Aleksander Madry

166 papers A* 58A 2B 2Journal 93Unranked 10

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	AI Supply Chains: An Emerging Ecosystem of AI Actors, Products, and Services. CoRR Aspen K. Hopkins, Sarah H. Cen, Andrew Ilyas, Isabella Struckman, Luis Videgaray, Aleksander Madry
2025	J	`jnl`	Ask Your Distribution Shift if Pre-Training is Right for You. Trans. Mach. Learn. Res. Benjamin Cohen-Wang, Joshua Vendrow, Aleksander Madry
2025	J	`jnl`	Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety. CoRR Tomek Korbak, Mikita Balesni, Elizabeth Barnes, Yoshua Bengio, Joe Benton, Joseph Bloom, Mark Chen, Alan Cooney, Allan Dafoe, Anca D. Dragan, Scott Emmons, Owain Evans, David Farhi, Ryan Greenblatt, Dan Hendrycks, Marius Hobbhahn, Evan Hubinger, Geoffrey Irving, Erik Jenner, Daniel Kokotajlo, Victoria Krakovna, Shane Legg, David Lindner, David Luan, Aleksander Madry, Julian Michael, Neel Nanda, Dave Orr, Jakub Pachocki, Ethan Perez, Mary Phuong, Fabien Roger, Joshua Saxe, Buck Shlegeris, Martín Soto, Eric Steinberger, Jasmine Wang, Wojciech Zaremba, Bowen Baker, Rohin Shah, Vladimir Mikulik
2025	J	`jnl`	DataMIL: Selecting Data for Robot Imitation Learning with Datamodels. CoRR Shivin Dass, Alaa Khaddaj, Logan Engstrom, Aleksander Madry, Andrew Ilyas, Roberto Martín-Martín
2025	J	`jnl`	Do Large Language Model Benchmarks Test Reliability? CoRR Joshua Vendrow, Edward Vendrow, Sara Beery, Aleksander Madry
2025	J	`jnl`	Large-Scale, Longitudinal Study of Large Language Models During the 2024 US Election Season. CoRR Sarah H. Cen, Andrew Ilyas, Hedi Driss, Charlotte Park, Aspen K. Hopkins, Chara Podimata, Aleksander Madry
2025	J	`jnl`	Learning to Attribute with Attention. CoRR Benjamin Cohen-Wang, Yung-Sung Chuang, Aleksander Madry
2025	A*	`conf`	MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering. ICLR Jun Shern Chan, Neil Chowdhury, Oliver Jaffe, James Aung, Dane Sherburn, Evan Mays, Giulio Starace, Kevin Liu, Leon Maksin, Tejal Patwardhan, Aleksander Madry, Lilian Weng
2025	A*	`conf`	Machine Unlearning via Simulated Oracle Matching. ICLR Kristian Georgiev, Roy Rinberg, Sung Min Park, Shivam Garg, Andrew Ilyas, Aleksander Madry, Seth Neel
2025	J	`jnl`	Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation. CoRR Bowen Baker, Joost Huizinga, Leo Gao, Zehao Dou, Melody Y. Guan, Aleksander Madry, Wojciech Zaremba, Jakub Pachocki, David Farhi
2025	J	`jnl`	Optimizing ML Training with Metagradient Descent. CoRR Logan Engstrom, Andrew Ilyas, Benjamin Chen, Axel Feldmann, William Moses, Aleksander Madry
2025	J	`jnl`	Small-to-Large Generalization: Data Influences Models Consistently Across Scale. CoRR Alaa Khaddaj, Logan Engstrom, Aleksander Madry
2025	A*	`conf`	Small-to-Large Generalization: Training Data Influences Models Consistently Across Scale. ICLR Alaa Khaddaj, Logan Engstrom, Aleksander Madry
2024	J	`jnl`	Ask Your Distribution Shift if Pre-Training is Right for You. CoRR Benjamin Cohen-Wang, Joshua Vendrow, Aleksander Madry
2024	J	`jnl`	Attribute-to-Delete: Machine Unlearning via Datamodel Matching. CoRR Kristian Georgiev, Roy Rinberg, Sung Min Park, Shivam Garg, Andrew Ilyas, Aleksander Madry, Seth Neel
2024	A*	`conf`	ContextCite: Attributing Model Generation to Context. NeurIPS Benjamin Cohen-Wang, Harshay Shah, Kristian Georgiev, Aleksander Madry
