{"total":125,"rows":[{"id":"2205.07460","title":"Diffusion Models for Adversarial Purification","created":"2022-05-16","cited_by_count":476,"area":"diffusion"},{"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":"2110.11417","title":"HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noise","created":"2021-10-06","cited_by_count":65,"area":null},{"id":"2403.07809","title":"pyvene: A Library for Understanding and Improving PyTorch Models via Interventions","created":"2024-03-12","cited_by_count":54,"area":null},{"id":"2104.11470","title":"Random Noise Defense Against Query-Based Black-Box Attacks","created":"2021-04-23","cited_by_count":47,"area":null},{"id":"2302.08469","title":"Hardware-aware training for large-scale and diverse deep learning inference workloads using in-memory computing-based accelerators","created":"2023-02-16","cited_by_count":43,"area":null},{"id":"2111.04625","title":"DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memories","created":"2021-11-08","cited_by_count":42,"area":null},{"id":"2107.12045","title":"How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review","created":"2021-07-26","cited_by_count":39,"area":null},{"id":"2205.04007","title":"ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learning","created":"2022-05-09","cited_by_count":36,"area":null},{"id":"2408.11779","title":"Personality Alignment of Large Language Models","created":"2024-08-21","cited_by_count":36,"area":"alignment"},{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"area":null},{"id":"2107.02425","title":"GradDiv: Adversarial Robustness of Randomized Neural Networks via Gradient Diversity Regularization","created":"2021-07-06","cited_by_count":34,"area":null},{"id":"2303.04449","title":"Loss-Curvature Matching for Dataset Selection and Condensation","created":"2023-03-08","cited_by_count":33,"area":null},{"id":"2103.14347","title":"Combating Adversaries with Anti-Adversaries","created":"2021-03-26","cited_by_count":27,"area":null},{"id":"2208.10159","title":"Prompt-Matched Semantic Segmentation","created":"2022-08-22","cited_by_count":22,"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":"2102.07379","title":"On the Inherent Regularization Effects of Noise Injection During Training","created":"2021-02-15","cited_by_count":18,"area":null},{"id":"2101.04829","title":"On the Effectiveness of Small Input Noise for Defending Against Query-based Black-Box Attacks","created":"2021-01-13","cited_by_count":17,"area":null},{"id":"2306.09124","title":"DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks","created":"2023-06-15","cited_by_count":15,"area":"diffusion"},{"id":"2104.03356","title":"Universal Spectral Adversarial Attacks for Deformable Shapes","created":"2021-04-07","cited_by_count":14,"area":null},{"id":"2112.03657","title":"Understanding Square Loss in Training Overparametrized Neural Network Classifiers","created":"2021-12-07","cited_by_count":14,"area":null},{"id":"2207.03574","title":"Demystifying the Adversarial Robustness of Random Transformation Defenses","created":"2022-06-18","cited_by_count":14,"area":null},{"id":"2308.12857","title":"Fast Adversarial Training with Smooth Convergence","created":"2023-08-24","cited_by_count":14,"area":null},{"id":"2201.12765","title":"Improving Robustness by Enhancing Weak Subnets","created":"2022-01-30","cited_by_count":13,"area":null},{"id":"2402.13987","title":"A Simple and Yet Fairly Effective Defense for Graph Neural Networks","created":"2024-02-21","cited_by_count":12,"area":null},{"id":"2208.00428","title":"Robust Real-World Image Super-Resolution against Adversarial Attacks","created":"2022-07-31","cited_by_count":11,"area":null},{"id":"2405.16262","title":"Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency","created":"2024-05-25","cited_by_count":10,"area":null},{"id":"2409.01249","title":"Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness","created":"2024-09-02","cited_by_count":10,"area":null},{"id":"2102.10875","title":"On