{"total":125,"rows":[{"id":"2304.07288","title":"Cross-Entropy Loss Functions: Theoretical Analysis and Applications","created":"2023-04-14","cited_by_count":210,"area":null},{"id":"2106.05945","title":"Does Knowledge Distillation Really Work?","created":"2021-06-10","cited_by_count":190,"area":"distill"},{"id":"2106.10807","title":"Adversarial Examples Make Strong Poisons","created":"2021-06-21","cited_by_count":119,"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":"2110.03825","title":"Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks","created":"2021-10-07","cited_by_count":74,"area":null},{"id":"2203.08124","title":"Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective","created":"2022-03-15","cited_by_count":57,"area":null},{"id":"2106.04928","title":"Reliable Adversarial Distillation with Unreliable Teachers","created":"2021-06-09","cited_by_count":56,"area":"distill"},{"id":"2104.09732","title":"Knowledge Distillation as Semiparametric Inference","created":"2021-04-20","cited_by_count":29,"area":"distill"},{"id":"2201.06192","title":"Fooling the Eyes of Autonomous Vehicles: Robust Physical Adversarial Examples Against Traffic Sign Recognition Systems","created":"2022-01-17","cited_by_count":27,"area":null},{"id":"2205.16004","title":"What Knowledge Gets Distilled in Knowledge Distillation?","created":"2022-05-31","cited_by_count":27,"area":"distill"},{"id":"2308.04268","title":"Teacher-Student Architecture for Knowledge Distillation: A Survey","created":"2023-08-08","cited_by_count":26,"area":"distill"},{"id":"2504.13146","title":"Antidistillation Sampling","created":"2025-04-17","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":"2201.08542","title":"Can Model Compression Improve NLP Fairness","created":"2022-01-21","cited_by_count":20,"area":null},{"id":"2203.07159","title":"On the benefits of knowledge distillation for adversarial robustness","created":"2022-03-14","cited_by_count":18,"area":"distill"},{"id":"2204.09975","title":"Eliminating Backdoor Triggers for Deep Neural Networks Using Attention Relation Graph Distillation","created":"2022-04-21","cited_by_count":18,"area":null},{"id":"2112.05005","title":"Mutual Adversarial Training: Learning together is better than going alone","created":"2021-12-09","cited_by_count":17,"area":null},{"id":"2303.14133","title":"Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challenges","created":"2023-03-24","cited_by_count":17,"area":null},{"id":"2110.12072","title":"How and When Adversarial Robustness Transfers in Knowledge Distillation?","created":"2021-10-22","cited_by_count":16,"area":"distill"},{"id":"2306.16170","title":"Mitigating Accuracy-Robustness Trade-off via Balanced Multi-Teacher Adversarial Distillation","created":"2023-06-28","cited_by_count":13,"area":null},{"id":"2210.04311","title":"Pruning Adversarially Robust Neural Networks without Adversarial Examples","created":"2022-10-09","cited_by_count":12,"area":null},{"id":"2211.01671","title":"Visual Adversarial Attacks and Defenses in the Physical World: A Survey","created":"2022-11-03","cited_by_count":11,"area":null},{"id":"2306.08805","title":"Exact Count of Boundary Pieces of ReLU Classifiers: Towards the Proper Complexity Measure for Classification","created":"2023-06-15","cited_by_count":11,"area":null},{"id":"2111.05073","title":"MixACM: Mixup-Based Robustness Transfer via Distillation of Activated Channel Maps","created":"2021-11-09","cited_by_count":9,"area":null},{"id":"2205.00706","title":"FedDKD: Federated Learning with Decentralized Knowledge Distillation","created":"2022-05-02","cited_by_count":9,"area":"distill"},{"id":"2210.08906","title":"A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities","created":"2022-10-17","cited_by_count":9,"area":null},{"id":"2302.08764","title":"Adversarial Contrastive Distillation with Adaptive Denoising","created":"2023-02-17","cited_by_count":9,"area":null},{"id":"2306.14126","title":"Robust