Robustness to Adversarial Attacks in Learning-Enabled Controllers

• URL: http://arxiv.org/abs/2006.06861v1
• Date: Thu, 11 Jun 2020 22:29:07 GMT
• Title: Robustness to Adversarial Attacks in Learning-Enabled Controllers
• Abstract summary: We consider state perturbations that encompass a wide variety of adversarial attacks and describe an attack scheme for discovering adversarial states. To be useful, these attacks need to be natural, yielding states in which the controller can be reasonably expected to generate a meaningful response. Our defense strategy allows us to treat the controller and environment as black-boxes with unknown dynamics.
• Score: 3.4983716329137353
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning-enabled controllers used in cyber-physical systems (CPS) are known to be susceptible to adversarial attacks. Such attacks manifest as perturbations to the states generated by the controller's environment in response to its actions. We consider state perturbations that encompass a wide variety of adversarial attacks and describe an attack scheme for discovering adversarial states. To be useful, these attacks need to be natural, yielding states in which the controller can be reasonably expected to generate a meaningful response. We consider shield-based defenses as a means to improve controller robustness in the face of such perturbations. Our defense strategy allows us to treat the controller and environment as black-boxes with unknown dynamics. We provide a two-stage approach to construct this defense and show its effectiveness through a range of experiments on realistic continuous control domains such as the navigation control-loop of an F16 aircraft and the motion control system of humanoid robots.

