389 citations · 2k across the 19 of their papers we have counts for
20 papers
Estimation of Standard Auction Models
Yeshwanth Cherapanamjeri, Constantinos Daskalakis, Andrew Ilyas +1
We provide efficient estimation methods for first- and second-price auctions under independent (asymmetric) private values and partial observability. Given a finite set of observat…
3DB: A Framework for Debugging Computer Vision Models
Guillaume Leclerc, Hadi Salman, Andrew Ilyas +9
We introduce 3DB: an extendable, unified framework for testing and debugging vision models using photorealistic simulation. We demonstrate, through a wide range of use cases, that…
Unadversarial Examples: Designing Objects for Robust Vision
Hadi Salman, Andrew Ilyas, Logan Engstrom +3
We study a class of realistic computer vision settings wherein one can influence the design of the objects being recognized. We develop a framework that leverages this capability t…
Do Adversarially Robust ImageNet Models Transfer Better?
Hadi Salman, Andrew Ilyas, Logan Engstrom +2
Transfer learning is a widely-used paradigm in deep learning, where models pre-trained on standard datasets can be efficiently adapted to downstream tasks. Typically, better pre-tr…
Noise or Signal: The Role of Image Backgrounds in Object Recognition
Kai Xiao, Logan Engstrom, Andrew Ilyas +1
We assess the tendency of state-of-the-art object recognition models to depend on signals from image backgrounds. We create a toolkit for disentangling foreground and background si…
Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO
Logan Engstrom, Andrew Ilyas, Shibani Santurkar +4
We study the roots of algorithmic progress in deep policy gradient algorithms through a case study on two popular algorithms: Proximal Policy Optimization (PPO) and Trust Region Po…
From ImageNet to Image Classification: Contextualizing Progress on Benchmarks
Dimitris Tsipras, Shibani Santurkar, Logan Engstrom +2
Building rich machine learning datasets in a scalable manner often necessitates a crowd-sourced data collection pipeline. In this work, we use human studies to investigate the cons…
Identifying Statistical Bias in Dataset Replication
Logan Engstrom, Andrew Ilyas, Shibani Santurkar +3
Dataset replication is a useful tool for assessing whether improvements in test accuracy on a specific benchmark correspond to improvements in models' ability to generalize reliabl…
Image Synthesis with a Single (Robust) Classifier
Shibani Santurkar, Dimitris Tsipras, Brandon Tran +3
We show that the basic classification framework alone can be used to tackle some of the most challenging tasks in image synthesis. In contrast to other state-of-the-art approaches,…
Adversarial Robustness as a Prior for Learned Representations
Logan Engstrom, Andrew Ilyas, Shibani Santurkar +3
An important goal in deep learning is to learn versatile, high-level feature representations of input data. However, standard networks' representations seem to possess shortcomings…
Adversarial Examples Are Not Bugs, They Are Features
Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras +3
Adversarial examples have attracted significant attention in machine learning, but the reasons for their existence and pervasiveness remain unclear. We demonstrate that adversarial…
A Closer Look at Deep Policy Gradients
Andrew Ilyas, Logan Engstrom, Shibani Santurkar +4
We study how the behavior of deep policy gradient algorithms reflects the conceptual framework motivating their development. To this end, we propose a fine-grained analysis of stat…
Evaluating and Understanding the Robustness of Adversarial Logit Pairing
Logan Engstrom, Andrew Ilyas, Anish Athalye
We evaluate the robustness of Adversarial Logit Pairing, a recently proposed defense against adversarial examples. We find that a network trained with Adversarial Logit Pairing ach…
Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors
Andrew Ilyas, Logan Engstrom, Aleksander Madry
We study the problem of generating adversarial examples in a black-box setting in which only loss-oracle access to a model is available. We introduce a framework that conceptually…
How Does Batch Normalization Help Optimization?
Shibani Santurkar, Dimitris Tsipras, Andrew Ilyas +1
Batch Normalization (BatchNorm) is a widely adopted technique that enables faster and more stable training of deep neural networks (DNNs). Despite its pervasiveness, the exact reas…
Black-box Adversarial Attacks with Limited Queries and Information
Andrew Ilyas, Logan Engstrom, Anish Athalye +1
Current neural network-based classifiers are susceptible to adversarial examples even in the black-box setting, where the attacker only has query access to the model. In practice,…
The Robust Manifold Defense: Adversarial Training using Generative Models
Ajil Jalal, Andrew Ilyas, Constantinos Daskalakis +1
We propose a new type of attack for finding adversarial examples for image classifiers. Our method exploits spanners, i.e. deep neural networks whose input space is low-dimensional…
Query-Efficient Black-box Adversarial Examples (superceded)
Andrew Ilyas, Logan Engstrom, Anish Athalye +1
Note that this paper is superceded by "Black-Box Adversarial Attacks with Limited Queries and Information." Current neural network-based image classifiers are susceptible to advers…
Training GANs with Optimism
Constantinos Daskalakis, Andrew Ilyas, Vasilis Syrgkanis +1
We address the issue of limit cycling behavior in training Generative Adversarial Networks and propose the use of Optimistic Mirror Decent (OMD) for training Wasserstein GANs. Rece…
Extracting Syntactic Patterns from Databases
Andrew Ilyas, Joana M. F. da Trindade, Raul Castro Fernandez +1
Many database columns contain string or numerical data that conforms to a pattern, such as phone numbers, dates, addresses, product identifiers, and employee ids. These patterns ar…