Balancing detectability and performance of attacks on the control channel of Markov Decision Processes

被引:0
|
作者
Russo, Alessio [1 ]
Proutiere, Alexandre [1 ]
机构
[1] KTH Royal Inst Technol, EECS Sch, Div Decis & Control Syst, Stockholm, Sweden
关键词
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We investigate the problem of designing optimal stealthy poisoning attacks on the control channel of Markov decision processes (MDPs). This research is motivated by the recent interest of the research community for adversarial and poisoning attacks applied to MDPs, and reinforcement learning (RL) methods. The policies resulting from these methods have been shown to be vulnerable to attacks perturbing the observations of the decision-maker. In such an attack, drawing inspiration from adversarial examples used in supervised learning, the amplitude of the adversarial perturbation is limited according to some norm, with the hope that this constraint will make the attack imperceptible. However, such constraints do not grant any level of undetectability and do not take into account the dynamic nature of the underlying Markov process. In this paper, we propose a new attack formulation, based on information-theoretical quantities, that considers the objective of minimizing the detectability of the attack as well as the performance of the controlled process. We analyze the trade-off between the efficiency of the attack and its detectability. We conclude with examples and numerical simulations illustrating this trade-off.
引用
收藏
页码:2843 / 2850
页数:8
相关论文
共 50 条
  • [21] IMPULSIVE CONTROL FOR CONTINUOUS-TIME MARKOV DECISION PROCESSES
    Dufour, Francois
    Piunovskiy, Alexei B.
    ADVANCES IN APPLIED PROBABILITY, 2015, 47 (01) : 106 - 127
  • [22] On Exact Embedding Framework for Optimal Control of Markov Decision Processes
    Kharade, Sonam
    Sutavani, Sarang
    Yerudkar, Amol
    Wagh, Sushama
    Liu, Yang
    Del Vecchio, Carmen
    Singh, N. M.
    IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2024, 69 (02) : 1316 - 1323
  • [23] A Bayesian Network Approach to Control of Networked Markov Decision Processes
    Adlakha, Sachin
    Lall, Sanjay
    Goldsmith, Andrea
    2008 46TH ANNUAL ALLERTON CONFERENCE ON COMMUNICATION, CONTROL, AND COMPUTING, VOLS 1-3, 2008, : 446 - +
  • [24] Robust control of Markov decision processes with uncertain transition matrices
    Nilim, A
    El Ghaoui, L
    OPERATIONS RESEARCH, 2005, 53 (05) : 780 - 798
  • [25] Optimal control in Markov decision processes via distributed optimization
    Fu, Jie
    Han, Shuo
    Topcu, Ufuk
    2015 54TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2015, : 7462 - 7469
  • [26] Learning Representation and Control in Markov Decision Processes: New Frontiers
    Mahadevan, Sridhar
    FOUNDATIONS AND TRENDS IN MACHINE LEARNING, 2009, 1 (04): : 403 - 565
  • [27] On the adaptive control of a class of partially observed Markov decision processes
    Hsu, Shun-Pin
    Arapostathis, Ari
    JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 2011, 380 (01) : 1 - 9
  • [28] An Argument for the Bayesian Control of Partially Observable Markov Decision Processes
    Vargo, Erik
    Cogill, Randy
    IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2014, 59 (10) : 2796 - 2800
  • [29] Optimal control of distributed Markov decision processes with network delays
    Adlakha, Sachin
    Madan, Ritesh
    Lall, Sanjay
    Goldsmith, Andrea
    PROCEEDINGS OF THE 46TH IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-14, 2007, : 4804 - +
  • [30] A Note on Infectious Disease Control using Markov Decision Processes
    Maeda Y.
    IEEJ Transactions on Electronics, Information and Systems, 2022, 142 (03) : 339 - 340