102 citations · 609 across the 64 of their papers we have counts for
40 papers · 1 filter
CFRecs: Counterfactual Recommendations on Real Estate User Listing Interaction Graphs
Seyedmasoud Mousavi, Ruomeng Xu, Xiaojing Zhu
Graph-structured data is ubiquitous and powerful in representing complex relationships in many online platforms. While graph neural networks (GNNs) are widely used to learn from su…
A Cramér-von Mises Approach to Incentivizing Truthful Data Sharing
Alex Clinton, Thomas Zeng, Yiding Chen +2
Modern data marketplaces and data sharing consortia increasingly rely on incentive mechanisms to encourage agents to contribute data. However, schemes that reward agents based on t…
Inception: Efficiently Computable Misinformation Attacks on Markov Games
Jeremy McMahan, Young Wu, Yudong Chen +2
We study security threats to Markov games due to information asymmetry and misinformation. We consider an attacker player who can spread misinformation about its reward function to…
Optimal Attack and Defense for Reinforcement Learning
Jeremy McMahan, Young Wu, Xiaojin Zhu +1
To ensure the usefulness of Reinforcement Learning (RL) in real systems, it is crucial to ensure they are robust to noise and adversarial attacks. In adversarial RL, an external at…
Optimally Teaching a Linear Behavior Cloning Agent
Shubham Kumar Bharti, Stephen Wright, Adish Singla +1
We study optimal teaching of Linear Behavior Cloning (LBC) learners. In this setup, the teacher can select which states to demonstrate to an LBC learner. The learner maintains a ve…
Anytime-Constrained Reinforcement Learning
Jeremy McMahan, Xiaojin Zhu
We introduce and study constrained Markov Decision Processes (cMDPs) with anytime constraints. An anytime constraint requires the agent to never violate its budget at any point in…
Dream the Impossible: Outlier Imagination with Diffusion Models
Xuefeng Du, Yiyou Sun, Xiaojin Zhu +1
Utilizing auxiliary outlier datasets to regularize the machine learning model has demonstrated promise for out-of-distribution (OOD) detection and safe prediction. Due to the labor…
Non-Parametric Outlier Synthesis
Leitian Tao, Xuefeng Du, Xiaojin Zhu +1
Out-of-distribution (OOD) detection is indispensable for safely deploying machine learning models in the wild. One of the key challenges is that models lack supervision signals fro…
Provable Defense against Backdoor Policies in Reinforcement Learning
Shubham Kumar Bharti, Xuezhou Zhang, Adish Singla +1
We propose a provable defense mechanism against backdoor policies in reinforcement learning under subspace trigger assumption. A backdoor policy is a security threat where an adver…
Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learning
Young Wu, Jeremy McMahan, Xiaojin Zhu +1
In offline multi-agent reinforcement learning (MARL), agents estimate policies from a given dataset. We study reward-poisoning attacks in this setting where an exogenous attacker m…
Byzantine-Robust Online and Offline Distributed Reinforcement Learning
Yiding Chen, Xuezhou Zhang, Kaiqing Zhang +2
We consider a distributed reinforcement learning setting where multiple agents separately explore the environment and communicate their experiences through a central server. Howeve…
Out-of-Distribution Detection with Deep Nearest Neighbors
Yiyou Sun, Yifei Ming, Xiaojin Zhu +1
Out-of-distribution (OOD) detection is a critical task for deploying machine learning models in the open world. Distance-based methods have demonstrated promise, where testing samp…
Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments
Amin Rakhsha, Xuezhou Zhang, Xiaojin Zhu +1
We study black-box reward poisoning attacks against reinforcement learning (RL), in which an adversary aims to manipulate the rewards to mislead a sequence of RL agents with unknow…
Robust Policy Gradient against Strong Data Corruption
Xuezhou Zhang, Yiding Chen, Xiaojin Zhu +1
We study the problem of robust reinforcement learning under adversarial corruption on both rewards and transitions. Our attack model assumes an \textit{adaptive} adversary who can…
Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks
Amin Rakhsha, Goran Radanovic, Rati Devidze +2
We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As…
Preference-Based Batch and Sequential Teaching
Farnam Mansouri, Yuxin Chen, Ara Vartanian +2
Algorithmic machine teaching studies the interaction between a teacher and a learner where the teacher selects labeled examples aiming at teaching a target hypothesis. In a quest t…
Using Machine Teaching to Investigate Human Assumptions when Teaching Reinforcement Learners
Yun-Shiuan Chuang, Xuezhou Zhang, Yuzhe Ma +3
Successful teaching requires an assumption of how the learner learns - how the learner uses experiences from the world to update their internal states. We investigate what expectat…
Learning to Read through Machine Teaching
Ayon Sen, Christopher R. Cox, Matthew Cooper Borkenhagen +2
Learning to read words aloud is a major step towards becoming a reader. Many children struggle with the task because of the inconsistencies of English spelling-sound correspondence…
The Sample Complexity of Teaching-by-Reinforcement on Q-Learning
Xuezhou Zhang, Shubham Kumar Bharti, Yuzhe Ma +2
We study the sample complexity of teaching, termed as "teaching dimension" (TDim) in the literature, for the teaching-by-reinforcement paradigm, where the teacher guides the studen…
Provable Training Set Debugging for Linear Regression
Xiaomin Zhang, Xiaojin Zhu, Po-Ling Loh
We investigate problems in penalized -estimation, inspired by applications in machine learning debugging. Data are collected from two pools, one containing data with possibly co…
Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning
Amin Rakhsha, Goran Radanovic, Rati Devidze +2
We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As…
Adaptive Reward-Poisoning Attacks against Reinforcement Learning
Xuezhou Zhang, Yuzhe Ma, Adish Singla +1
In reward-poisoning attacks against reinforcement learning (RL), an attacker can perturb the environment reward into at each step, with the goal of forcing the RL a…
Policy Poisoning in Batch Reinforcement Learning and Control
Yuzhe Ma, Xuezhou Zhang, Wen Sun +1
We study a security threat to batch reinforcement learning and control where the attacker aims to poison the learned policy. The victim is a reinforcement learner / controller whic…
A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning
Xuanqing Liu, Si Si, Xiaojin Zhu +2
In this paper, we proposed a general framework for data poisoning attacks to graph-based semi-supervised learning (G-SSL). In this framework, we first unify different tasks, goals,…