English
Related papers

Related papers: Policy Poisoning in Batch Reinforcement Learning a…

200 papers

Data-driven predictive control (DPC) is a feedback control method for systems with unknown dynamics. It repeatedly optimizes a system's future trajectories based on past input-output data. We develop a numerical method that computes…

Systems and Control · Electrical Eng. & Systems 2022-11-28 Yue Yu , Ruihan Zhao , Sandeep Chinchali , Ufuk Topcu

Gradient-based methods have been widely used for system design and optimization in diverse application domains. Recently, there has been a renewed interest in studying theoretical properties of these methods in the context of control and…

Optimization and Control · Mathematics 2022-10-11 Bin Hu , Kaiqing Zhang , Na Li , Mehran Mesbahi , Maryam Fazel , Tamer Başar

Recommender systems play a crucial role in helping users to find their interested information in various web services such as Amazon, YouTube, and Google News. Various recommender systems, ranging from neighborhood-based,…

Cryptography and Security · Computer Science 2021-01-11 Hai Huang , Jiaming Mu , Neil Zhenqiang Gong , Qi Li , Bin Liu , Mingwei Xu

Federated learning (FL) is an emerging paradigm for distributed training of large-scale deep neural networks in which participants' data remains on their own devices with only model updates being shared with a central server. However, the…

Machine Learning · Computer Science 2020-08-13 Vale Tolpegin , Stacey Truex , Mehmet Emre Gursoy , Ling Liu

We study the safe reinforcement learning problem with nonlinear function approximation, where policy optimization is formulated as a constrained optimization problem with both the objective and the constraint being nonconvex functions. For…

Machine Learning · Computer Science 2019-10-29 Ming Yu , Zhuoran Yang , Mladen Kolar , Zhaoran Wang

The perturbation analysis of linear solvers applied to systems arising broadly in machine learning settings -- for instance, when using linear regression models -- establishes an important perspective when reframing these analyses through…

Machine Learning · Computer Science 2024-10-02 Yixin Liu , Arielle Carr , Lichao Sun

Neural network classifiers are vulnerable to data poisoning attacks, as attackers can degrade or even manipulate their predictions thorough poisoning only a few training samples. However, the robustness of heuristic defenses is hard to…

Machine Learning · Computer Science 2020-10-14 Ruoxin Chen , Jie Li , Chentao Wu , Bin Sheng , Ping Li

In this work, we study the deception of a Linear-Quadratic-Gaussian (LQG) agent by manipulating the cost signals. We show that a small falsification of the cost parameters will only lead to a bounded change in the optimal policy. The bound…

Systems and Control · Electrical Eng. & Systems 2022-04-08 Yunhan Huang , Quanyan Zhu

The increasing adoption of Reinforcement Learning in safety-critical systems domains such as autonomous vehicles, health, and aviation raises the need for ensuring their safety. Existing safety mechanisms such as adversarial training,…

Machine Learning · Computer Science 2021-11-11 Paulina Stevia Nouwou Mindom , Amin Nikanjam , Foutse Khomh , John Mullins

This paper focuses on finding reinforcement learning policies for control systems with hard state and action constraints. Despite its success in many domains, reinforcement learning is challenging to apply to problems with hard constraints,…

Machine Learning · Computer Science 2020-03-24 Liyuan Zheng , Yuanyuan Shi , Lillian J. Ratliff , Baosen Zhang

Federated learning is a technique that allows multiple entities to collaboratively train models using their data without compromising data privacy. However, despite its advantages, federated learning can be susceptible to false data…

Machine Learning · Computer Science 2024-01-17 Or Shalom , Amir Leshem , Waheed U. Bajwa

We study the problem of learning-based attacks in linear systems, where the communication channel between the controller and the plant can be hijacked by a malicious attacker. We assume the attacker learns the dynamics of the system from…

Systems and Control · Electrical Eng. & Systems 2021-05-21 Anshuka Rangi , Mohammad Javad Khojasteh , Massimo Franceschetti

For all its successes, Reinforcement Learning (RL) still struggles to deliver formal guarantees on the closed-loop behavior of the learned policy. Among other things, guaranteeing the safety of RL with respect to safety-critical systems is…

Systems and Control · Electrical Eng. & Systems 2020-04-03 Sebastien Gros , Mario Zanon , Alberto Bemporad

Reinforcement learning (RL) agents need to be robust to variations in safety-critical environments. While system identification methods provide a way to infer the variation from online experience, they can fail in settings where fast…

Machine Learning · Computer Science 2022-03-07 Annie Xie , Shagun Sodhani , Chelsea Finn , Joelle Pineau , Amy Zhang

Consider the task of learning a hypothesis class $\mathcal{H}$ in the presence of an adversary that can replace up to an $\eta$ fraction of the examples in the training set with arbitrary adversarial examples. The adversary aims to fail the…

Machine Learning · Computer Science 2022-10-13 Steve Hanneke , Amin Karbasi , Mohammad Mahmoody , Idan Mehalel , Shay Moran

This chapter studies emerging cyber-attacks on reinforcement learning (RL) and introduces a quantitative approach to analyze the vulnerabilities of RL. Focusing on adversarial manipulation on the cost signals, we analyze the performance…

Machine Learning · Computer Science 2020-07-22 Yunhan Huang , Quanyan Zhu

In this paper the connection between stochastic optimal control and reinforcement learning is investigated. Our main motivation is to apply importance sampling to sampling rare events which can be reformulated as an optimal control problem.…

Optimization and Control · Mathematics 2024-02-16 Jannes Quer , Enric Ribera Borrell

The recent success of machine learning (ML) has been fueled by the increasing availability of computing power and large amounts of data in many different applications. However, the trustworthiness of the resulting models can be compromised…

Cryptography and Security · Computer Science 2024-03-11 Antonio Emanuele Cinà , Kathrin Grosse , Ambra Demontis , Battista Biggio , Fabio Roli , Marcello Pelillo

We consider availability data poisoning attacks, where an adversary aims to degrade the overall test accuracy of a machine learning model by crafting small perturbations to its training data. Existing poisoning strategies can achieve the…

Cryptography and Security · Computer Science 2024-06-07 Yiyong Liu , Michael Backes , Xiao Zhang

Adversarial data poisoning is an effective attack against machine learning and threatens model integrity by introducing poisoned data into the training dataset. So far, it has been studied mostly for classification, even though regression…

Machine Learning · Computer Science 2020-09-16 Nicolas Michael Müller , Daniel Kowatsch , Konstantin Böttinger