VCAT: Vulnerability-aware and Curiosity-driven Adversarial Training for Enhancing Autonomous Vehicle Robustness

• URL: http://arxiv.org/abs/2409.12997v1
• Date: Thu, 19 Sep 2024 14:53:02 GMT
• Title: VCAT: Vulnerability-aware and Curiosity-driven Adversarial Training for Enhancing Autonomous Vehicle Robustness
• Authors: Xuan Cai, Zhiyong Cui, Xuesong Bai, Ruimin Ke, Zhenshu Ma, Haiyang Yu, Yilong Ren,
• Abstract summary: Vulnerability-aware and Curiosity-driven Adversarial Training (VCAT) is a framework to train autonomous vehicles (AVs) against malicious attacks. VCAT uses a surrogate network to fit the value function of the AV victim, providing dense information about the victim's inherent vulnerabilities. In the victim defense training phase, the AV is trained in critical scenarios in which the pretrained attacker is positioned around the victim to generate attack behaviors.
• Score: 18.27802330689405
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autonomous vehicles (AVs) face significant threats to their safe operation in complex traffic environments. Adversarial training has emerged as an effective method of enabling AVs to preemptively fortify their robustness against malicious attacks. Train an attacker using an adversarial policy, allowing the AV to learn robust driving through interaction with this attacker. However, adversarial policies in existing methodologies often get stuck in a loop of overexploiting established vulnerabilities, resulting in poor improvement for AVs. To overcome the limitations, we introduce a pioneering framework termed Vulnerability-aware and Curiosity-driven Adversarial Training (VCAT). Specifically, during the traffic vehicle attacker training phase, a surrogate network is employed to fit the value function of the AV victim, providing dense information about the victim's inherent vulnerabilities. Subsequently, random network distillation is used to characterize the novelty of the environment, constructing an intrinsic reward to guide the attacker in exploring unexplored territories. In the victim defense training phase, the AV is trained in critical scenarios in which the pretrained attacker is positioned around the victim to generate attack behaviors. Experimental results revealed that the training methodology provided by VCAT significantly improved the robust control capabilities of learning-based AVs, outperforming both conventional training modalities and alternative reinforcement learning counterparts, with a marked reduction in crash rates. The code is available at https://github.com/caixxuan/VCAT.

Related papers

• Improving the Shortest Plank: Vulnerability-Aware Adversarial Training for Robust Recommender System [60.719158008403376]
  Vulnerability-aware Adversarial Training (VAT) is designed to defend against poisoning attacks in recommender systems. VAT employs a novel vulnerability-aware function to estimate users' vulnerability based on the degree to which the system fits them.
  arXiv  Detail & Related papers  (2024-09-26T02:24:03Z)
• CAT: Closed-loop Adversarial Training for Safe End-to-End Driving [54.60865656161679]
  Adversarial Training (CAT) is a framework for safe end-to-end driving in autonomous vehicles. Cat aims to continuously improve the safety of driving agents by training the agent on safety-critical scenarios. Cat can effectively generate adversarial scenarios countering the agent being trained.
  arXiv  Detail & Related papers  (2023-10-19T02:49:31Z)
• Stackelberg Driver Model for Continual Policy Improvement in Scenario-Based Closed-Loop Autonomous Driving [5.765939495779461]
  adversarial generation methods have emerged as a class of efficient approaches to synthesize safety-critical scenarios. We tailor the Stackelberg Driver Model (SDM) to accurately characterize the hierarchical nature of vehicle interaction dynamics. Our algorithm exhibits superior performance compared to several baselines especially in higher dimensional scenarios.
  arXiv  Detail & Related papers  (2023-09-25T15:47:07Z)
• Improved Adversarial Training Through Adaptive Instance-wise Loss Smoothing [5.1024659285813785]
  Adversarial training has been the most successful defense against such adversarial attacks. We propose a new adversarial training method: Instance-adaptive Smoothness Enhanced Adversarial Training. Our method achieves state-of-the-art robustness against $ell_infty$-norm constrained attacks.
  arXiv  Detail & Related papers  (2023-03-24T15:41:40Z)
• Robust Adversarial Attacks Detection based on Explainable Deep Reinforcement Learning For UAV Guidance and Planning [4.640835690336653]
  Adversarial attacks on Uncrewed Aerial Vehicle (UAV) agents operating in public are increasing. Deep Learning (DL) approaches to control and guide these UAVs can be beneficial in terms of performance but can add concerns regarding the safety of those techniques and their vulnerability against adversarial attacks. This paper proposes an innovative approach based on the explainability of DL methods to build an efficient detector that will protect these DL schemes and the UAVs adopting them from attacks.
  arXiv  Detail & Related papers  (2022-06-06T15:16:10Z)
• Adversarial Visual Robustness by Causal Intervention [56.766342028800445]
  Adversarial training is the de facto most promising defense against adversarial examples. Yet, its passive nature inevitably prevents it from being immune to unknown attackers. We provide a causal viewpoint of adversarial vulnerability: the cause is the confounder ubiquitously existing in learning.
  arXiv  Detail & Related papers  (2021-06-17T14:23:54Z)
• Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defenses [13.161104978510943]
  This survey provides a thorough analysis of different attacks that may jeopardize autonomous driving systems. It covers adversarial attacks for various deep learning models and attacks in both physical and cyber context. Some promising research directions are suggested in order to improve deep learning-based autonomous driving safety.
  arXiv  Detail & Related papers  (2021-04-05T06:31:47Z)
• Adversarial defense for automatic speaker verification by cascaded self-supervised learning models [101.42920161993455]
  More and more malicious attackers attempt to launch adversarial attacks at automatic speaker verification (ASV) systems. We propose a standard and attack-agnostic method based on cascaded self-supervised learning models to purify the adversarial perturbations. Experimental results demonstrate that the proposed method achieves effective defense performance and can successfully counter adversarial attacks.
  arXiv  Detail & Related papers  (2021-02-14T01:56:43Z)
• Investigating Robustness of Adversarial Samples Detection for Automatic Speaker Verification [78.51092318750102]
  This work proposes to defend ASV systems against adversarial attacks with a separate detection network. A VGG-like binary classification detector is introduced and demonstrated to be effective on detecting adversarial samples.
  arXiv  Detail & Related papers  (2020-06-11T04:31:56Z)
• 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.