2024	J	`jnl`	ContextCite: Attributing Model Generation to Context. CoRR Benjamin Cohen-Wang, Harshay Shah, Kristian Georgiev, Aleksander Madry
2024	J	`jnl`	Data Debiasing with Datamodels (D3M): Improving Subgroup Robustness via Data Selection. CoRR Saachi Jain, Kimia Hamidieh, Kristian Georgiev, Andrew Ilyas, Marzyeh Ghassemi, Aleksander Madry
2024	A*	`conf`	Decomposing and Editing Predictions by Modeling Model Computation. ICML Harshay Shah, Andrew Ilyas, Aleksander Madry
2024	J	`jnl`	Decomposing and Editing Predictions by Modeling Model Computation. CoRR Harshay Shah, Andrew Ilyas, Aleksander Madry
2024	A*	`conf`	DsDm: Model-Aware Dataset Selection with Datamodels. ICML Logan Engstrom, Axel Feldmann, Aleksander Madry
2024	J	`jnl`	DsDm: Model-Aware Dataset Selection with Datamodels. CoRR Logan Engstrom, Axel Feldmann, Aleksander Madry
2024	A*	`conf`	Improving Subgroup Robustness via Data Selection. NeurIPS Saachi Jain, Kimia Hamidieh, Kristian Georgiev, Andrew Ilyas, Marzyeh Ghassemi, Aleksander Madry
2024	J	`jnl`	MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering. CoRR Jun Shern Chan, Neil Chowdhury, Oliver Jaffe, James Aung, Dane Sherburn, Evan Mays, Giulio Starace, Kevin Liu, Leon Maksin, Tejal Patwardhan, Lilian Weng, Aleksander Madry
2024	A*	`conf`	Measuring Strategization in Recommendation: Users Adapt Their Behavior to Shape Future Content. EC Sarah H. Cen, Andrew Ilyas, Jennifer Allen, Hannah Li, Aleksander Madry
2024	J	`jnl`	Measuring Strategization in Recommendation: Users Adapt Their Behavior to Shape Future Content. CoRR Sarah H. Cen, Andrew Ilyas, Jennifer Allen, Hannah Li, Aleksander Madry
2024	A*	`conf`	User Strategization and Trustworthy Algorithms. EC Sarah H. Cen, Andrew Ilyas, Aleksander Madry
2023	A*	`conf`	A Data-Based Perspective on Transfer Learning. CVPR Saachi Jain, Hadi Salman, Alaa Khaddaj, Eric Wong, Sung Min Park, Aleksander Madry
2023	J	`jnl`	A User-Driven Framework for Regulating and Auditing Social Media. CoRR Sarah H. Cen, Aleksander Madry, Devavrat Shah
2023	J	`jnl`	Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation. CoRR Joshua Vendrow, Saachi Jain, Logan Engstrom, Aleksander Madry
2023	J	`jnl`	Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses. IEEE Trans. Pattern Anal. Mach. Intell. Micah Goldblum, Dimitris Tsipras, Chulin Xie, Xinyun Chen, Avi Schwarzschild, Dawn Song, Aleksander Madry, Bo Li, Tom Goldstein
2023	A*	`conf`	Distilling Model Failures as Directions in Latent Space. ICLR Saachi Jain, Hannah Lawrence, Ankur Moitra, Aleksander Madry
2023	A*	`conf`	FFCV: Accelerating Training by Removing Data Bottlenecks. CVPR Guillaume Leclerc, Andrew Ilyas, Logan Engstrom, Sung Min Park, Hadi Salman, Aleksander Madry
2023	J	`jnl`	FFCV: Accelerating Training by Removing Data Bottlenecks. CoRR Guillaume Leclerc, Andrew Ilyas, Logan Engstrom, Sung Min Park, Hadi Salman, Aleksander Madry
2023	A*	`conf`	ModelDiff: A Framework for Comparing Learning Algorithms. ICML Harshay Shah, Sung Min Park, Andrew Ilyas, Aleksander Madry
2023	A*	`conf`	Raising the Cost of Malicious AI-Powered Image Editing. ICML Hadi Salman, Alaa Khaddaj, Guillaume Leclerc, Andrew Ilyas, Aleksander Madry
2023	J	`jnl`	Raising the Cost of Malicious AI-Powered Image Editing. CoRR Hadi Salman, Alaa Khaddaj, Guillaume Leclerc, Andrew Ilyas, Aleksander Madry
