research
∙
07/18/2023
VISER: A Tractable Solution Concept for Games with Information Asymmetry
Many real-world games suffer from information asymmetry: one player is o...
share
research
∙
06/13/2023
On Faking a Nash Equilibrium
We characterize offline data poisoning attacks on Multi-Agent Reinforcem...
research
∙
06/10/2023
Mechanism Design for Collaborative Normal Mean Estimation
We study collaborative normal mean estimation, where m strategic agents ...
research
∙
03/06/2023
Non-Parametric Outlier Synthesis
Out-of-distribution (OOD) detection is indispensable for safely deployin...
research
∙
11/18/2022
Provable Defense against Backdoor Policies in Reinforcement Learning
We propose a provable defense mechanism against backdoor policies in rei...
research
∙
06/04/2022
Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learning
We expose the danger of reward poisoning in offline multi-agent reinforc...
research
∙
06/01/2022
Byzantine-Robust Online and Offline Distributed Reinforcement Learning
We consider a distributed reinforcement learning setting where multiple ...
research
∙
04/13/2022
Out-of-distribution Detection with Deep Nearest Neighbors
Out-of-distribution (OOD) detection is a critical task for deploying mac...
research
∙
10/18/2021
Game Redesign in No-regret Game Playing
We study the game redesign problem in which an external designer has the...
research
∙
02/16/2021
Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments
We study black-box reward poisoning attacks against reinforcement learni...
research
∙
02/11/2021
Robust Policy Gradient against Strong Data Corruption
We study the problem of robust reinforcement learning under adversarial ...
research
∙
12/16/2020
Sequential Attacks on Kalman Filter-based Forward Collision Warning Systems
Kalman Filter (KF) is widely used in various domains to perform sequenti...
research
∙
11/21/2020
Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks
We study a security threat to reinforcement learning where an attacker p...
research
∙
10/17/2020
Preference-Based Batch and Sequential Teaching
Algorithmic machine teaching studies the interaction between a teacher a...
research
∙
09/05/2020
Using Machine Teaching to Investigate Human Assumptions when Teaching Reinforcement Learners
Successful teaching requires an assumption of how the learner learns - h...
research
∙
06/30/2020
Learning to Read through Machine Teaching
Learning to read words aloud is a major step towards becoming a reader. ...
research
∙
06/16/2020
The Teaching Dimension of Q-learning
In this paper, we initiate the study of sample complexity of teaching, t...
research
∙
06/16/2020
Theory of Machine Learning Debugging via M-estimation
We investigate problems in penalized M-estimation, inspired by applicati...
research
∙
03/28/2020
Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning
We study a security threat to reinforcement learning where an attacker p...
research
∙
03/27/2020
Adaptive Reward-Poisoning Attacks against Reinforcement Learning
In reward-poisoning attacks against reinforcement learning (RL), an atta...
research
∙
10/30/2019
A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning
In this paper, we proposed a general framework for data poisoning attack...
research
∙
10/24/2019
Preference-Based Batch and Sequential Teaching: Towards a Unified View of Models
Algorithmic machine teaching studies the interaction between a teacher a...
research
∙
10/18/2019
Error Lower Bounds of Constant Step-size Stochastic Gradient Descent
Stochastic Gradient Descent (SGD) plays a central role in modern machine...
research
∙
10/13/2019
Policy Poisoning in Batch Reinforcement Learning and Control
We study a security threat to batch reinforcement learning and control w...
research
∙
10/08/2019
Can We Distinguish Machine Learning from Human Learning?
What makes a task relatively more or less difficult for a machine compar...
research
∙
06/06/2019
Should Adversarial Attacks Use Pixel p-Norm?
Adversarial attacks aim to confound machine learning systems, while rema...
research
∙
05/16/2019
Fooling Computer Vision into Inferring the Wrong Body Mass Index
Recently it's been shown that neural networks can use images of human fa...
research
∙
03/23/2019
Data Poisoning against Differentially-Private Learners: Attacks and Defenses
Data poisoning attacks aim to manipulate the model produced by a learnin...
research
∙
03/05/2019
Online Data Poisoning Attack
We study data poisoning attacks in the online learning setting where the...
research
∙
02/01/2019
Optimal Adversarial Attack on Autoregressive Models
We investigate optimal adversarial attacks against time series forecast ...
research
∙
12/13/2018
Training Set Camouflage
We introduce a form of steganography in the domain of machine learning w...
research
∙
11/11/2018
An Optimal Control View of Adversarial Machine Learning
I describe an optimal control view of adversarial machine learning, wher...
research
∙
10/29/2018
Adversarial Attacks on Stochastic Bandits
We study adversarial attacks that manipulate the reward signals to contr...
research
∙
10/15/2018
An Optimal Control Approach to Sequential Machine Teaching
Given a sequential learning algorithm and a target model, sequential mac...
research
∙
08/17/2018
Data Poisoning Attacks in Contextual Bandits
We study offline data poisoning attacks in contextual bandits, a class o...
research
∙
06/04/2018
Program Synthesis from Visual Specification
Program synthesis is the process of automatically translating a specific...
research
∙
02/25/2018
Teacher Improves Learning by Selecting a Training Subset
We call a learner super-teachable if a teacher can trim down an iid trai...
research
∙
01/24/2018
Training Set Debugging Using Trusted Items
Training set bugs are flaws in the data that adversely affect machine le...
research
∙
01/18/2018
An Overview of Machine Teaching
In this paper we try to organize machine teaching as a coherent set of i...
research
∙
11/18/2016
Analysis of a Design Pattern for Teaching with Features and Labels
We study the task of teaching a machine to classify objects using featur...
research
∙
06/29/2015
S2: An Efficient Graph Based Active Learning Algorithm with Application to Nonparametric Classification
This paper investigates the problem of active learning for binary label ...
research
∙
04/10/2012