首页/论文/2003.01782

arXiv 2003.017822020-03-03cs.CRcs.CVcs.LG

Security of Deep Learning based Lane Keeping System under Physical-World Adversarial Attack

ByteDance AI Lab（字节跳动人工智能实验室）；Northeastern University（东北大学）

Takami Sato, Junjie Shen, Ningfei Wang, Yunhan Jack Jia, Xue Lin, Qi Alfred Chen

备注：: Project page: https://sites.google.com/view/lane-keeping-adv-attack/

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Lane-Keeping Assistance System (LKAS) is convenient and widely available today, but also extremely security and safety critical. In this work, we design and implement the first systematic approach to attack real-world DNN-based LKASes. We identify dirty road patches as a novel and domain-specific threat model for practicality and stealthiness. We formulate the attack as an optimization problem, and address the challenge from the inter-dependencies among attacks on consecutive camera frames. We evaluate our approach on a state-of-the-art LKAS and our preliminary results show that our attack can successfully cause it to drive off lane boundaries within as short as 1.3 seconds.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Dirty Road Can Attack: Security of Deep Learning based Automated Lane Centering under Physical-World Attack

UC Irvine（加州大学欧文分校）；ByteDance（字节跳动）；Northeastern University（东北大学）

Automated Lane Centering (ALC) systems are convenient and widely deployed today, but also highly security and safety critical. In this work, we are the first to systematically study the security of state-of-the-art deep learning based ALC systems in their designed operational domains under physical-world adversarial attacks. We formulate the problem with a safety-critical attack goal, and a novel and domain-specific attack vector: dirty road patches. To systematically generate the attack, we adopt an optimization-based approach and overcome domain-specific design challenges such as camera fram…

2021-06-13cs.CRcs.CVcs.LG

适应但不要遗忘：面向分布偏移下车道检测的微调与对比路由

Adapt, But Don't Forget: Fine-Tuning and Contrastive Routing for Lane Detection under Distribution Shift

Florida Institute of Technology（佛罗里达理工学院）；NASA Langley Research Center（美国国家航空航天局兰利研究中心）

针对跨数据集分布偏移导致微调遗忘的问题，本文提出固定源分支、选择性微调目标分支并用监督对比学习动态路由的车道检测框架，以更少参数获得接近最优F1分数。

2025-07-22cs.CVcs.LG

Model-Agnostic Defense for Lane Detection against Adversarial Attack

University of California, Berkeley（加州大学伯克利分校）

Susceptibility of neural networks to adversarial attack prompts serious safety concerns for lane detection efforts, a domain where such models have been widely applied. Recent work on adversarial road patches have successfully induced perception of lane lines with arbitrary form, presenting an avenue for rogue control of vehicle behavior. In this paper, we propose a modular lane verification system that can catch such threats before the autonomous driving system is misled while remaining agnostic to the particular lane detection model. Our experiments show that implementing the system with a s…

2021-03-01cs.CV

On Robustness of Lane Detection Models to Physical-World Adversarial Attacks in Autonomous Driving

University of California, Irvine（加州大学欧文分校）

After the 2017 TuSimple Lane Detection Challenge, its evaluation based on accuracy and F1 score has become the de facto standard to measure the performance of lane detection methods. In this work, we conduct the first large-scale empirical study to evaluate the robustness of state-of-the-art lane detection methods under physical-world adversarial attacks in autonomous driving. We evaluate 4 major types of lane detection approaches with the conventional evaluation and end-to-end evaluation in autonomous driving scenarios and then discuss the security proprieties of each lane detection model. We…

2021-07-06cs.CRcs.CV

面向车道检测的隐蔽且有效的后门攻击：一种自然数据污染方法

Towards Stealthy and Effective Backdoor Attacks on Lane Detection: A Naturalistic Data Poisoning Approach

State Key Laboratory of Intelligent Vehicle Safety Technology, Changan Automobile（长安汽车智能车辆安全技术国家重点实验室）；National University of Singapore (Chongqing) Research Institute, Chongqing（新加坡国立大学（重庆）研究院）；Hong Kong University of Science and Technology (Guangzhou), Guangzhou（香港科技大学（广州））；National University of Singapore, Singapore（新加坡国立大学）；Ningbo University, Ningbo（宁波大学）；Sun Yat-Sen University, Guangzhou（中山大学）；Chongqing Changan Automobile Co., Ltd., Chongqing（重庆长安汽车有限公司）