2023	A*	`conf`	Rethinking Backdoor Attacks. ICML Alaa Khaddaj, Guillaume Leclerc, Aleksandar Makelov, Kristian Georgiev, Hadi Salman, Andrew Ilyas, Aleksander Madry
2023	J	`jnl`	Rethinking Backdoor Attacks. CoRR Alaa Khaddaj, Guillaume Leclerc, Aleksandar Makelov, Kristian Georgiev, Hadi Salman, Andrew Ilyas, Aleksander Madry
2023	A*	`conf`	TRAK: Attributing Model Behavior at Scale. ICML Sung Min Park, Kristian Georgiev, Andrew Ilyas, Guillaume Leclerc, Aleksander Madry
2023	J	`jnl`	TRAK: Attributing Model Behavior at Scale. CoRR Sung Min Park, Kristian Georgiev, Andrew Ilyas, Guillaume Leclerc, Aleksander Madry
2023	J	`jnl`	The Journey, Not the Destination: How Data Guides Diffusion Models. CoRR Kristian Georgiev, Joshua Vendrow, Hadi Salman, Sung Min Park, Aleksander Madry
2023	J	`jnl`	User Strategization and Trustworthy Algorithms. CoRR Sarah H. Cen, Andrew Ilyas, Aleksander Madry
2022	A*	`conf`	3DB: A Framework for Debugging Computer Vision Models. NeurIPS Guillaume Leclerc, Hadi Salman, Andrew Ilyas, Sai Vemprala, Logan Engstrom, Vibhav Vineet, Kai Yuanqing Xiao, Pengchuan Zhang, Shibani Santurkar, Greg Yang, Ashish Kapoor, Aleksander Madry
2022	J	`jnl`	A Data-Based Perspective on Transfer Learning. CoRR Saachi Jain, Hadi Salman, Alaa Khaddaj, Eric Wong, Sung Min Park, Aleksander Madry
2022	A*	`conf`	Adversarially trained neural representations are already as robust as biological neural representations. ICML Chong Guo, Michael J. Lee, Guillaume Leclerc, Joel Dapello, Yug Rao, Aleksander Madry, James J. DiCarlo
2022	J	`jnl`	Adversarially trained neural representations may already be as robust as corresponding biological neural representations. CoRR Chong Guo, Michael J. Lee, Guillaume Leclerc, Joel Dapello, Yug Rao, Aleksander Madry, James J. DiCarlo
2022	A*	`conf`	Certified Patch Robustness via Smoothed Vision Transformers. CVPR Hadi Salman, Saachi Jain, Eric Wong, Aleksander Madry
2022	A*	`conf`	Combining Diverse Feature Priors. ICML Saachi Jain, Dimitris Tsipras, Aleksander Madry
2022	J	`jnl`	Datamodels: Predicting Predictions from Training Data. CoRR Andrew Ilyas, Sung Min Park, Logan Engstrom, Guillaume Leclerc, Aleksander Madry
2022	A*	`conf`	Datamodels: Understanding Predictions with Data and Data with Predictions. ICML Andrew Ilyas, Sung Min Park, Logan Engstrom, Guillaume Leclerc, Aleksander Madry
2022	J	`jnl`	Distilling Model Failures as Directions in Latent Space. CoRR Saachi Jain, Hannah Lawrence, Ankur Moitra, Aleksander Madry
2022	A*	`conf`	Missingness Bias in Model Debugging. ICLR Saachi Jain, Hadi Salman, Eric Wong, Pengchuan Zhang, Vibhav Vineet, Sai Vemprala, Aleksander Madry
2022	J	`jnl`	Missingness Bias in Model Debugging. CoRR Saachi Jain, Hadi Salman, Eric Wong, Pengchuan Zhang, Vibhav Vineet, Sai Vemprala, Aleksander Madry
2022	J	`jnl`	ModelDiff: A Framework for Comparing Learning Algorithms. CoRR Harshay Shah, Sung Min Park, Andrew Ilyas, Aleksander Madry
2022	J	`jnl`	When does Bias Transfer in Transfer Learning? CoRR Hadi Salman, Saachi Jain, Andrew Ilyas, Logan Engstrom, Eric Wong, Aleksander Madry
2021	J	`jnl`	3DB: A Framework for Debugging Computer Vision Models. CoRR Guillaume Leclerc, Hadi Salman, Andrew Ilyas, Sai Vemprala, Logan Engstrom, Vibhav Vineet, Kai Yuanqing Xiao, Pengchuan Zhang, Shibani Santurkar, Greg Yang, Ashish Kapoor, Aleksander Madry
