{"total":880,"rows":[{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439,"area":"agents"},{"id":"2310.03684","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","created":"2023-10-05","cited_by_count":469,"area":"safety"},{"id":"2209.07511","title":"Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models","created":"2022-09-15","cited_by_count":382,"area":"mllm"},{"id":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322,"area":"safety"},{"id":"2102.01356","title":"Recent Advances in Adversarial Training for Adversarial Robustness","created":"2021-02-02","cited_by_count":279,"area":null},{"id":"2110.09468","title":"Improving Robustness using Generated Data","created":"2021-10-18","cited_by_count":234,"area":null},{"id":"2304.07288","title":"Cross-Entropy Loss Functions: Theoretical Analysis and Applications","created":"2023-04-14","cited_by_count":210,"area":null},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207,"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":"2309.01446","title":"Open Sesame! Universal Black Box Jailbreaking of Large Language Models","created":"2023-09-04","cited_by_count":134,"area":"safety"},{"id":"2206.07758","title":"Reconstructing Training Data from Trained Neural Networks","created":"2022-06-15","cited_by_count":133,"area":null},{"id":"2112.05135","title":"PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures","created":"2021-12-09","cited_by_count":131,"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":"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":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118,"area":null},{"id":"2212.07016","title":"Understanding Zero-Shot Adversarial Robustness for Large-Scale Models","created":"2022-12-14","cited_by_count":117,"area":"mllm"},{"id":"2106.11230","title":"Can contrastive learning avoid shortcut solutions?","created":"2021-06-21","cited_by_count":114,"area":null},{"id":"2110.04301","title":"Salient ImageNet: How to discover spurious features in Deep Learning?","created":"2021-10-08","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":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93,"area":null},{"id":"2110.13771","title":"AugMax: Adversarial Composition of Random Augmentations for Robust Training","created":"2021-10-26","cited_by_count":90,"area":null},{"id":"2205.10268","title":"B-cos Networks: Alignment is All We Need for Interpretability","created":"2022-05-20","cited_by_count":88,"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":"2202.02643","title":"The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training","created":"2022-02-05","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":"2305.15241","title":"Robust Classification via a Single Diffusion Model","created":"2023-05-24","cited_by_count":79,"area":"diffusion"},{"id":"2110.07736","title":"Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP Models","created":"2021-10-14","cited_by_count":76,"area":null},{"id":"2106.02890","title":"Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?","created":"2021-06-05","cited_by_count":75,"area":null},{"id":"2105.14602","title":"On the geometry of generalization and memorization in deep neural networks","created":"2021-05-30","cited_by_count":73,"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":"2105.11417","title":"Skew Orthogonal Convolutions","created":"2021-05-24","cited_by_count":67,"area":null},{"id":"2204.03632","title":"The Effects of Regularization and Data Augmentation are Class Dependent","created":"2022-04-07","cited_by_count":67,"area":null},{"id":"2207.09944","title":"Probable Domain Generalization via Quantile Risk Minimization","created":"2022-07-20","cited_by_count":66,"area":null},{"id":"2305.10862","title":"How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses","created":"2023-05-18","cited_by_count":66,"area":null},{"id":"2105.02968","title":"This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networks","created":"2021-05-05","cited_by_count":65,"area":null},{"id":"2209.07399","title":"A Light Recipe to Train Robust Vision Transformers","created":"2022-09-15","cited_by_count":64,"area":null},{"id":"2502.03714","title":"Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment","created":"2025-02-06","cited_by_count":62,"area":"mechinterp"},{"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":"2405.16341","title":"R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model","created":"2024-05-25","cited_by_count":58,"area":"diffusion"},{"id":"2104.04448","title":"Relating Adversarially Robust Generalization to Flat Minima","created":"2021-04-09","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":"2111.09571","title":"Person Re-identification Method Based on Color Attack and Joint Defence","created":"2021-11-18","cited_by_count":56,"area":null},{"id":"2303.14460","title":"CFA: Class-wise Calibrated Fair Adversarial Training","created":"2023-03-25","cited_by_count":53,"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":"2102.06605","title":"Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning","created":"2021-02-12","cited_by_count":50,"area":null},{"id":"2101.06560","title":"Adversarial Attacks On Multi-Agent Communication","created":"2021-01-17","cited_by_count":49,"area":null},{"id":"2111.09277","title":"SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness","created":"2021-11-17","cited_by_count":49,"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":"2107.11400","title":"Robust Explainability: A Tutorial on Gradient-Based Attribution Methods for Deep Neural Networks","created":"2021-07-23","cited_by_count":48,"area":null},{"id":"2107.11630","title":"Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them","created":"2021-07-24","cited_by_count":48,"area":null},{"id":"2403.01849","title":"One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models","created":"2024-03-04","cited_by_count":48,"area":"mllm"},{"id":"2103.14222","title":"Adversarial Attacks are Reversible with Natural