the robustness of randomized classifiers to adversarial examples","created":"2021-02-22","cited_by_count":9,"area":null},{"id":"2501.19202","title":"Improving LLM Unlearning Robustness via Random Perturbations","created":"2025-01-31","cited_by_count":9,"area":"safety"},{"id":"2310.11970","title":"Quantifying Privacy Risks of Prompts in Visual Prompt Learning","created":"2023-10-18","cited_by_count":8,"area":"safety"},{"id":"2111.06503","title":"AnalogNets: ML-HW Co-Design of Noise-robust TinyML Models and Always-On Analog Compute-in-Memory Accelerator","created":"2021-11-10","cited_by_count":7,"area":null},{"id":"2403.13134","title":"Robust NAS under adversarial training: benchmark, theory, and beyond","created":"2024-03-19","cited_by_count":6,"area":null},{"id":"2505.20934","title":"NatADiff: Adversarial Boundary Guidance for Natural Adversarial Diffusion","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2103.00381","title":"Adversarial Information Bottleneck","created":"2021-02-28","cited_by_count":5,"area":null},{"id":"2109.05223","title":"2-in-1 Accelerator: Enabling Random Precision Switch for Winning Both Adversarial Robustness and Efficiency","created":"2021-09-11","cited_by_count":5,"area":null},{"id":"2207.06035","title":"Perturbation Inactivation Based Adversarial Defense for Face Recognition","created":"2022-07-13","cited_by_count":5,"area":null},{"id":"2208.12428","title":"Robust Prototypical Few-Shot Organ Segmentation with Regularized Neural-ODEs","created":"2022-08-26","cited_by_count":5,"area":null},{"id":"2302.04445","title":"Quantum Multi-Agent Actor-Critic Networks for Cooperative Mobile Access in Multi-UAV Systems","created":"2023-02-09","cited_by_count":5,"area":null},{"id":"2303.06302","title":"Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Survey","created":"2023-03-11","cited_by_count":5,"area":null},{"id":"2304.04343","title":"Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence","created":"2023-04-10","cited_by_count":5,"area":null},{"id":"2307.16865","title":"Universal Adversarial Defense in Remote Sensing Based on Pre-trained Denoising Diffusion Models","created":"2023-07-31","cited_by_count":5,"area":"diffusion"},{"id":"2409.09406","title":"Real-world Adversarial Defense against Patch Attacks based on Diffusion Model","created":"2024-09-14","cited_by_count":5,"area":"diffusion"},{"id":"2412.14714","title":"Holistic Adversarially Robust Pruning","created":"2024-12-19","cited_by_count":5,"area":null},{"id":"2104.09350","title":"A speckle filter for Sentinel-1 SAR Ground Range Detected data based on Residual Convolutional Neural Networks","created":"2021-04-19","cited_by_count":4,"area":null},{"id":"2209.09996","title":"Audit and Improve Robustness of Private Neural Networks on Encrypted Data","created":"2022-09-20","cited_by_count":4,"area":null},{"id":"2302.03523","title":"Sparse Mixture Once-for-all Adversarial Training for Efficient In-Situ Trade-Off Between Accuracy and Robustness of DNNs","created":"2022-12-27","cited_by_count":4,"area":null},{"id":"2302.07221","title":"On the Role of Randomization in Adversarially Robust Classification","created":"2023-02-14","cited_by_count":4,"area":null},{"id":"2306.17630","title":"Navigating Noise: A Study of How Noise Influences Generalisation and Calibration of Neural Networks","created":"2023-06-30","cited_by_count":4,"area":null},{"id":"2307.09375","title":"CertPri: Certifiable Prioritization for Deep Neural Networks via Movement Cost in Feature Space","created":"2023-07-18","cited_by_count":4,"area":null},{"id":"2405.17164","title":"WeiPer: OOD Detection using Weight Perturbations of Class Projections","created":"2024-05-27","cited_by_count":4,"area":null},{"id":"2105.04003","title":"Efficiency-driven Hardware Optimization for Adversarially Robust Neural Networks","created":"2021-05-09","cited_by_count":3,"area":null},{"id":"2109.15160","title":"Mitigating