← Authors

Aleksander Madry

44 papers · 2018–2025 · 5 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (6) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (14) πŸƒ Academic Marathon (7) πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (5) πŸ—ΊοΈ Taxonomy Completionist (17) 🀝 Dynamic Duo (21) πŸ‘‘ Triple Crown πŸ† Keyword Champion (2) πŸ”¬ Deep Specialist (10) πŸ“ˆ Trend Setter πŸš€ Conference Pioneer πŸ”₯ Unstoppable (8) ⚑ Prolific Year (7) ❓ The Questioner (2) πŸ—ƒοΈ Keyword Collector (138) πŸ’Ž Century Club (44)

Conferences

ICML (15) ICLR (13) NIPS (12) CVPR (3) AISTATS (1)

Top co-authors

Andrew Ilyas (21) Logan Engstrom (17) Shibani Santurkar (14) Dimitris Tsipras (14) Hadi Salman (9) Guillaume Leclerc (7) Sung Min Park (6) Saachi Jain (6) Ludwig Schmidt (6) Kristian Georgiev (5)

Research topics

Privacy (1)

Keywords

adversarial robustness (6) image classification (5) adversarial learning (4) benchmark evaluation (3) adversarial perturbation (3) domain generalization (3) feature representation (3) neural network (3) influence function (2) data poisoning (2) adversarial example (2) backdoor attack (2) transfer learning (2) domain adaptation (2) model debugging (2) adversarial defense (2) data augmentation (2) feature attribution (2) robust classification (2) robust statistics (2)

Papers

Small-to-Large Generalization: Training Data Influences Models Consistently Across Scale ICLR 2025
Machine Unlearning via Simulated Oracle Matching ICLR 2025
MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering ICLR 2025
Decomposing and Editing Predictions by Modeling Model Computation ICML 2024
DsDm: Model-Aware Dataset Selection with Datamodels ICML 2024
ContextCite: Attributing Model Generation to Context NIPS 2024
Improving Subgroup Robustness via Data Selection NIPS 2024
ModelDiff: A Framework for Comparing Learning Algorithms ICML 2023
Raising the Cost of Malicious AI-Powered Image Editing ICML 2023
TRAK: Attributing Model Behavior at Scale ICML 2023
Rethinking Backdoor Attacks ICML 2023
A Data-Based Perspective on Transfer Learning CVPR 2023
FFCV: Accelerating Training by Removing Data Bottlenecks CVPR 2023
Distilling Model Failures as Directions in Latent Space ICLR 2023
Adversarially trained neural representations may already be as robust as corresponding biological neural representations ICML 2022
Missingness Bias in Model Debugging ICLR 2022
Datamodels: Understanding Predictions with Data and Data with Predictions ICML 2022
3DB: A Framework for Debugging Computer Vision Models NIPS 2022
Combining Diverse Feature Priors ICML 2022
Certified Patch Robustness via Smoothed Vision Transformers CVPR 2022
Noise or Signal: The Role of Image Backgrounds in Object Recognition ICLR 2021
Unadversarial Examples: Designing Objects for Robust Vision NIPS 2021
Editing a classifier by rewriting its prediction rules NIPS 2021
BREEDS: Benchmarks for Subpopulation Shift ICLR 2021
Leveraging Sparse Linear Layers for Debuggable Deep Networks ICML 2021
Implementation Matters in Deep RL: A Case Study on PPO and TRPO ICLR 2020
Do Adversarially Robust ImageNet Models Transfer Better? NIPS 2020
On Adaptive Attacks to Adversarial Example Defenses NIPS 2020
A Closer Look at Deep Policy Gradients ICLR 2020
Identifying Statistical Bias in Dataset Replication ICML 2020
From ImageNet to Image Classification: Contextualizing Progress on Benchmarks ICML 2020
Prior Convictions: Black-box Adversarial Attacks with Bandits and Priors ICLR 2019
Robustness May Be at Odds with Accuracy ICLR 2019
Training for Faster Adversarial Robustness Verification via Inducing ReLU Stability ICLR 2019
Adversarial Examples Are Not Bugs, They Are Features NIPS 2019
Image Synthesis with a Single (Robust) Classifier NIPS 2019
Exploring the Landscape of Spatial Robustness ICML 2019
Spectral Signatures in Backdoor Attacks NIPS 2018
On the Limitations of First-Order Approximation in GAN Dynamics ICML 2018
A Classification-Based Study of Covariate Shift in GAN Distributions ICML 2018
How Does Batch Normalization Help Optimization? NIPS 2018
Towards Deep Learning Models Resistant to Adversarial Attacks ICLR 2018
A Fast Algorithm for Separated Sparsity via Perturbed Lagrangians AISTATS 2018
Adversarially Robust Generalization Requires More Data NIPS 2018