2021	A*	`conf`	BREEDS: Benchmarks for Subpopulation Shift. ICLR Shibani Santurkar, Dimitris Tsipras, Aleksander Madry
2021	J	`jnl`	Certified Patch Robustness via Smoothed Vision Transformers. CoRR Hadi Salman, Saachi Jain, Eric Wong, Aleksander Madry
2021	J	`jnl`	Combining Diverse Feature Priors. CoRR Saachi Jain, Dimitris Tsipras, Aleksander Madry
2021	A*	`conf`	Editing a classifier by rewriting its prediction rules. NeurIPS Shibani Santurkar, Dimitris Tsipras, Mahalaxmi Elango, David Bau, Antonio Torralba, Aleksander Madry
2021	J	`jnl`	Editing a classifier by rewriting its prediction rules. CoRR Shibani Santurkar, Dimitris Tsipras, Mahalaxmi Elango, David Bau, Antonio Torralba, Aleksander Madry
2021	A*	`conf`	Faster Sparse Minimum Cost Flow by Electrical Flow Localization. FOCS Kyriakos Axiotis, Aleksander Madry, Adrian Vladu
2021	J	`jnl`	Faster Sparse Minimum Cost Flow by Electrical Flow Localization. CoRR Kyriakos Axiotis, Aleksander Madry, Adrian Vladu
2021	A*	`conf`	Leveraging Sparse Linear Layers for Debuggable Deep Networks. ICML Eric Wong, Shibani Santurkar, Aleksander Madry
2021	J	`jnl`	Leveraging Sparse Linear Layers for Debuggable Deep Networks. CoRR Eric Wong, Shibani Santurkar, Aleksander Madry
2021	A*	`conf`	Noise or Signal: The Role of Image Backgrounds in Object Recognition. ICLR Kai Yuanqing Xiao, Logan Engstrom, Andrew Ilyas, Aleksander Madry
2021	J	`jnl`	On Distinctive Properties of Universal Perturbations. CoRR Sung Min Park, Kuo-An Wei, Kai Yuanqing Xiao, Jerry Li, Aleksander Madry
2021	A*	`conf`	Unadversarial Examples: Designing Objects for Robust Vision. NeurIPS Hadi Salman, Andrew Ilyas, Logan Engstrom, Sai Vemprala, Aleksander Madry, Ashish Kapoor
2020	A*	`conf`	A Closer Look at Deep Policy Gradients. ICLR Andrew Ilyas, Logan Engstrom, Shibani Santurkar, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, Aleksander Madry
2020	J	`jnl`	BREEDS: Benchmarks for Subpopulation Shift. CoRR Shibani Santurkar, Dimitris Tsipras, Aleksander Madry
2020	A*	`conf`	Circulation Control for Faster Minimum Cost Flow in Unit-Capacity Graphs. FOCS Kyriakos Axiotis, Aleksander Madry, Adrian Vladu
2020	J	`jnl`	Circulation Control for Faster Minimum Cost Flow in Unit-Capacity Graphs. CoRR Kyriakos Axiotis, Aleksander Madry, Adrian Vladu
2020	J	`jnl`	Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses. CoRR Micah Goldblum, Dimitris Tsipras, Chulin Xie, Xinyun Chen, Avi Schwarzschild, Dawn Song, Aleksander Madry, Bo Li, Tom Goldstein
2020	A*	`conf`	Do Adversarially Robust ImageNet Models Transfer Better? NeurIPS Hadi Salman, Andrew Ilyas, Logan Engstrom, Ashish Kapoor, Aleksander Madry
2020	J	`jnl`	Do Adversarially Robust ImageNet Models Transfer Better? CoRR Hadi Salman, Andrew Ilyas, Logan Engstrom, Ashish Kapoor, Aleksander Madry
2020	A*	`conf`	From ImageNet to Image Classification: Contextualizing Progress on Benchmarks. ICML Dimitris Tsipras, Shibani Santurkar, Logan Engstrom, Andrew Ilyas, Aleksander Madry
2020	J	`jnl`	From ImageNet to Image Classification: Contextualizing Progress on Benchmarks. CoRR Dimitris Tsipras, Shibani Santurkar, Logan Engstrom, Andrew Ilyas, Aleksander Madry