Black-Box Adversarial Attacks via Output Noise Perturbation","created":"2021-09-30","cited_by_count":3,"area":null},{"id":"2205.09037","title":"Empirical Advocacy of Bio-inspired Models for Robust Image Recognition","created":"2022-05-18","cited_by_count":3,"area":null},{"id":"2206.03727","title":"Wavelet Regularization Benefits Adversarial Training","created":"2022-06-08","cited_by_count":3,"area":null},{"id":"2211.16806","title":"Toward Robust Diagnosis: A Contour Attention Preserving Adversarial Defense for COVID-19 Detection","created":"2022-11-30","cited_by_count":3,"area":null},{"id":"2410.08456","title":"A Unified Deep Semantic Expansion Framework for Domain-Generalized Person Re-identification","created":"2024-10-11","cited_by_count":3,"area":null},{"id":"2201.00148","title":"Rethinking Feature Uncertainty in Stochastic Neural Networks for Adversarial Robustness","created":"2022-01-01","cited_by_count":2,"area":null},{"id":"2202.04271","title":"Adversarial Detection without Model Information","created":"2022-02-09","cited_by_count":2,"area":null},{"id":"2207.13036","title":"Jacobian Norm with Selective Input Gradient Regularization for Improved and Interpretable Adversarial Defense","created":"2022-07-09","cited_by_count":2,"area":null},{"id":"2208.00862","title":"Attacking Adversarial Defences by Smoothing the Loss Landscape","created":"2022-08-01","cited_by_count":2,"area":null},{"id":"2209.04547","title":"Defend Data Poisoning Attacks on Voice Authentication","created":"2022-09-09","cited_by_count":2,"area":"safety"},{"id":"2212.10430","title":"Walking Noise: On Layer-Specific Robustness of Neural Architectures against Noisy Computations and Associated Characteristic Learning Dynamics","created":"2022-12-20","cited_by_count":2,"area":null},{"id":"2311.13656","title":"Panda or not Panda? Understanding Adversarial Attacks with Interactive Visualization","created":"2023-11-22","cited_by_count":2,"area":null},{"id":"2405.01741","title":"PVF:Understanding AI Vulnerability Against SDCs","created":"2024-05-02","cited_by_count":2,"area":null},{"id":"2406.18144","title":"Artificial Immune System of Secure Face Recognition Against Adversarial Attacks","created":"2024-06-26","cited_by_count":2,"area":null},{"id":"2408.10818","title":"Learning Randomized Algorithms with Transformers","created":"2024-08-20","cited_by_count":2,"area":null},{"id":"2503.16183","title":"Variance-Aware Noisy Training: Hardening DNNs against Unstable Analog Computations","created":"2025-03-20","cited_by_count":2,"area":null},{"id":"2510.09685","title":"Deep Neural Networks Inspired by Differential Equations","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2602.15346","title":"Effective and Robust Multimodal Medical Image Analysis","created":"2026-02-17","cited_by_count":2,"area":null},{"id":"2102.09230","title":"Random Projections for Improved Adversarial Robustness","created":"2021-02-18","cited_by_count":1,"area":null},{"id":"2104.06377","title":"Mitigating Adversarial Attack for Compute-in-Memory Accelerator Utilizing On-chip Finetune","created":"2021-04-13","cited_by_count":1,"area":null},{"id":"2107.09804","title":"Using Undervolting as an On-Device Defense Against Adversarial Machine Learning Attacks","created":"2021-07-20","cited_by_count":1,"area":null},{"id":"2203.06474","title":"Optimizer Amalgamation","created":"2022-03-12","cited_by_count":1,"area":null},{"id":"2204.00426","title":"A Fast and Efficient Conditional Learning for Tunable Trade-Off between Accuracy and Robustness","created":"2022-03-28","cited_by_count":1,"area":null},{"id":"2204.10839","title":"How Sampling Impacts the Robustness of Stochastic Neural Networks","created":"2022-04-22","cited_by_count":1,"area":null},{"id":"2206.01705","title":"Gradient Obfuscation Checklist Test Gives a False Sense of Security","created":"2022-06-03","cited_by_count":1,"area":null},{"id":"2208.06228","title":"Unifying