{"total":292,"rows":[{"id":"2210.11466","title":"Surgical Fine-Tuning Improves Adaptation to Distribution Shifts","created":"2022-10-20","cited_by_count":205,"area":null},{"id":"2106.07411","title":"Partial success in closing the gap between human and machine vision","created":"2021-06-14","cited_by_count":185,"area":null},{"id":"2211.15583","title":"On the Effectiveness of Parameter-Efficient Fine-Tuning","created":"2022-11-28","cited_by_count":141,"area":null},{"id":"2305.06329","title":"Similarity of Neural Network Models: A Survey of Functional and Representational Measures","created":"2023-05-10","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":"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":"2204.00008","title":"Improving Adversarial Transferability via Neuron Attribution-Based Attacks","created":"2022-03-31","cited_by_count":93,"area":null},{"id":"2303.09105","title":"Rethinking Model Ensemble in Transfer-based Adversarial Attacks","created":"2023-03-16","cited_by_count":89,"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":"2303.01870","title":"Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models","created":"2023-03-03","cited_by_count":79,"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":"2210.05968","title":"Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation","created":"2022-10-12","cited_by_count":68,"area":null},{"id":"2105.11144","title":"Improved OOD Generalization via Adversarial Training and Pre-training","created":"2021-05-24","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":"2305.16494","title":"Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability","created":"2023-05-25","cited_by_count":66,"area":null},{"id":"2103.14641","title":"On Generating Transferable Targeted Perturbations","created":"2021-03-26","cited_by_count":65,"area":null},{"id":"2303.09051","title":"Robust Evaluation of Diffusion-Based Adversarial Purification","created":"2023-03-16","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":"2305.06386","title":"Text-To-Concept (and Back) via Cross-Model Alignment","created":"2023-05-10","cited_by_count":64,"area":null},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61,"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":"2211.04533","title":"Harmonizing the object recognition strategies of deep neural networks with humans","created":"2022-11-08","cited_by_count":59,"area":null},{"id":"2201.05867","title":"Transferability in Deep Learning: A Survey","created":"2022-01-15","cited_by_count":57,"area":null},{"id":"2102.12781","title":"Do Input Gradients Highlight Discriminative Features?","created":"2021-02-25","cited_by_count":52,"area":null},{"id":"2111.13445","title":"How Well Do Sparse Imagenet Models Transfer?","created":"2021-11-26","cited_by_count":50,"area":null},{"id":"2210.03895","title":"ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpoints","created":"2022-10-08","cited_by_count":48,"area":null},{"id":"2210.04200","title":"Boosting Out-of-distribution Detection with Typical Features","created":"2022-10-09","cited_by_count":48,"area":null},{"id":"2308.16258","title":"Robust Principles: Architectural Design Principles for Adversarially Robust CNNs","created":"2023-08-30","cited_by_count":46,"area":null},{"id":"2106.09362","title":"Frustratingly Easy Transferability Estimation","created":"2021-06-17","cited_by_count":45,"area":null},{"id":"2111.04578","title":"Improved Regularization and Robustness for Fine-tuning in Neural Networks","created":"2021-11-08","cited_by_count":45,"area":null},{"id":"2203.05154","title":"Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack","created":"2022-03-10","cited_by_count":44,"area":null},{"id":"2105.02221","title":"How Fine-Tuning Allows for Effective Meta-Learning","created":"2021-05-05","cited_by_count":41,"area":null},{"id":"2210.04213","title":"Towards Understanding and Boosting Adversarial Transferability from a Distribution Perspective","created":"2022-10-09","cited_by_count":37,"area":null},{"id":"2106.10189","title":"Adversarial Training Helps Transfer Learning via Better Representations","created":"2021-06-18","cited_by_count":36,"area":null},{"id":"2110.05922","title":"Trivial or impossible -- dichotomous data difficulty masks model differences (on ImageNet and beyond)","created":"2021-10-12","cited_by_count":35,"area":null},{"id":"2301.04644","title":"Does progress on ImageNet transfer to real-world datasets?","created":"2023-01-11","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":"2212.05630","title":"DISCO: Adversarial Defense