ImageNet

Dataset Card for ImageNet-D This is a FiftyOne dataset with 4838 samples. Installation If you haven't already, install FiftyOne: pip install -U fiftyone Usage import fiftyone as fo import fiftyone.utils.huggingface as fouh # Load the dataset # Note: other available arguments include 'max_samples', etc dataset = fouh.lo

Papers using ImageNet (18)

Perturbation Analysis Of Gradient-based Adversarial Attacks2020 · 11 citesParsimonious Black-box Adversarial Attacks Via Efficient Combinatorial Optimization2019 · 55 citesHow Worst-case Are Adversarial Attacks? Linking Adversarial And Perturbation Robustness2026Pubdef: Defending Against Transfer Attacks From Public Models2023Injection, Attack and Erasure: Revocable Backdoor Attacks via Machine Unlearning2025A Versatile Framework for Designing Group-Sparse Adversarial Attacks2025HAMLOCK: HArdware-Model LOgically Combined attacK2025DASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examples2025Enhancing Output Diversity Improves Conjugate Gradient-based Adversarial Attacks2024Adversarial Logit Pairing2018 · 467 citesBlack-box Adversarial Attacks With Limited Queries And Information2018 · 326 citesThere Are No Bit Parts For Sign Bits In Black-box Attacks2019 · 14 citesAttacking Deep Networks With Surrogate-based Adversarial Black-box Methods Is Easy2022 · 10 citesBenchmarking Robustness To Adversarial Image Obfuscations2023 · 2 citesBeating Attackers At Their Own Games: Adversarial Example Detection Using Adversarial Gradient Directions2020 · 1 citesTheoretical Corrections And The Leveraging Of Reinforcement Learning To Enhance Triangle Attack2024On Practical Aspects Of Aggregation Defenses Against Data Poisoning Attacks2023BO-DBA: Query-Efficient Decision-Based Adversarial Attacks via Bayesian Optimization2021 · 1 cites