Gradients to Improve Real-world Robustness for Deep Networks","created":"2022-08-12","cited_by_count":1,"area":null},{"id":"2209.10381","title":"DARTSRepair: Core-failure-set Guided DARTS for Network Robustness to Common Corruptions","created":"2022-09-21","cited_by_count":1,"area":null},{"id":"2209.11920","title":"Tradeoffs between convergence rate and noise amplification for momentum-based accelerated optimization algorithms","created":"2022-09-24","cited_by_count":1,"area":null},{"id":"2210.00062","title":"Learning Robust Kernel Ensembles with Kernel Average Pooling","created":"2022-09-30","cited_by_count":1,"area":null},{"id":"2210.15764","title":"Noise Injection Node Regularization for Robust Learning","created":"2022-10-27","cited_by_count":1,"area":null},{"id":"2304.08811","title":"Towards the Transferable Audio Adversarial Attack via Ensemble Methods","created":"2023-04-18","cited_by_count":1,"area":null},{"id":"2309.06438","title":"Exploring Non-additive Randomness on ViT against Query-Based Black-Box Attacks","created":"2023-09-12","cited_by_count":1,"area":null},{"id":"2311.05790","title":"The Paradox of Noise: An Empirical Study of Noise-Infusion Mechanisms to Improve Generalization, Stability, and Privacy in Federated Learning","created":"2023-11-09","cited_by_count":1,"area":null},{"id":"2403.02707","title":"Enhancing Generalization in Medical Visual Question Answering Tasks via Gradient-Guided Model Perturbation","created":"2024-03-05","cited_by_count":1,"area":"mllm"},{"id":"2405.18499","title":"Training More Robust Classification Model via Discriminative Loss and Gaussian Noise Injection","created":"2024-05-28","cited_by_count":1,"area":null},{"id":"2411.00383","title":"Preventing Model Collapse in Deep Canonical Correlation Analysis by Noise Regularization","created":"2024-11-01","cited_by_count":1,"area":"synth"},{"id":"2501.12314","title":"Uncertainty Quantification With Noise Injection in Neural Networks: A Bayesian Perspective","created":"2025-01-21","cited_by_count":1,"area":null},{"id":"2505.16714","title":"Experimental robustness benchmarking of quantum neural networks on a superconducting quantum processor","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2603.11623","title":"The Density of Cross-Persistence Diagrams and Its Applications","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2605.01519","title":"Certified vs. Empirical Adversarial Robust-ness via Hybrid Convolutions with Attention Stochasticity","created":"2026-05-02","cited_by_count":1,"area":null},{"id":"2607.14921","title":"Random Logit Scaling: Defending Deep Neural Networks Against Black-Box Score-Based Adversarial Example Attacks","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2101.05950","title":"Robusta: Robust AutoML for Feature Selection via Reinforcement Learning","created":"2021-01-15","cited_by_count":0,"area":null},{"id":"2105.14710","title":"Robustifying $\\ell_\\infty$ Adversarial Training to the Union of Perturbation Models","created":"2021-05-31","cited_by_count":0,"area":null},{"id":"2106.05825","title":"HASI: Hardware-Accelerated Stochastic Inference, A Defense Against Adversarial Machine Learning Attacks","created":"2021-06-09","cited_by_count":0,"area":null},{"id":"2106.10212","title":"Residual Error: a New Performance Measure for Adversarial Robustness","created":"2021-06-18","cited_by_count":0,"area":null},{"id":"2107.03620","title":"Predicting Disease Progress with Imprecise Lab Test Results","created":"2021-07-08","cited_by_count":0,"area":null},{"id":"2112.15111","title":"Improving the Behaviour of Vision Transformers with Token-consistent Stochastic Layers","created":"2021-12-30","cited_by_count":0,"area":null},{"id":"2202.10320","title":"Resurrecting Trust in Facial Recognition: Mitigating Backdoor Attacks in Face Recognition to Prevent Potential Privacy Breaches","created":"2022-02-18","cited_by_count":0,"area":null}],"next_cursor":"100"}