Spatiotemporal Traffic Forecasting with Reinforced Dynamic Adversarial Training","created":"2023-06-25","cited_by_count":9,"area":null},{"id":"2311.01441","title":"Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models","created":"2023-11-02","cited_by_count":9,"area":"mllm"},{"id":"2403.09101","title":"Soften to Defend: Towards Adversarial Robustness via Self-Guided Label Refinement","created":"2024-03-14","cited_by_count":9,"area":null},{"id":"2312.05508","title":"Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation","created":"2023-12-09","cited_by_count":8,"area":null},{"id":"2403.13322","title":"DD-RobustBench: An Adversarial Robustness Benchmark for Dataset Distillation","created":"2024-03-20","cited_by_count":8,"area":null},{"id":"2104.00322","title":"Domain Invariant Adversarial Learning","created":"2021-04-01","cited_by_count":7,"area":null},{"id":"2202.09994","title":"Transferring Adversarial Robustness Through Robust Representation Matching","created":"2022-02-21","cited_by_count":7,"area":null},{"id":"2210.14283","title":"Accelerating Certified Robustness Training via Knowledge Transfer","created":"2022-10-25","cited_by_count":7,"area":null},{"id":"2303.11611","title":"Out of Thin Air: Exploring Data-Free Adversarial Robustness Distillation","created":"2023-03-21","cited_by_count":7,"area":null},{"id":"2305.12118","title":"Annealing Self-Distillation Rectification Improves Adversarial Training","created":"2023-05-20","cited_by_count":7,"area":"distill"},{"id":"2403.06668","title":"PeerAiD: Improving Adversarial Distillation from a Specialized Peer Tutor","created":"2024-03-11","cited_by_count":7,"area":"distill"},{"id":"2312.03286","title":"Indirect Gradient Matching for Adversarial Robust Distillation","created":"2023-12-06","cited_by_count":6,"area":null},{"id":"2312.05924","title":"Data-Free Hard-Label Robustness Stealing Attack","created":"2023-12-10","cited_by_count":6,"area":null},{"id":"2401.14948","title":"Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Training","created":"2024-01-26","cited_by_count":6,"area":null},{"id":"2410.15042","title":"Adversarial Training: A Survey","created":"2024-10-19","cited_by_count":6,"area":null},{"id":"2411.15244","title":"Adversarial Prompt Distillation for Vision-Language Models","created":"2024-11-22","cited_by_count":6,"area":"mllm"},{"id":"2201.00111","title":"Role of Data Augmentation Strategies in Knowledge Distillation for Wearable Sensor Data","created":"2022-01-01","cited_by_count":5,"area":"distill"},{"id":"2310.02480","title":"Splitting the Difference on Adversarial Training","created":"2023-10-03","cited_by_count":5,"area":null},{"id":"2404.03340","title":"Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks","created":"2024-04-04","cited_by_count":5,"area":null},{"id":"2405.20876","title":"Investigating Calibration and Corruption Robustness of Post-hoc Pruned Perception CNNs: An Image Classification Benchmark Study","created":"2024-05-31","cited_by_count":5,"area":null},{"id":"2409.01627","title":"Dynamic Guidance Adversarial Distillation with Enhanced Teacher Knowledge","created":"2024-09-03","cited_by_count":5,"area":"distill"},{"id":"2501.15014","title":"On Accelerating Edge AI: Optimizing Resource-Constrained Environments","created":"2025-01-25","cited_by_count":5,"area":null},{"id":"2503.06461","title":"Long-tailed Adversarial Training with Self-Distillation","created":"2025-03-09","cited_by_count":5,"area":"distill"},{"id":"2104.00233","title":"Unsupervised Domain Expansion for Visual Categorization","created":"2021-04-01","cited_by_count":4,"area":"distill"},{"id":"2110.06802","title":"Identification of Attack-Specific Signatures in Adversarial Examples","created":"2021-10-13","cited_by_count":4,"area":null},{"id":"2206.07842","title":"Queried Unlabeled Data Improves and Robustifies Class-Incremental Learning","created":"2022-06-15","cited_by_count":4,"area":null},{"id":"2210.11728","title":"Distilling