Many real-world games suffer from information asymmetry: one player is o...
We characterize offline data poisoning attacks on Multi-Agent Reinforcem...
We study collaborative normal mean estimation, where m strategic agents
...
Out-of-distribution (OOD) detection is indispensable for safely deployin...
We propose a provable defense mechanism against backdoor policies in
rei...
We expose the danger of reward poisoning in offline multi-agent reinforc...
We consider a distributed reinforcement learning setting where multiple
...
Out-of-distribution (OOD) detection is a critical task for deploying mac...
We study the game redesign problem in which an external designer has the...
We study black-box reward poisoning attacks against reinforcement learni...
We study the problem of robust reinforcement learning under adversarial
...
Kalman Filter (KF) is widely used in various domains to perform sequenti...
We study a security threat to reinforcement learning where an attacker
p...
Algorithmic machine teaching studies the interaction between a teacher a...
Successful teaching requires an assumption of how the learner learns - h...
Learning to read words aloud is a major step towards becoming a reader. ...
In this paper, we initiate the study of sample complexity of teaching, t...
We investigate problems in penalized M-estimation, inspired by applicati...
We study a security threat to reinforcement learning where an attacker
p...
In reward-poisoning attacks against reinforcement learning (RL), an atta...
In this paper, we proposed a general framework for data poisoning attack...
Algorithmic machine teaching studies the interaction between a teacher a...
Stochastic Gradient Descent (SGD) plays a central role in modern machine...
We study a security threat to batch reinforcement learning and control w...
What makes a task relatively more or less difficult for a machine compar...
Adversarial attacks aim to confound machine learning systems, while rema...
Recently it's been shown that neural networks can use images of human fa...
Data poisoning attacks aim to manipulate the model produced by a learnin...
We study data poisoning attacks in the online learning setting where the...
We investigate optimal adversarial attacks against time series forecast ...
We introduce a form of steganography in the domain of machine learning w...
I describe an optimal control view of adversarial machine learning, wher...
We study adversarial attacks that manipulate the reward signals to contr...
Given a sequential learning algorithm and a target model, sequential mac...
We study offline data poisoning attacks in contextual bandits, a class o...
Program synthesis is the process of automatically translating a specific...
We call a learner super-teachable if a teacher can trim down an iid trai...
Training set bugs are flaws in the data that adversely affect machine
le...
In this paper we try to organize machine teaching as a coherent set of i...
We study the task of teaching a machine to classify objects using featur...
This paper investigates the problem of active learning for binary label
...
Many real-world phenomena can be represented by a spatio-temporal signal...