本文提出DBALD框架，通过自然触发器生成提升车道检测模型的攻击成功率和隐蔽性，实验显示其在四个主流模型上的平均成功率提升10.87%。

2026-03-25cs.CR

高级自动驾驶中的横向方向定位攻击：基于车道检测的领域特定防御机会

Lateral-Direction Localization Attack in High-Level Autonomous Driving: Domain-Specific Defense Opportunity via Lane Detection

本文首次系统探索利用车道检测（LD）防御高级自动驾驶中GPS欺骗导致的横向方向定位攻击，提出$LD^3$方法，实现100%真阳性率和0%假阳性率的实时检测，并在检测到攻击时安全停车，在Baidu Apollo和Autoware上验证了其有效性与鲁棒性。

2023-07-26cs.CR

更多相关论文收起更多论文

扭曲 Warp：针对 CUDA 集体决策的非控制数据攻击

Gerrymandering the Warp: Non-Control-Data Attacks on CUDA Collective Decision

International University of La Rioja（罗霍里奥国际大学）

本文提出集体语义破坏（CSC）攻击，利用 CUDA 集体操作中的参与元数据（如掩码、谓词等）绕过安全决策，并引入集体完整性契约（CIC）防御机制。

2026-06-11cs.CR

数据安全威胁下基于大语言模型（LLM）的车辆轨迹预测的鲁棒性

Robustness of LLM-enabled vehicle trajectory prediction under data security threats

Southwest Jiaotong University（西南交通大学）；McGill University（麦吉尔大学）

本研究针对基于大语言模型（LLM）的车辆轨迹预测模型在数据安全威胁下的鲁棒性空白，提出单特征差分进化攻击并开展系统性脆弱性分析，揭示其易受对抗操纵的特性，为相关系统的鲁棒性设计提供了首个关键见解。

2025-11-14cs.AIcs.CRcs.LG

Mitigating Deep Learning Vulnerabilities from Adversarial Examples Attack in the Cybersecurity Domain

Institute of Electrical and Electronic Engineers（电气与电子工程师协会）

Deep learning models are known to solve classification and regression problems by employing a number of epoch and training samples on a large dataset with optimal accuracy. However, that doesn't mean they are attack-proof or unexposed to vulnerabilities. Newly deployed systems particularly on a public environment (i.e public networks) are vulnerable to attacks from various entities. Moreover, published research on deep learning systems (Goodfellow et al., 2014) have determined a significant number of attacks points and a wide array of attack surface that has evidence of exploitation from adver…

2019-05-09cs.CRcs.LG

Security and Privacy Issues in Wireless Mesh Networks: A Survey

This book chapter identifies various security threats in wireless mesh network (WMN). Keeping in mind the critical requirement of security and user privacy in WMNs, this chapter provides a comprehensive overview of various possible attacks on different layers of the communication protocol stack for WMNs and their corresponding defense mechanisms. First, it identifies the security vulnerabilities in the physical, link, network, transport, application layers. Furthermore, various possible attacks on the key management protocols, user authentication and access control protocols, and user privacy …

2013-02-05cs.CRcs.NI

具备后量子安全的高效全栈私有联邦深度学习

Efficient Full-Stack Private Federated Deep Learning with Post-Quantum Security

本文提出后量子安全联邦学习框架Beskar，融合安全聚合与差分隐私，优化计算开销并系统分析安全、性能与精度的权衡。

2025-05-09cs.CR

Federated Learning for Intrusion Detection in IoT Security: A Hybrid Ensemble Approach

IIT Bombay（印度理工学院孟买分校）

Critical role of Internet of Things (IoT) in various domains like smart city, healthcare, supply chain and transportation has made them the target of malicious attacks. Past works in this area focused on centralized Intrusion Detection System (IDS), assuming the existence of a central entity to perform data analysis and identify threats. However, such IDS may not always be feasible, mainly due to spread of data across multiple sources and gathering at central node can be costly. Also, the earlier works primarily focused on improving True Positive Rate (TPR) and ignored the False Positive Rate …

2021-06-25cs.AIcs.CRcs.LG

Quantitative Information Flow for Hardware: Advancing the Attack Landscape

Security still remains an afterthought in modern Electronic Design Automation (EDA) tools, which solely focus on enhancing performance and reducing the chip size. Typically, the security analysis is conducted by hand, leading to vulnerabilities in the design remaining unnoticed. Security-aware EDA tools assist the designer in the identification and removal of security threats while keeping performance and area in mind. State-of-the-art approaches utilize information flow analysis to spot unintended information leakages in design structures. However, the classification of such threats is binary…

2022-11-30cs.ARcs.CR