the Undistillable: Learning from a Nasty Teacher","created":"2022-10-21","cited_by_count":4,"area":"distill"},{"id":"2210.14410","title":"Improving Adversarial Robustness via Joint Classification and Multiple Explicit Detection Classes","created":"2022-10-26","cited_by_count":4,"area":null},{"id":"2303.00250","title":"Combating Exacerbated Heterogeneity for Robust Models in Federated Learning","created":"2023-03-01","cited_by_count":4,"area":null},{"id":"2306.03430","title":"Revisiting the Trade-off between Accuracy and Robustness via Weight Distribution of Filters","created":"2023-06-06","cited_by_count":4,"area":null},{"id":"2309.04650","title":"Exploring Robust Features for Improving Adversarial Robustness","created":"2023-09-09","cited_by_count":4,"area":null},{"id":"2408.13102","title":"Dynamic Label Adversarial Training for Deep Learning Robustness Against Adversarial Attacks","created":"2024-08-23","cited_by_count":4,"area":null},{"id":"2212.13700","title":"Publishing Efficient On-device Models Increases Adversarial Vulnerability","created":"2022-12-28","cited_by_count":3,"area":null},{"id":"2311.00428","title":"NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks","created":"2023-11-01","cited_by_count":3,"area":"distill"},{"id":"2402.15586","title":"Distilling Adversarial Robustness Using Heterogeneous Teachers","created":"2024-02-23","cited_by_count":3,"area":"distill"},{"id":"2404.01828","title":"Defense without Forgetting: Continual Adversarial Defense with Anisotropic & Isotropic Pseudo Replay","created":"2024-04-02","cited_by_count":3,"area":null},{"id":"2410.12568","title":"Robust RL with LLM-Driven Data Synthesis and Policy Adaptation for Autonomous Driving","created":"2024-10-16","cited_by_count":3,"area":"lr"},{"id":"2502.16834","title":"A Novel Multi-Task Teacher-Student Architecture with Self-Supervised Pretraining for 48-Hour Vasoactive-Inotropic Trend Analysis in Sepsis Mortality Prediction","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2502.20562","title":"LISArD: Learning Image Similarity to Defend Against Gray-box Adversarial Attacks","created":"2025-02-27","cited_by_count":3,"area":null},{"id":"2511.11009","title":"Unsupervised Robust Domain Adaptation: Paradigm, Theory and Algorithm","created":"2025-11-14","cited_by_count":3,"area":null},{"id":"2108.12001","title":"Understanding the Logit Distributions of Adversarially-Trained Deep Neural Networks","created":"2021-08-26","cited_by_count":2,"area":null},{"id":"2209.13883","title":"MLink: Linking Black-Box Models from Multiple Domains for Collaborative Inference","created":"2022-09-28","cited_by_count":2,"area":null},{"id":"2301.08092","title":"RNAS-CL: Robust Neural Architecture Search by Cross-Layer Knowledge Distillation","created":"2023-01-19","cited_by_count":2,"area":"distill"},{"id":"2303.14922","title":"CAT:Collaborative Adversarial Training","created":"2023-03-27","cited_by_count":2,"area":null},{"id":"2405.13324","title":"Adversarial Training via Adaptive Knowledge Amalgamation of an Ensemble of Teachers","created":"2024-05-22","cited_by_count":2,"area":null},{"id":"2406.03409","title":"Robust Knowledge Distillation Based on Feature Variance Against Backdoored Teacher Model","created":"2024-06-01","cited_by_count":2,"area":"distill"},{"id":"2410.15889","title":"Model Mimic Attack: Knowledge Distillation for Provably Transferable Adversarial Examples","created":"2024-10-21","cited_by_count":2,"area":"distill"},{"id":"2412.19354","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","created":"2024-12-26","cited_by_count":2,"area":"distill"},{"id":"2506.00325","title":"Towards Effective and Efficient Adversarial Defense with Diffusion Models for Robust Visual Tracking","created":"2025-05-31","cited_by_count":2,"area":"diffusion"},{"id":"2506.11892","title":"Attention-based Adversarial Robust Distillation in Radio Signal Classifications for Low-Power IoT