Certifiable Robustness to Adversarial State Uncertainty in Deep Reinforcement Learning

• URL: http://arxiv.org/abs/2004.06496v6
• Date: Wed, 2 Feb 2022 18:48:37 GMT
• Title: Certifiable Robustness to Adversarial State Uncertainty in Deep Reinforcement Learning
• Authors: Michael Everett, Bjorn Lutjens, Jonathan P. How
• Abstract summary: Deep Neural Network-based systems are now the state-of-the-art in many robotics tasks, but their application in safety-critical domains remains dangerous without formal guarantees on network robustness. Small perturbations to sensor inputs are often enough to change network-based decisions, which was recently shown to cause an autonomous vehicle to swerve into another lane. This work leverages research on certified adversarial robustness to develop an online certifiably robust for deep reinforcement learning algorithms.
• Score: 40.989393438716476
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep Neural Network-based systems are now the state-of-the-art in many robotics tasks, but their application in safety-critical domains remains dangerous without formal guarantees on network robustness. Small perturbations to sensor inputs (from noise or adversarial examples) are often enough to change network-based decisions, which was recently shown to cause an autonomous vehicle to swerve into another lane. In light of these dangers, numerous algorithms have been developed as defensive mechanisms from these adversarial inputs, some of which provide formal robustness guarantees or certificates. This work leverages research on certified adversarial robustness to develop an online certifiably robust for deep reinforcement learning algorithms. The proposed defense computes guaranteed lower bounds on state-action values during execution to identify and choose a robust action under a worst-case deviation in input space due to possible adversaries or noise. Moreover, the resulting policy comes with a certificate of solution quality, even though the true state and optimal action are unknown to the certifier due to the perturbations. The approach is demonstrated on a Deep Q-Network policy and is shown to increase robustness to noise and adversaries in pedestrian collision avoidance scenarios and a classic control task. This work extends one of our prior works with new performance guarantees, extensions to other RL algorithms, expanded results aggregated across more scenarios, an extension into scenarios with adversarial behavior, comparisons with a more computationally expensive method, and visualizations that provide intuition about the robustness algorithm.

Related papers

• Collision Avoidance Verification of Multiagent Systems with Learned Policies [9.550601011551024]
  This paper presents a backward reachability-based approach for verifying the collision avoidance properties of Multi-Agent Feedback Loops (MA-NFLs) We account for many uncertainties, making it well aligned with real-world scenarios. We demonstrate the proposed algorithm can verify collision-free properties of a MA-NFL with agents trained to imitate a collision avoidance algorithm.
  arXiv  Detail & Related papers  (2024-03-05T20:36:26Z)
• Inter-Domain Fusion for Enhanced Intrusion Detection in Power Systems: An Evidence Theoretic and Meta-Heuristic Approach [0.0]
  False alerts due to/ compromised IDS in ICS networks can lead to severe economic and operational damage. This work presents an approach for reducing false alerts in CPS power systems by dealing with uncertainty without prior distribution of alerts.
  arXiv  Detail & Related papers  (2021-11-20T00:05:39Z)
• 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)
• Exploring Robustness of Unsupervised Domain Adaptation in Semantic Segmentation [74.05906222376608]
  We propose adversarial self-supervision UDA (or ASSUDA) that maximizes the agreement between clean images and their adversarial examples by a contrastive loss in the output space. This paper is rooted in two observations: (i) the robustness of UDA methods in semantic segmentation remains unexplored, which pose a security concern in this field; and (ii) although commonly used self-supervision (e.g., rotation and jigsaw) benefits image tasks such as classification and recognition, they fail to provide the critical supervision signals that could learn discriminative representation for segmentation tasks.
  arXiv  Detail & Related papers  (2021-05-23T01:50:44Z)
• Scalable Synthesis of Verified Controllers in Deep Reinforcement Learning [0.0]
  We propose an automated verification pipeline capable of synthesizing high-quality safety shields. Our key insight involves separating safety verification from neural controller, using pre-computed verified safety shields to constrain neural controller training. Experimental results over a range of realistic high-dimensional deep RL benchmarks demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2021-04-20T19:30:29Z)
• Generating Probabilistic Safety Guarantees for Neural Network Controllers [30.34898838361206]
  We use a dynamics model to determine the output properties that must hold for a neural network controller to operate safely. We develop an adaptive verification approach to efficiently generate an overapproximation of the neural network policy. We show that our method is able to generate meaningful probabilistic safety guarantees for aircraft collision avoidance neural networks.
  arXiv  Detail & Related papers  (2021-03-01T18:48:21Z)
• Increasing the Confidence of Deep Neural Networks by Coverage Analysis [71.57324258813674]
  This paper presents a lightweight monitoring architecture based on coverage paradigms to enhance the model against different unsafe inputs. Experimental results show that the proposed approach is effective in detecting both powerful adversarial examples and out-of-distribution inputs.
  arXiv  Detail & Related papers  (2021-01-28T16:38:26Z)
• Enforcing robust control guarantees within neural network policies [76.00287474159973]
  We propose a generic nonlinear control policy class, parameterized by neural networks, that enforces the same provable robustness criteria as robust control. We demonstrate the power of this approach on several domains, improving in average-case performance over existing robust control methods and in worst-case stability over (non-robust) deep RL methods.
  arXiv  Detail & Related papers  (2020-11-16T17:14:59Z)
• Hidden Cost of Randomized Smoothing [72.93630656906599]
  In this paper, we point out the side effects of current randomized smoothing. Specifically, we articulate and prove two major points: 1) the decision boundaries of smoothed classifiers will shrink, resulting in disparity in class-wise accuracy; 2) applying noise augmentation in the training process does not necessarily resolve the shrinking issue due to the inconsistent learning objectives.
  arXiv  Detail & Related papers  (2020-03-02T23:37:42Z)

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.