2020	A*	`conf`	Identifying Statistical Bias in Dataset Replication. ICML Logan Engstrom, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Jacob Steinhardt, Aleksander Madry
2020	J	`jnl`	Identifying Statistical Bias in Dataset Replication. CoRR Logan Engstrom, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Jacob Steinhardt, Aleksander Madry
2020	J	`jnl`	Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO. CoRR Logan Engstrom, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, Aleksander Madry
2020	A*	`conf`	Implementation Matters in Deep RL: A Case Study on PPO and TRPO. ICLR Logan Engstrom, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, Aleksander Madry
2020	J	`jnl`	Noise or Signal: The Role of Image Backgrounds in Object Recognition. CoRR Kai Yuanqing Xiao, Logan Engstrom, Andrew Ilyas, Aleksander Madry
2020	A*	`conf`	On Adaptive Attacks to Adversarial Example Defenses. NeurIPS Florian Tramèr, Nicholas Carlini, Wieland Brendel, Aleksander Madry
2020	J	`jnl`	On Adaptive Attacks to Adversarial Example Defenses. CoRR Florian Tramèr, Nicholas Carlini, Wieland Brendel, Aleksander Madry
2020	J	`jnl`	Round Compression for Parallel Matching Algorithms. SIAM J. Comput. Artur Czumaj, Jakub Lacki, Aleksander Madry, Slobodan Mitrovic, Krzysztof Onak, Piotr Sankowski
2020	J	`jnl`	The Two Regimes of Deep Network Training. CoRR Guillaume Leclerc, Aleksander Madry
2020	J	`jnl`	Unadversarial Examples: Designing Objects for Robust Vision. CoRR Hadi Salman, Andrew Ilyas, Logan Engstrom, Sai Vemprala, Aleksander Madry, Ashish Kapoor
2019	A*	`conf`	Adversarial Examples Are Not Bugs, They Are Features. NeurIPS Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Logan Engstrom, Brandon Tran, Aleksander Madry
2019	J	`jnl`	Adversarial Examples Are Not Bugs, They Are Features. CoRR Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Logan Engstrom, Brandon Tran, Aleksander Madry
2019	J	`jnl`	Computer Vision with a Single (Robust) Classifier. CoRR Shibani Santurkar, Dimitris Tsipras, Brandon Tran, Andrew Ilyas, Logan Engstrom, Aleksander Madry
2019	A*	`conf`	Exploring the Landscape of Spatial Robustness. ICML Logan Engstrom, Brandon Tran, Dimitris Tsipras, Ludwig Schmidt, Aleksander Madry
2019	A*	`conf`	Image Synthesis with a Single (Robust) Classifier. NeurIPS Shibani Santurkar, Andrew Ilyas, Dimitris Tsipras, Logan Engstrom, Brandon Tran, Aleksander Madry
2019	J	`jnl`	Label-Consistent Backdoor Attacks. CoRR Alexander Turner, Dimitris Tsipras, Aleksander Madry
2019	J	`jnl`	Learning Perceptually-Aligned Representations via Adversarial Robustness. CoRR Logan Engstrom, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Brandon Tran, Aleksander Madry
2019	J	`jnl`	On Evaluating Adversarial Robustness. CoRR Nicholas Carlini, Anish Athalye, Nicolas Papernot, Wieland Brendel, Jonas Rauber, Dimitris Tsipras, Ian J. Goodfellow, Aleksander Madry, Alexey Kurakin
2019	—	`conf`	Prior Convictions: Black-box Adversarial Attacks with Bandits and Priors. ICLR (Poster) Andrew Ilyas, Logan Engstrom, Aleksander Madry
2019	—	`conf`	Robustness May Be at Odds with Accuracy. ICLR (Poster) Dimitris Tsipras, Shibani Santurkar, Logan Engstrom, Alexander Turner, Aleksander Madry
2019	—	`conf`	Training for Faster Adversarial Robustness Verification via Inducing ReLU Stability. ICLR (Poster) Kai Yuanqing Xiao, Vincent Tjeng, Nur Muhammad (Mahi) Shafiullah, Aleksander Madry