Related papers

• Trojan Attacks on Neural Network Controllers for Robotic Systems [0.3823356975862005]
  This paper investigates backdoor (Trojan) attacks against neural controllers.<n>We design a lightweight, parallel Trojan network that can be embedded within the controller.<n>The results confirm the effectiveness of the proposed attack and demonstrate that neural network-based robotic control systems are subject to potentially critical security threats.
  arXiv  Detail & Related papers  (2026-02-04T23:12:22Z)
• Reinforcement Learning for Decision-Level Interception Prioritization in Drone Swarm Defense [56.47577824219207]
  We present a case study demonstrating the practical advantages of reinforcement learning in addressing this challenge.<n>We introduce a high-fidelity simulation environment that captures realistic operational constraints.<n>Agent learns to coordinate multiple effectors for optimal interception prioritization.<n>We evaluate the learned policy against a handcrafted rule-based baseline across hundreds of simulated attack scenarios.
  arXiv  Detail & Related papers  (2025-08-01T13:55:39Z)
• ARMOR: Robust Reinforcement Learning-based Control for UAVs under Physical Attacks [6.362264393795084]
  Unmanned Aerial Vehicles (UAVs) depend on onboard sensors for perception, navigation, and control.<n>ArmOR is an attack-resilient, model-free reinforcement learning controller.<n>ArmOR learns a robust latent representation of the UAV's physical state via a two-stage training framework.
  arXiv  Detail & Related papers  (2025-06-27T17:46:33Z)
• Designing Control Barrier Function via Probabilistic Enumeration for Safe Reinforcement Learning Navigation [55.02966123945644]
  We propose a hierarchical control framework leveraging neural network verification techniques to design control barrier functions (CBFs) and policy correction mechanisms. Our approach relies on probabilistic enumeration to identify unsafe regions of operation, which are then used to construct a safe CBF-based control layer. These experiments demonstrate the ability of the proposed solution to correct unsafe actions while preserving efficient navigation behavior.
  arXiv  Detail & Related papers  (2025-04-30T13:47:25Z)
• Smart Grid Security: A Verified Deep Reinforcement Learning Framework to Counter Cyber-Physical Attacks [2.159496955301211]
  Smart grids are vulnerable to strategically crafted cyber-physical attacks. Malicious attacks can manipulate power demands using high-wattage Internet of Things (IoT) botnet devices. Grid operators overlook potential scenarios of cyber-physical attacks during their design phase. We propose a safe Deep Reinforcement Learning (DRL)-based framework for mitigating attacks on smart grids.
  arXiv  Detail & Related papers  (2024-09-24T05:26:20Z)
• Rethinking Robustness Assessment: Adversarial Attacks on Learning-based Quadrupedal Locomotion Controllers [33.50779001548997]
  Legged locomotion has recently achieved remarkable success with the progress of machine learning techniques. We propose a computational method that leverages sequential adversarial attacks to identify weaknesses in learned locomotion controllers. Our research demonstrates that, even state-of-the-art robust controllers can fail significantly under well-designed, low-magnitude adversarial sequence.
  arXiv  Detail & Related papers  (2024-05-21T00:26:11Z)
• Model Predictive Control with adaptive resilience for Denial-of-Service Attacks mitigation on a Regulated Dam [5.32980262772932]
  SCADA (Supervisory Control and Data Acquisition) systems have increasingly become the target of cyber attacks. In a cyber-warfare context, we propose a Model Predictive Control architecture with adaptive resilience. We demonstrate the resulting MPC strategy's effectiveness in 2 attack scenarios on a real system with actual data.
  arXiv  Detail & Related papers  (2024-02-28T17:47:27Z)
• Adversarial Markov Games: On Adaptive Decision-Based Attacks and Defenses [21.759075171536388]
  We show how attacks but also defenses can benefit by it and by learning from each other through interaction. We demonstrate that active defenses, which control how the system responds, are a necessary complement to model hardening when facing decision-based attacks. We lay out effective strategies in ensuring the robustness of ML-based systems deployed in the real-world.
  arXiv  Detail & Related papers  (2023-12-20T21:24:52Z)
• Perpetual Humanoid Control for Real-time Simulated Avatars [77.05287269685911]
  We present a physics-based humanoid controller that achieves high-fidelity motion imitation and fault-tolerant behavior. Our controller scales up to learning ten thousand motion clips without using any external stabilizing forces. We demonstrate the effectiveness of our controller by using it to imitate noisy poses from video-based pose estimators and language-based motion generators in a live and real-time multi-person avatar use case.
  arXiv  Detail & Related papers  (2023-05-10T20:51:37Z)
• Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attacks [76.35478518372692]
  We introduce epsilon-illusory, a novel form of adversarial attack on sequential decision-makers. Compared to existing attacks, we empirically find epsilon-illusory to be significantly harder to detect with automated methods. Our findings suggest the need for better anomaly detectors, as well as effective hardware- and system-level defenses.
  arXiv  Detail & Related papers  (2022-07-20T19:49:09Z)
• Fixed Points in Cyber Space: Rethinking Optimal Evasion Attacks in the Age of AI-NIDS [70.60975663021952]
  We study blackbox adversarial attacks on network classifiers. We argue that attacker-defender fixed points are themselves general-sum games with complex phase transitions. We show that a continual learning approach is required to study attacker-defender dynamics.
  arXiv  Detail & Related papers  (2021-11-23T23:42:16Z)
• Targeted Attack on Deep RL-based Autonomous Driving with Learned Visual Patterns [18.694795507945603]
  Recent studies demonstrated the vulnerability of control policies learned through deep reinforcement learning against adversarial attacks. This paper investigates the feasibility of targeted attacks through visually learned patterns placed on physical object in the environment.
  arXiv  Detail & Related papers  (2021-09-16T04:59:06Z)
• Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attacks [62.87459235819762]
  In a real-world scenario like autonomous driving, more attention should be devoted to real-world adversarial examples (RWAEs) This paper presents an in-depth evaluation of the robustness of popular SS models by testing the effects of both digital and real-world adversarial patches.
  arXiv  Detail & Related papers  (2021-08-13T11:49:09Z)
• Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots [121.42930679076574]
  We present a model-free reinforcement learning framework for training robust locomotion policies in simulation. domain randomization is used to encourage the policies to learn behaviors that are robust across variations in system dynamics. We demonstrate this on versatile walking behaviors such as tracking a target walking velocity, walking height, and turning yaw.
  arXiv  Detail & Related papers  (2021-03-26T07:14:01Z)
• Learning a Contact-Adaptive Controller for Robust, Efficient Legged Locomotion [95.1825179206694]
  We present a framework that synthesizes robust controllers for a quadruped robot. A high-level controller learns to choose from a set of primitives in response to changes in the environment. A low-level controller that utilizes an established control method to robustly execute the primitives.
  arXiv  Detail & Related papers  (2020-09-21T16:49:26Z)

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.