Supervision","created":"2021-03-26","cited_by_count":47,"area":null},{"id":"2104.09658","title":"Calibration and Consistency of Adversarial Surrogate Losses","created":"2021-04-19","cited_by_count":47,"area":null},{"id":"2108.04062","title":"Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100","created":"2021-08-05","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":"2408.14037","title":"Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learning","created":"2024-08-26","cited_by_count":47,"area":"offlinerl"},{"id":"2112.05588","title":"Copy, Right? A Testing Framework for Copyright Protection of Deep Learning Models","created":"2021-12-10","cited_by_count":46,"area":"safety"},{"id":"2206.03693","title":"Autoregressive Perturbations for Data Poisoning","created":"2022-06-08","cited_by_count":46,"area":"safety"},{"id":"2207.01164","title":"Aug-NeRF: Training Stronger Neural Radiance Fields with Triple-Level Physically-Grounded Augmentations","created":"2022-07-04","cited_by_count":46,"area":null},{"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":"2106.14851","title":"Data Poisoning Won't Save You From Facial Recognition","created":"2021-06-28","cited_by_count":45,"area":"safety"},{"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":"2305.18761","title":"Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias","created":"2023-05-30","cited_by_count":44,"area":null},{"id":"2207.03162","title":"Harnessing Out-Of-Distribution Examples via Augmenting Content and Style","created":"2022-07-07","cited_by_count":43,"area":null},{"id":"2306.14321","title":"RobuT: A Systematic Study of Table QA Robustness Against Human-Annotated Adversarial Perturbations","created":"2023-06-25","cited_by_count":43,"area":null},{"id":"2307.10562","title":"Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples","created":"2023-07-20","cited_by_count":43,"area":null},{"id":"2103.04623","title":"Consistency Regularization for Adversarial Robustness","created":"2021-03-08","cited_by_count":42,"area":null},{"id":"2103.05134","title":"Constrained Learning with Non-Convex Losses","created":"2021-03-08","cited_by_count":42,"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":"2207.04153","title":"Probing Classifiers are Unreliable for Concept Removal and Detection","created":"2022-07-08","cited_by_count":41,"area":null},{"id":"2212.04871","title":"Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet","created":"2022-12-09","cited_by_count":41,"area":null},{"id":"2108.01634","title":"Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation","created":"2021-08-03","cited_by_count":40,"area":null},{"id":"2112.13547","title":"PRIME: A few primitives can boost robustness to common corruptions","created":"2021-12-27","cited_by_count":40,"area":null},{"id":"2203.06768","title":"Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse","created":"2022-03-13","cited_by_count":40,"area":null},{"id":"2105.06625","title":"Biometrics: Trust, but Verify","created":"2021-05-14","cited_by_count":39,"area":null},{"id":"2109.07986","title":"Harnessing Perceptual Adversarial Patches for Crowd Counting","created":"2021-09-16","cited_by_count":39,"area":null},{"id":"2110.15767","title":"Adversarial Robustness with Semi-Infinite Constrained Learning","created":"2021-10-29","cited_by_count":39,"area":null},{"id":"2111.15121","title":"Pyramid Adversarial Training Improves ViT Performance","created":"2021-11-30","cited_by_count":39,"area":null},{"id":"2203.14195","title":"How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective","created":"2022-03-27","cited_by_count":39,"area":null},{"id":"2301.13694","title":"Are Defenses for Graph Neural Networks Robust?","created":"2023-01-31","cited_by_count":38,"area":null},{"id":"2202.01136","title":"Probabilistically Robust Learning: Balancing Average- and Worst-case Performance","created":"2022-02-02","cited_by_count":37,"area":null},{"id":"2206.07438","title":"Multi-Objective Hyperparameter Optimization in Machine Learning -- An Overview","created":"2022-06-15","cited_by_count":37,"area":null},{"id":"2210.12873","title":"FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning","created":"2022-10-23","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":"2310.14772","title":"Predictor-Rejector Multi-Class Abstention: Theoretical Analysis and Algorithms","created":"2023-10-23","cited_by_count":36,"area":null},{"id":"2104.01396","title":"Neural Network Robustness as a Verification Property: A Principled Case Study","created":"2021-04-03","cited_by_count":35,"area":null},{"id":"2110.10942","title":"Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness","created":"2021-10-21","cited_by_count":35,"area":null},{"id":"2203.09747","title":"Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization","created":"2022-03-18","cited_by_count":35,"area":null},{"id":"2106.02105","title":"A Little Robustness Goes a Long Way: Leveraging Robust Features for Targeted Transfer Attacks","created":"2021-06-03","cited_by_count":34,"area":null},{"id":"2107.11228","title":"Taxonomizing local versus global structure in neural network loss landscapes","created":"2021-07-23","cited_by_count":34,"area":null},{"id":"2207.08977","title":"Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift","created":"2022-07-18","cited_by_count":34,"area":null},{"id":"2305.19753","title":"The Tunnel Effect: Building Data Representations in Deep Neural Networks","created":"2023-05-31","cited_by_count":34,"area":null},{"id":"2104.02466","title":"A Review of Formal Methods applied to Machine Learning","created":"2021-04-06","cited_by_count":33,"area":null},{"id":"2208.08664","title":"Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidance","created":"2022-08-18","cited_by_count":33,"area":"diffusion"},{"id":"2106.04938","title":"Attacking Adversarial Attacks as A Defense","created":"2021-06-09","cited_by_count":32,"area":null},{"id":"2108.10879","title":"Are socially-aware trajectory prediction models really socially-aware?","created":"2021-08-24","cited_by_count":32,"area":null}],"next_cursor":"100"}