2018	A*	`conf`	A Classification-Based Study of Covariate Shift in GAN Distributions. ICML Shibani Santurkar, Ludwig Schmidt, Aleksander Madry
2018	A	`conf`	A Fast Algorithm for Separated Sparsity via Perturbed Lagrangians. AISTATS Aleksander Madry, Slobodan Mitrovic, Ludwig Schmidt
2018	A*	`conf`	Adversarially Robust Generalization Requires More Data. NeurIPS Ludwig Schmidt, Shibani Santurkar, Dimitris Tsipras, Kunal Talwar, Aleksander Madry
2018	J	`jnl`	Adversarially Robust Generalization Requires More Data. CoRR Ludwig Schmidt, Shibani Santurkar, Dimitris Tsipras, Kunal Talwar, Aleksander Madry
2018	J	`jnl`	Are Deep Policy Gradient Algorithms Truly Policy Gradient Algorithms? CoRR Andrew Ilyas, Logan Engstrom, Shibani Santurkar, Dimitris Tsipras, Firdaus Janoos, Larry Rudolph, Aleksander Madry
2018	A*	`conf`	How Does Batch Normalization Help Optimization? NeurIPS Shibani Santurkar, Dimitris Tsipras, Andrew Ilyas, Aleksander Madry
2018	J	`jnl`	How Does Batch Normalization Help Optimization? (No, It Is Not About Internal Covariate Shift). CoRR Shibani Santurkar, Dimitris Tsipras, Andrew Ilyas, Aleksander Madry
2018	A*	`conf`	On the Limitations of First-Order Approximation in GAN Dynamics. ICML Jerry Li, Aleksander Madry, John Peebles, Ludwig Schmidt
2018	J	`jnl`	Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors. CoRR Andrew Ilyas, Logan Engstrom, Aleksander Madry
2018	A*	`conf`	Round compression for parallel matching algorithms. STOC Artur Czumaj, Jakub Lacki, Aleksander Madry, Slobodan Mitrovic, Krzysztof Onak, Piotr Sankowski
2018	A*	`conf`	Spectral Signatures in Backdoor Attacks. NeurIPS Brandon Tran, Jerry Li, Aleksander Madry
2018	J	`jnl`	Spectral Signatures in Backdoor Attacks. CoRR Brandon Tran, Jerry Li, Aleksander Madry
2018	J	`jnl`	There Is No Free Lunch In Adversarial Robustness (But There Are Unexpected Benefits). CoRR Dimitris Tsipras, Shibani Santurkar, Logan Engstrom, Alexander Turner, Aleksander Madry
2018	—	`conf`	Towards Deep Learning Models Resistant to Adversarial Attacks. ICLR (Poster) Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, Adrian Vladu
2018	J	`jnl`	Training for Faster Adversarial Robustness Verification via Inducing ReLU Stability. CoRR Kai Yuanqing Xiao, Vincent Tjeng, Nur Muhammad (Mahi) Shafiullah, Aleksander Madry
2018	A*	`conf`	k-server via multiscale entropic regularization. STOC Sébastien Bubeck, Michael B. Cohen, Yin Tat Lee, James R. Lee, Aleksander Madry
2017	J	`jnl`	A Classification-Based Perspective on GAN Distributions. CoRR Shibani Santurkar, Ludwig Schmidt, Aleksander Madry
2017	J	`jnl`	A Fast Algorithm for Separated Sparsity via Perturbed Lagrangians. CoRR Aleksander Madry, Slobodan Mitrovic, Ludwig Schmidt
2017	J	`jnl`	A Rotation and a Translation Suffice: Fooling CNNs with Simple Transformations. CoRR Logan Engstrom, Dimitris Tsipras, Ludwig Schmidt, Aleksander Madry
2017	J	`jnl`	An Oper. Res. Arash Asadpour, Michel X. Goemans, Aleksander Madry, Shayan Oveis Gharan, Amin Saberi
2017	A*	`conf`	Matrix Scaling and Balancing via Box Constrained Newton's Method and Interior Point Methods. FOCS Michael B. Cohen, Aleksander Madry, Dimitris Tsipras, Adrian Vladu
2017	J	`jnl`	Matrix Scaling and Balancing via Box Constrained Newton's Method and Interior Point Methods. CoRR Michael B. Cohen, Aleksander Madry, Dimitris Tsipras, Adrian Vladu
