Mlia Modulated Led Illuminationbased Adversarial Attack On Traffic Sign Recognition System For Autonomous Vehicle

• doi: 10.1109/TrustCom56396.2022.00139
• title: MLIA: modulated LED illumination-based adversarial attack on traffic sign recognition system for autonomous vehicle
• publisher: IEEE
• isbn: 978-1-6654-9426-7
• issn: 2324-898X
• rank: 2968
• access_type: LOCKED
• content_type: Conferences
• abstract: Traffic sign recognition (TSR) system is essential for autonomous vehicle and is vulnerable to security threats from adversarial attacks. The existing adversarial attacks for TSR are invasive and suffer from poor concealment and high computational complexity, and thus have low feasibility in real-world scenarios. This paper proposes a non-invasive modulated LED illumination-based adversarial attack scheme. By generating luminance flashes imperceptible to human eyes through fast intensity modulation of lighting such as LED streetlights and exploiting the rolling shutter mechanism of CMOS sensors of in-vehicle imaging system, the proposed attack scheme can successfully perform adversarial attacks on TSR system by implanting luminance information perturbations into the images acquired by autonomous vehicle and thus poisoning the image data fed into TSR system. Depending on the modulation frequency and pattern of LED illumination, the proposed attack scheme enables denial of service (DoS) attack that leads to traffic sign detection failure and escape attack that leads to traffic sign misclassification, with the advantages of superior concealment, low computational complexity and high practical feasibility. Experiments are conducted with two benchmark datasets (GTSDB and GTSRB) and two state-of-the-art models of TSR detection and TSR classification, YOLOv5m and Sill-Net respectively, in both the digital and physical world. Experimental results show that the proposed DoS attack on the TSR detection model (YOLOv5m) can reach the success rate of 90.00% and the proposed escape attack on the TSR classification model (Sill-Net) can achieve the success rate of 35.00%.
• article_number: 10063453
• pdf_url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10063453
• html_url: https://ieeexplore.ieee.org/document/10063453/
• abstract_url: https://ieeexplore.ieee.org/document/10063453/
• publication_title: 2022 IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)
• conference_location: Wuhan, China
• conference_dates: 9-11 Dec. 2022
• publication_number: 10063338
• is_number: 10063342
• publication_year: 2022
• publication_date: 9-11 Dec. 2022
• start_page: 1020
• end_page: 1027
• citing_paper_count: 1
• citing_patent_count: 0
• download_count: 543
• insert_date: 20230320
• index_terms:
  • ieee_terms:
    • Computational modeling
    • Lighting
    • Benchmark testing
    • Light emitting diodes
    • Sensor systems
    • Sensors
    • Security
  • author_terms:
    • Autonomous vehicle
    • Adversarial attack
    • Traffic sign recognition
    • Modulated LED illumination attack
  • dynamic_index_terms:
    • Light Signal
    • Traffic Signal
    • Autonomous Vehicles
    • Autonomous Driving
    • Adversarial Attacks
    • Traffic Sign Recognition
    • Sign Recognition System
    • Traffic Sign Recognition System
    • Computational Complexity
    • Benchmark Datasets
    • Benchmark Data Sets
    • Human Eye
    • Human Eyes
    • Real-world Scenarios
    • Physical World
    • Low Computational Complexity
    • Digital World
    • Denial Of Service
    • Denial-of-service Attacks
    • Denial Of Service Attacks
    • Denial-of-service
    • Practical Feasibility
    • Attack Strategy
    • Attack Scheme
    • Fast Modulation
    • Low Feasibility
    • Rolling Shutter
    • Light-emitting Diodes
    • LED Light
    • Light Emission
    • LEDs
    • Adversarial Examples
    • Physical Attacks
    • Useless Information
    • Attack Methods
    • Attack Method
    • Edge Features
    • Attack Rate
    • Misinformation
    • Misleading Information
    • False Information
    • Gradient Information
    • Image Pixels
    • Subset Of Images
• isbn_formats:
  • format: Print on Demand(PoD) ISBN, value: 978-1-6654-9426-7, isbnType: New-2005
  • format: Electronic ISBN, value: 978-1-6654-9425-0, isbnType: New-2005
• authors:
  • Author Name: Yixuan Shen
    Affiliation: Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications, Guangzhou, China
    Author URL: https://ieeexplore.ieee.org/author/37089766680
    ID: 37089766680
    Order: 1
    Author Affiliations:
    • Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications, Guangzhou, China
    • Guangdong Provincial Engineering Technology Research Center on VLC, Guangzhou, China
    • Guangzhou Municipal Key Laboratory of Engineering Technology on VLC, Guangzhou, China
    • Department of Optoelectronic Engineering, Jinan University, Guangzhou, China
  • Author Name: Yu Cheng
    Affiliation: Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications, Guangzhou, China
    Author URL: https://ieeexplore.ieee.org/author/37089770302
    ID: 37089770302