with Local Implicit Functions","created":"2022-12-11","cited_by_count":34,"area":null},{"id":"2207.05739","title":"A Data-Based Perspective on Transfer Learning","created":"2022-07-12","cited_by_count":32,"area":null},{"id":"2306.04719","title":"Don't trust your eyes: on the (un)reliability of feature visualizations","created":"2023-06-07","cited_by_count":32,"area":null},{"id":"2307.07873","title":"Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability","created":"2023-07-15","cited_by_count":32,"area":null},{"id":"2303.17096","title":"ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing","created":"2023-03-30","cited_by_count":30,"area":null},{"id":"2102.10454","title":"On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning","created":"2021-02-20","cited_by_count":29,"area":null},{"id":"2204.00491","title":"FrequencyLowCut Pooling -- Plug & Play against Catastrophic Overfitting","created":"2022-04-01","cited_by_count":28,"area":null},{"id":"2309.13190","title":"Spatial-frequency channels, shape bias, and adversarial robustness","created":"2023-09-22","cited_by_count":28,"area":null},{"id":"2110.03605","title":"Robust Feature-Level Adversaries are Interpretability Tools","created":"2021-10-07","cited_by_count":27,"area":null},{"id":"2203.04412","title":"ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patches","created":"2022-03-07","cited_by_count":27,"area":null},{"id":"2210.05938","title":"Robust Models are less Over-Confident","created":"2022-10-12","cited_by_count":25,"area":null},{"id":"2307.12532","title":"On the Connection between Pre-training Data Diversity and Fine-tuning Robustness","created":"2023-07-24","cited_by_count":25,"area":null},{"id":"2109.00946","title":"Adversarial Robustness for Unsupervised Domain Adaptation","created":"2021-09-02","cited_by_count":24,"area":null},{"id":"2212.12206","title":"Understanding and Improving Transfer Learning of Deep Models via Neural Collapse","created":"2022-12-23","cited_by_count":24,"area":null},{"id":"2207.02842","title":"When does Bias Transfer in Transfer Learning?","created":"2022-07-06","cited_by_count":23,"area":null},{"id":"2207.07065","title":"On the Strong Correlation Between Model Invariance and Generalization","created":"2022-07-14","cited_by_count":23,"area":null},{"id":"2209.07735","title":"Enhance the Visual Representation via Discrete Adversarial Training","created":"2022-09-16","cited_by_count":23,"area":null},{"id":"2308.02533","title":"Improving Generalization of Adversarial Training via Robust Critical Fine-Tuning","created":"2023-08-01","cited_by_count":23,"area":null},{"id":"2207.13247","title":"Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation","created":"2022-07-27","cited_by_count":21,"area":null},{"id":"2103.08187","title":"Adversarial Training is Not Ready for Robot Learning","created":"2021-03-15","cited_by_count":20,"area":null},{"id":"2203.15331","title":"CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters","created":"2022-03-29","cited_by_count":20,"area":null},{"id":"2204.03934","title":"Does Robustness on ImageNet Transfer to Downstream Tasks?","created":"2022-04-08","cited_by_count":20,"area":null},{"id":"2206.03198","title":"Explaining the physics of transfer learning a data-driven subgrid-scale closure to a different turbulent flow","created":"2022-06-07","cited_by_count":20,"area":null},{"id":"2209.07592","title":"Explicit Tradeoffs between Adversarial and Natural Distributional Robustness","created":"2022-09-15","cited_by_count":20,"area":null},{"id":"2305.19101","title":"Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness","created":"2023-05-30","cited_by_count":20,"area":null},{"id":"2404.01509","title":"Can Biases in ImageNet Models Explain Generalization?","created":"2024-04-01","cited_by_count":20,"area":null},{"id":"2103.14577","title":"Unsupervised Robust Domain Adaptation without Source Data","created":"2021-03-26","cited_by_count":19,"area":null},{"id":"2104.08313","title":"Does language help generalization in vision models?","created":"2021-04-16","cited_by_count":19,"area":null},{"id":"2205.12134","title":"Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attacks","created":"2022-05-24","cited_by_count":19,"area":null},{"id":"2307.10235","title":"Towards Viewpoint-Invariant Visual Recognition via Adversarial Training","created":"2023-07-16","cited_by_count":19,"area":null},{"id":"2303.11135","title":"TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization","created":"2023-03-20","cited_by_count":18,"area":null},{"id":"2306.03779","title":"Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex","created":"2023-06-06","cited_by_count":18,"area":null},{"id":"2111.03536","title":"A