2017	A*	`conf`	Negative-Weight Shortest Paths and Unit Capacity Minimum Cost Flow in Õ ( SODA Michael B. Cohen, Aleksander Madry, Piotr Sankowski, Adrian Vladu
2017	J	`jnl`	On the Resiliency of Static Forwarding Tables. IEEE/ACM Trans. Netw. Marco Chiesa, Ilya Nikolaevskiy, Slobodan Mitrovic, Andrei V. Gurtov, Aleksander Madry, Michael Schapira, Scott Shenker
2017	J	`jnl`	Round Compression for Parallel Matching Algorithms. CoRR Artur Czumaj, Jakub Lacki, Aleksander Madry, Slobodan Mitrovic, Krzysztof Onak, Piotr Sankowski
2017	J	`jnl`	Towards Deep Learning Models Resistant to Adversarial Attacks. CoRR Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, Adrian Vladu
2017	J	`jnl`	Towards Understanding the Dynamics of Generative Adversarial Networks. CoRR Jerry Li, Aleksander Madry, John Peebles, Ludwig Schmidt
2017	J	`jnl`	k-server via multiscale entropic regularization. CoRR Sébastien Bubeck, Michael B. Cohen, James R. Lee, Yin Tat Lee, Aleksander Madry
2016	A*	`conf`	Computing Maximum Flow with Augmenting Electrical Flows. FOCS Aleksander Madry
2016	J	`jnl`	Computing Maximum Flow with Augmenting Electrical Flows. CoRR Aleksander Madry
2016	—	`conf`	Continuous Optimization: The "Right" Language for Graph Algorithms? (Invited Talk). FSTTCS Aleksander Madry
2016	J	`jnl`	Negative-Weight Shortest Paths and Unit Capacity Minimum Cost Flow in Õ(m CoRR Michael B. Cohen, Aleksander Madry, Piotr Sankowski, Adrian Vladu
2016	A*	`conf`	On the Resiliency of Randomized Routing Against Multiple Edge Failures. ICALP Marco Chiesa, Andrei V. Gurtov, Aleksander Madry, Slobodan Mitrovic, Ilya Nikolaevskiy, Michael Schapira, Scott Shenker
2016	A*	`conf`	The quest for resilient (static) forwarding tables. INFOCOM Marco Chiesa, Ilya Nikolaevskiy, Slobodan Mitrovic, Aurojit Panda, Andrei V. Gurtov, Aleksander Madry, Michael Schapira, Scott Shenker
2015	J	`jnl`	A Polylogarithmic-Competitive Algorithm for the J. ACM Nikhil Bansal, Niv Buchbinder, Aleksander Madry, Joseph Naor
2015	A*	`conf`	Fast Generation of Random Spanning Trees and the Effective Resistance Metric. SODA Aleksander Madry, Damian Straszak, Jakub Tarnawski
2015	J	`jnl`	Fast Generation of Random Spanning Trees and the Effective Resistance Metric. CoRR Aleksander Madry, Damian Straszak, Jakub Tarnawski
2015	J	`jnl`	On the configuration LP for maximum budgeted allocation. Math. Program. Christos Kalaitzis, Aleksander Madry, Alantha Newman, Lukás Polácek, Ola Svensson
2014	B	`conf`	On the Configuration LP for Maximum Budgeted Allocation. IPCO Christos Kalaitzis, Aleksander Madry, Alantha Newman, Lukas Polacek, Ola Svensson
2014	J	`jnl`	On the Configuration LP for Maximum Budgeted Allocation. CoRR Christos Kalaitzis, Aleksander Madry, Alantha Newman, Lukas Polacek, Ola Svensson
2013	A*	`conf`	Navigating Central Path with Electrical Flows: From Flows to Matchings, and Back. FOCS Aleksander Madry
2013	J	`jnl`	Navigating Central Path with Electrical Flows: from Flows to Matchings, and Back. CoRR Aleksander Madry
2013	A	`conf`	Runtime guarantees for regression problems. ITCS Hui Han Chin, Aleksander Madry, Gary L. Miller, Richard Peng
2011	J	`jnl`	A Polylogarithmic-Competitive Algorithm for the k-Server Problem CoRR Nikhil Bansal, Niv Buchbinder, Aleksander Madry, Joseph Naor
