_count":46,"area":"safety"},{"id":"2101.06784","title":"Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Driving","created":"2021-01-17","cited_by_count":45,"area":null},{"id":"2105.01622","title":"Poisoning the Unlabeled Dataset of Semi-Supervised Learning","created":"2021-05-04","cited_by_count":44,"area":null},{"id":"2203.14046","title":"A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologies","created":"2022-03-26","cited_by_count":44,"area":null},{"id":"2310.17626","title":"A Survey on Transferability of Adversarial Examples across Deep Neural Networks","created":"2023-10-26","cited_by_count":44,"area":null},{"id":"2106.03734","title":"Reveal of Vision Transformers Robustness against Adversarial Attacks","created":"2021-06-07","cited_by_count":43,"area":null},{"id":"2103.08951","title":"Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties","created":"2021-03-16","cited_by_count":41,"area":null},{"id":"2106.10151","title":"The Dimpled Manifold Model of Adversarial Examples in Machine Learning","created":"2021-06-18","cited_by_count":41,"area":null},{"id":"2206.01161","title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","created":"2022-06-02","cited_by_count":41,"area":null},{"id":"2209.15266","title":"Data Poisoning Attacks Against Multimodal Encoders","created":"2022-09-30","cited_by_count":41,"area":"safety"},{"id":"2211.05568","title":"Unbiased Supervised Contrastive Learning","created":"2022-11-10","cited_by_count":40,"area":null},{"id":"2104.00671","title":"TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness","created":"2021-04-01","cited_by_count":38,"area":null},{"id":"2202.00132","title":"Submodularity In Machine Learning and Artificial Intelligence","created":"2022-01-31","cited_by_count":38,"area":null},{"id":"2106.06196","title":"CausalAdv: Adversarial Robustness through the Lens of Causality","created":"2021-06-11","cited_by_count":37,"area":null},{"id":"2110.03109","title":"Consistent Counterfactuals for Deep Models","created":"2021-10-06","cited_by_count":37,"area":null},{"id":"2107.10171","title":"Leave-one-out Unfairness","created":"2021-07-21","cited_by_count":36,"area":null},{"id":"2108.00049","title":"Object-aware Contrastive Learning for Debiased Scene Representation","created":"2021-07-30","cited_by_count":35,"area":null},{"id":"2203.14533","title":"Robust Unlearnable Examples: Protecting Data Against Adversarial Learning","created":"2022-03-28","cited_by_count":35,"area":null}],"next_cursor":"100"}