Devices","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2106.03613","title":"RoSearch: Search for Robust Student Architectures When Distilling Pre-trained Language Models","created":"2021-06-07","cited_by_count":1,"area":"distill"},{"id":"2208.09139","title":"DAFT: Distilling Adversarially Fine-tuned Models for Better OOD Generalization","created":"2022-08-19","cited_by_count":1,"area":null},{"id":"2211.00239","title":"ARDIR: Improving Robustness using Knowledge Distillation of Internal Representation","created":"2022-11-01","cited_by_count":1,"area":"distill"},{"id":"2306.04431","title":"Faithful Knowledge Distillation","created":"2023-06-07","cited_by_count":1,"area":"distill"},{"id":"2309.12914","title":"VIC-KD: Variance-Invariance-Covariance Knowledge Distillation to Make Keyword Spotting More Robust Against Adversarial Attacks","created":"2023-09-22","cited_by_count":1,"area":"distill"},{"id":"2311.17607","title":"Topology-preserving Adversarial Training for Alleviating Natural Accuracy Degradation","created":"2023-11-29","cited_by_count":1,"area":null},{"id":"2401.11365","title":"Confidence Preservation Property in Knowledge Distillation Abstractions","created":"2024-01-21","cited_by_count":1,"area":"safety"},{"id":"2402.05675","title":"Is Adversarial Training with Compressed Datasets Effective?","created":"2024-02-08","cited_by_count":1,"area":null},{"id":"2403.09441","title":"An Empirical Study of the Influence of Adversarial Fine-Tuning on Compressed Neural Networks","created":"2024-03-14","cited_by_count":1,"area":null},{"id":"2404.15656","title":"MISLEAD: Manipulating Importance of Selected features for Learning Epsilon in Evasion Attack Deception","created":"2024-04-24","cited_by_count":1,"area":null},{"id":"2406.01112","title":"BACON: Bayesian Optimal Condensation Framework for Dataset Distillation","created":"2024-06-03","cited_by_count":1,"area":null},{"id":"2406.06313","title":"ProAct: Progressive Training for Hybrid Clipped Activation Function to Enhance Resilience of DNNs","created":"2024-06-10","cited_by_count":1,"area":null},{"id":"2501.15257","title":"Towards Communication-Efficient Adversarial Federated Learning for Robust Edge Intelligence","created":"2025-01-25","cited_by_count":1,"area":null},{"id":"2506.07056","title":"D2R: dual regularization loss with collaborative adversarial generation for model robustness","created":"2025-06-08","cited_by_count":1,"area":null},{"id":"2509.12633","title":"CIARD: Cyclic Iterative Adversarial Robustness Distillation","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2511.05476","title":"A Metamorphic Testing Perspective on Knowledge Distillation for Language Models of Code: Does the Student Deeply Mimic the Teacher?","created":"2025-11-07","cited_by_count":1,"area":"distill"},{"id":"2607.06603","title":"Do Counterfactually Fair Image Classifiers Satisfy Group Fairness? -- A Theoretical and Empirical Study","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2103.08031","title":"BreakingBED -- Breaking Binary and Efficient Deep Neural Networks by Adversarial Attacks","created":"2021-03-14","cited_by_count":0,"area":null},{"id":"2112.13551","title":"Learning Robust and Lightweight Model through Separable Structured Transformations","created":"2021-12-27","cited_by_count":0,"area":null},{"id":"2202.11898","title":"Improving Robustness of Convolutional Neural Networks Using Element-Wise Activation Scaling","created":"2022-02-24","cited_by_count":0,"area":null},{"id":"2202.13755","title":"Towards Robust Stacked Capsule Autoencoder with Hybrid Adversarial Training","created":"2022-02-28","cited_by_count":0,"area":null},{"id":"2203.07027","title":"Learning from Attacks: Attacking Variational Autoencoder for Improving Image Classification","created":"2022-03-11","cited_by_count":0,"area":null},{"id":"2205.15763","title":"Exact Feature Collisions in Neural Networks","created":"2022-05-31","cited_by_count":0,"area":null}],"next_cursor":"100"}