Model Extraction Attacks Against Reinforcement Learning Based Controllers

• URL: http://arxiv.org/abs/2304.13090v1
• Date: Tue, 25 Apr 2023 18:48:42 GMT
• Title: Model Extraction Attacks Against Reinforcement Learning Based Controllers
• Authors: Momina Sajid, Yanning Shen, Yasser Shoukry
• Abstract summary: This paper focuses on the setting when a Deep Neural Network (DNN) controller is trained using Reinforcement Learning (RL) algorithms and is used to control a system. In the first phase, also called the offline phase, the attacker uses side-channel information about the RL-reward function and the system dynamics to identify a set of candidate estimates of the unknown DNN. In the second phase, also called the online phase, the attacker observes the behavior of the unknown DNN and uses these observations to shortlist the set of final policy estimates.
• Score: 9.273077240506016
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce the problem of model-extraction attacks in cyber-physical systems in which an attacker attempts to estimate (or extract) the feedback controller of the system. Extracting (or estimating) the controller provides an unmatched edge to attackers since it allows them to predict the future control actions of the system and plan their attack accordingly. Hence, it is important to understand the ability of the attackers to perform such an attack. In this paper, we focus on the setting when a Deep Neural Network (DNN) controller is trained using Reinforcement Learning (RL) algorithms and is used to control a stochastic system. We play the role of the attacker that aims to estimate such an unknown DNN controller, and we propose a two-phase algorithm. In the first phase, also called the offline phase, the attacker uses side-channel information about the RL-reward function and the system dynamics to identify a set of candidate estimates of the unknown DNN. In the second phase, also called the online phase, the attacker observes the behavior of the unknown DNN and uses these observations to shortlist the set of final policy estimates. We provide theoretical analysis of the error between the unknown DNN and the estimated one. We also provide numerical results showing the effectiveness of the proposed algorithm.

Related papers

• Securing Graph Neural Networks in MLaaS: A Comprehensive Realization of Query-based Integrity Verification [68.86863899919358]
  We introduce a groundbreaking approach to protect GNN models in Machine Learning from model-centric attacks. Our approach includes a comprehensive verification schema for GNN's integrity, taking into account both transductive and inductive GNNs. We propose a query-based verification technique, fortified with innovative node fingerprint generation algorithms.
  arXiv  Detail & Related papers  (2023-12-13T03:17:05Z)
• Downlink Power Allocation in Massive MIMO via Deep Learning: Adversarial Attacks and Training [62.77129284830945]
  This paper considers a regression problem in a wireless setting and shows that adversarial attacks can break the DL-based approach. We also analyze the effectiveness of adversarial training as a defensive technique in adversarial settings and show that the robustness of DL-based wireless system against attacks improves significantly.
  arXiv  Detail & Related papers  (2022-06-14T04:55:11Z)
• Early Detection of Network Attacks Using Deep Learning [0.0]
  A network intrusion detection system (IDS) is a tool used for identifying unauthorized and malicious behavior by observing the network traffic. We propose an end-to-end early intrusion detection system to prevent network attacks before they could cause any more damage to the system under attack.
  arXiv  Detail & Related papers  (2022-01-27T16:35:37Z)
• Modelling DDoS Attacks in IoT Networks using Machine Learning [21.812642970826563]
  TCP-specific attacks are one of the most plausible tools that attackers can use on Cyber-Physical Systems. This study compares the effectiveness of supervised, unsupervised, and semi-supervised machine learning algorithms for detecting DDoS attacks in CPS-IoT.
  arXiv  Detail & Related papers  (2021-12-10T12:09:26Z)
• The Feasibility and Inevitability of Stealth Attacks [63.14766152741211]
  We study new adversarial perturbations that enable an attacker to gain control over decisions in generic Artificial Intelligence systems. In contrast to adversarial data modification, the attack mechanism we consider here involves alterations to the AI system itself.
  arXiv  Detail & Related papers  (2021-06-26T10:50:07Z)
• Policy Smoothing for Provably Robust Reinforcement Learning [109.90239627115336]
  We study the provable robustness of reinforcement learning against norm-bounded adversarial perturbations of the inputs. We generate certificates that guarantee that the total reward obtained by the smoothed policy will not fall below a certain threshold under a norm-bounded adversarial of perturbation the input.
  arXiv  Detail & Related papers  (2021-06-21T21:42:08Z)
• Towards Adversarial Patch Analysis and Certified Defense against Crowd Counting [61.99564267735242]
  Crowd counting has drawn much attention due to its importance in safety-critical surveillance systems. Recent studies have demonstrated that deep neural network (DNN) methods are vulnerable to adversarial attacks. We propose a robust attack strategy called Adversarial Patch Attack with Momentum to evaluate the robustness of crowd counting models.
  arXiv  Detail & Related papers  (2021-04-22T05:10:55Z)
• Learning-Based Vulnerability Analysis of Cyber-Physical Systems [10.066594071800337]
  This work focuses on the use of deep learning for vulnerability analysis of cyber-physical systems. We consider a control architecture widely used in CPS (e.g., robotics) where the low-level control is based on e.g., the extended Kalman filter (EKF) and an anomaly detector. To facilitate analyzing the impact potential sensing attacks could have, our objective is to develop learning-enabled attack generators.
  arXiv  Detail & Related papers  (2021-03-10T06:52:26Z)
• Towards Adversarial-Resilient Deep Neural Networks for False Data Injection Attack Detection in Power Grids [7.351477761427584]
  False data injection attacks (FDIAs) pose a significant security threat to power system state estimation. Recent studies have proposed machine learning (ML) techniques, particularly deep neural networks (DNNs)
  arXiv  Detail & Related papers  (2021-02-17T22:26:34Z)
• A Secure Learning Control Strategy via Dynamic Camouflaging for Unknown Dynamical Systems under Attacks [0.0]
  This paper presents a secure reinforcement learning (RL) based control method for unknown linear time-invariant cyber-physical systems (CPSs) We consider the attack scenario where the attacker learns about the dynamic model during the exploration phase of the learning conducted by the designer. We propose a dynamic camouflaging based attack-resilient reinforcement learning (ARRL) algorithm which can learn the desired optimal controller for the dynamic system.
  arXiv  Detail & Related papers  (2021-02-01T00:34:38Z)
• Adversarial vs behavioural-based defensive AI with joint, continual and active learning: automated evaluation of robustness to deception, poisoning and concept drift [62.997667081978825]
  Recent advancements in Artificial Intelligence (AI) have brought new capabilities to behavioural analysis (UEBA) for cyber-security. In this paper, we present a solution to effectively mitigate this attack by improving the detection process and efficiently leveraging human expertise.
  arXiv  Detail & Related papers  (2020-01-13T13:54:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.