Unified Game-Theoretic Interpretation of Adversarial Robustness","created":"2021-11-05","cited_by_count":17,"area":null},{"id":"2202.01263","title":"NoisyMix: Boosting Model Robustness to Common Corruptions","created":"2022-02-02","cited_by_count":17,"area":null},{"id":"2206.05259","title":"Is Self-Supervised Learning More Robust Than Supervised Learning?","created":"2022-06-10","cited_by_count":17,"area":null},{"id":"2210.15909","title":"Subsidiary Prototype Alignment for Universal Domain Adaptation","created":"2022-10-28","cited_by_count":17,"area":null},{"id":"2202.10627","title":"On the Effectiveness of Adversarial Training against Backdoor Attacks","created":"2022-02-22","cited_by_count":16,"area":null},{"id":"2305.16316","title":"Making Vision Transformers Truly Shift-Equivariant","created":"2023-05-25","cited_by_count":16,"area":null},{"id":"2311.15551","title":"Instruct2Attack: Language-Guided Semantic Adversarial Attacks","created":"2023-11-27","cited_by_count":16,"area":null},{"id":"2203.15566","title":"Core Risk Minimization using Salient ImageNet","created":"2022-03-28","cited_by_count":15,"area":null},{"id":"2211.09565","title":"Towards Good Practices in Evaluating Transfer Adversarial Attacks","created":"2022-11-17","cited_by_count":15,"area":null},{"id":"2210.12030","title":"Evolution of Neural Tangent Kernels under Benign and Adversarial Training","created":"2022-10-21","cited_by_count":14,"area":null},{"id":"2212.09035","title":"Minimizing Maximum Model Discrepancy for Transferable Black-box Targeted Attacks","created":"2022-12-18","cited_by_count":14,"area":null},{"id":"2302.03857","title":"Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection","created":"2023-02-08","cited_by_count":14,"area":null},{"id":"2306.02595","title":"Explore and Exploit the Diverse Knowledge in Model Zoo for Domain Generalization","created":"2023-06-05","cited_by_count":14,"area":null},{"id":"2309.12821","title":"A Spectral Theory of Neural Prediction and Alignment","created":"2023-09-22","cited_by_count":14,"area":null},{"id":"2404.19460","title":"AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples","created":"2024-04-30","cited_by_count":14,"area":null},{"id":"2106.09534","title":"Adversarial Visual Robustness by Causal Intervention","created":"2021-06-17","cited_by_count":13,"area":null},{"id":"2111.02331","title":"LTD: Low Temperature Distillation for Gradient Masking-free Adversarial Training","created":"2021-11-03","cited_by_count":13,"area":null},{"id":"2201.12765","title":"Improving Robustness by Enhancing Weak Subnets","created":"2022-01-30","cited_by_count":13,"area":null},{"id":"2211.15929","title":"Backdoor Vulnerabilities in Normally Trained Deep Learning Models","created":"2022-11-29","cited_by_count":13,"area":null},{"id":"2212.02648","title":"Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases","created":"2022-12-05","cited_by_count":13,"area":null},{"id":"2302.04852","title":"SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks","created":"2023-02-09","cited_by_count":13,"area":null},{"id":"2308.15499","title":"Classification robustness to common optical aberrations","created":"2023-08-29","cited_by_count":13,"area":null},{"id":"2508.17456","title":"Adversarial Examples Are Not Bugs, They Are Superposition","created":"2025-08-24","cited_by_count":13,"area":null},{"id":"2110.08220","title":"Combining Diverse Feature Priors","created":"2021-10-15","cited_by_count":12,"area":null},{"id":"2210.09236","title":"ZooD: Exploiting Model Zoo for Out-of-Distribution Generalization","created":"2022-10-17","cited_by_count":12,"area":null},{"id":"2301.12576","title":"Uncovering Adversarial Risks of Test-Time Adaptation","created":"2023-01-29","cited_by_count":12,"area":null},{"id":"2305.17438","title":"On the Importance of Backbone to the Adversarial Robustness of Object Detectors","created":"2023-05-27","cited_by_count":12,"area":null},{"id":"2306.12941","title":"Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models","created":"2023-06-22","cited_by_count":12,"area":null},{"id":"2307.11823","title":"HybridAugment++: Unified Frequency Spectra Perturbations for Model Robustness","created":"2023-07-21","cited_by_count":12,"area":null},{"id":"2103.07470","title":"Understanding Invariance via Feedforward Inversion of Discriminatively Trained Classifiers","created":"2021-03-15","cited_by_count":11,"area":null}],"next_cursor":"100"}