2011	A*	`conf`	A Polylogarithmic-Competitive Algorithm for the k-Server Problem. FOCS Nikhil Bansal, Niv Buchbinder, Aleksander Madry, Joseph Naor
2011	J	`jnl`	Electrical Flow Algorithms for Total Variation Minimization CoRR Aleksander Madry, Gary L. Miller, Richard Peng
2011	A*	`conf`	Electrical flows, laplacian systems, and faster approximation of maximum flow in undirected graphs. STOC Paul F. Christiano, Jonathan A. Kelner, Aleksander Madry, Daniel A. Spielman, Shang-Hua Teng
2011	J	`jnl`	Maximum bipartite flow in networks with adaptive channel width. Theor. Comput. Sci. Yossi Azar, Aleksander Madry, Thomas Moscibroda, Debmalya Panigrahi, Aravind Srinivasan
2011	—	`—`	New techniques for graph algorithms. Aleksander Madry
2011	—	`conf`	The Semi-stochastic Ski-rental Problem. FSTTCS Aleksander Madry, Debmalya Panigrahi
2010	A*	`conf`	An O(log n/ log log n)-approximation Algorithm for the Asymmetric Traveling Salesman Problem. SODA Arash Asadpour, Michel X. Goemans, Aleksander Madry, Shayan Oveis Gharan, Amin Saberi
2010	J	`jnl`	Electrical Flows, Laplacian Systems, and Faster Approximation of Maximum Flow in Undirected Graphs CoRR Paul F. Christiano, Jonathan A. Kelner, Aleksander Madry, Daniel A. Spielman, Shang-Hua Teng
2010	A*	`conf`	Fast Approximation Algorithms for Cut-Based Problems in Undirected Graphs. FOCS Aleksander Madry
2010	J	`jnl`	Fast Approximation Algorithms for Cut-based Problems in Undirected Graphs CoRR Aleksander Madry
2010	J	`jnl`	Faster Approximation Schemes for Fractional Multicommodity Flow Problems via Dynamic Graph Algorithms CoRR Aleksander Madry
2010	A*	`conf`	Faster approximation schemes for fractional multicommodity flow problems via dynamic graph algorithms. STOC Aleksander Madry
2009	—	`conf`	A 7/9 - Approximation Algorithm for the Maximum Traveling Salesman Problem. APPROX-RANDOM Katarzyna E. Paluch, Marcin Mucha, Aleksander Madry
2009	A*	`conf`	Faster Generation of Random Spanning Trees. FOCS Jonathan A. Kelner, Aleksander Madry
2009	J	`jnl`	Faster generation of random spanning trees CoRR Jonathan A. Kelner, Aleksander Madry
2009	—	`conf`	Maximum Bipartite Flow in Networks with Adaptive Channel Width. ICALP (2) Yossi Azar, Aleksander Madry, Thomas Moscibroda, Debmalya Panigrahi, Aravind Srinivasan
2008	J	`jnl`	A 7/9 - Approximation Algorithm for the Maximum Traveling Salesman Problem CoRR Katarzyna E. Paluch, Marcin Mucha, Aleksander Madry
2008	B	`conf`	Geometric Aspects of Online Packet Buffering: An Optimal Randomized Algorithm for Two Buffers. LATIN Marcin Bienkowski, Aleksander Madry
2008	—	`conf`	Susceptible Two-Party Quantum Computations. ICITS Andreas Jakoby, Maciej Liskiewicz, Aleksander Madry
2006	—	`conf`	Using Quantum Oblivious Transfer to Cheat Sensitive Quantum Bit Commitment. Complexity of Boolean Functions Andreas Jakoby, Maciej Liskiewicz, Aleksander Madry
2006	J	`jnl`	Using Quantum Oblivious Transfer to Cheat Sensitive Quantum Bit Commitment. Electron. Colloquium Comput. Complex. Andreas Jakoby, Maciej Liskiewicz, Aleksander Madry
2006	J	`jnl`	Using quantum oblivious transfer to cheat sensitive quantum bit commitment CoRR Andreas Jakoby, Maciej Liskiewicz, Aleksander Madry
2005	J	`jnl`	Data exchange: On the complexity of answering queries with inequalities. Inf. Process. Lett. Aleksander Madry