Robust Deep Reinforcement Learning for Security and Safety in Autonomous Vehicle Systems
Authors:
- 1 November 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 307-312
Abstract
The dependence of autonomous vehicles (AVs) on sensors and communication links exposes them to cyber-physical (CP) attacks by adversaries that seek to take control of the AVs by manipulating their data. In this paper, the state estimation process for monitoring AV dynamics, in presence of CP attacks, is analyzed and a novel adversarial deep reinforcement learning (RL) algorithm is proposed to maximize the robustness of AV dynamics control to CP attacks. The attacker's action and the AV's reaction to CP attacks are studied in a game-theoretic framework. In the formulated game, the attacker seeks to inject faulty data to AV sensor readings so as to manipulate the inter-vehicle optimal safe spacing and potentially increase the risk of AV accidents or reduce the vehicle flow on the roads. Meanwhile, the AV, acting as a defender, seeks to minimize the deviations of spacing so as to ensure robustness to the attacker's actions. Since the AV has no information about the attacker's action and due to the infinite possibilities for data value manipulations, each player uses long short term memory (LSTM) blocks to learn the expected spacing deviation resulting from its own action and feeds this deviation to a reinforcement learning (RL) algorithm. Then, the attacker's RL algorithm chooses the action which maximizes the spacing deviation, while the AV's RL algorithm seeks to find the optimal action that minimizes such deviation. Simulation results show that the proposed adversarial deep RL algorithm can improve the robustness of the AV dynamics control as it minimizes the intra-AV spacing deviation.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- A data trust framework for VANETs enabling false data detection and secure vehicle tracking2017
- A colonel blotto game for interdependence-aware cyber-physical systems security in smart cities2017
- Unmanned Aerial Vehicle With Underlaid Device-to-Device Communications: Performance and TradeoffsIEEE Transactions on Wireless Communications, 2016
- Intra-Vehicle Networks: A ReviewIEEE Transactions on Intelligent Transportation Systems, 2014
- Survey on security threats and protection mechanisms in embedded automotive networks2013
- Speech recognition with deep recurrent neural networks2013
- On the Performance of Secure Vehicular Communication SystemsIEEE Transactions on Dependable and Secure Computing, 2010
- VANET alert endorsement using multi-source filters2010
- Secure vehicular communication systems: implementation, performance, and research challengesIEEE Communications Magazine, 2008
- Car-following: a historical reviewTransportation Research Part F: Traffic Psychology and Behaviour, 1999