    Order: 2
    Author Affiliations:
    • Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications, Guangzhou, China
    • Guangdong Provincial Engineering Technology Research Center on VLC, Guangzhou, China
    • Guangzhou Municipal Key Laboratory of Engineering Technology on VLC, Guangzhou, China
    • Department of Optoelectronic Engineering, Jinan University, Guangzhou, China
  • Author Name: Yini Lin
    Affiliation: Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications, Guangzhou, China
    Author URL: https://ieeexplore.ieee.org/author/37089766684
    ID: 37089766684
    Order: 3
    Author Affiliations:
    • Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications, Guangzhou, China
    • Guangdong Provincial Engineering Technology Research Center on VLC, Guangzhou, China
    • Guangzhou Municipal Key Laboratory of Engineering Technology on VLC, Guangzhou, China
    • Department of Optoelectronic Engineering, Jinan University, Guangzhou, China
  • Author Name: Sicheng Long
    Affiliation: Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications, Guangzhou, China
    Author URL: https://ieeexplore.ieee.org/author/37089766210
    ID: 37089766210
    Order: 4
    Author Affiliations:
    • Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications, Guangzhou, China
    • Guangdong Provincial Engineering Technology Research Center on VLC, Guangzhou, China
    • Guangzhou Municipal Key Laboratory of Engineering Technology on VLC, Guangzhou, China
    • Department of Optoelectronic Engineering, Jinan University, Guangzhou, China
  • Author Name: Canjian Jiang
    Affiliation: Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications, Guangzhou, China
    Author URL: https://ieeexplore.ieee.org/author/37089480732
    ID: 37089480732
    Order: 5
    Author Affiliations:
    • Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications, Guangzhou, China
    • Guangdong Provincial Engineering Technology Research Center on VLC, Guangzhou, China
    • Guangzhou Municipal Key Laboratory of Engineering Technology on VLC, Guangzhou, China
    • Department of Optoelectronic Engineering, Jinan University, Guangzhou, China
  • Author Name: Danjie Li
    Affiliation: Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications, Guangzhou, China
    Author URL: https://ieeexplore.ieee.org/author/37089768835
    ID: 37089768835
    Order: 6
    Author Affiliations:
    • Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications, Guangzhou, China
    • Guangdong Provincial Engineering Technology Research Center on VLC, Guangzhou, China
    • Guangzhou Municipal Key Laboratory of Engineering Technology on VLC, Guangzhou, China
    • Department of Optoelectronic Engineering, Jinan University, Guangzhou, China
  • Author Name: Siyuan Dai
    Affiliation: Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications, Guangzhou, China
    Author URL: https://ieeexplore.ieee.org/author/37089765651
    ID: 37089765651
    Order: 7
    Author Affiliations:
    • Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications, Guangzhou, China
    • Guangdong Provincial Engineering Technology Research Center on VLC, Guangzhou, China
    • Guangzhou Municipal Key Laboratory of Engineering Technology on VLC, Guangzhou, China
  • Author Name: You Jiang
    Affiliation: Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications, Guangzhou, China
    Author URL: https://ieeexplore.ieee.org/author/37089769190
    ID: 37089769190
    Order: 8
    Author Affiliations:
    • Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications, Guangzhou, China
    • Guangdong Provincial Engineering Technology Research Center on VLC, Guangzhou, China
    • Guangzhou Municipal Key Laboratory of Engineering Technology on VLC, Guangzhou, China
    • Department of Optoelectronic Engineering, Jinan University, Guangzhou, China
  • Author Name: Junbin Fang
    Affiliation: Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications, Guangzhou, China
    Author URL: https://ieeexplore.ieee.org/author/37398098000
    ID: 37398098000
    Order: 9
    Author Affiliations:
    • Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications, Guangzhou, China
    • Guangdong Provincial Engineering Technology Research Center on VLC, Guangzhou, China
    • Guangzhou Municipal Key Laboratory of Engineering Technology on VLC, Guangzhou, China
    • Department of Optoelectronic Engineering, Jinan University, Guangzhou, China
  • Author Name: Zoe Lin Jiang
    Affiliation: Harbin Institute of Technology, Shenzhen, China
    Author URL: https://ieeexplore.ieee.org/author/37405776600
    ID: 37405776600
    Order: 10
    Author Affiliations:
    • Harbin Institute of Technology, Shenzhen, China
  • Author Name: Siu-Ming Yiu
    Affiliation: Department of Computer Science, The University of Hong Kong, Hong Kong, China
    Author URL: https://ieeexplore.ieee.org/author/37267995800
    ID: 37267995800
    Order: 11
    Author Affiliations:
    • Department of Computer Science, The University of Hong Kong, Hong Kong, China

Image Sensor

• sensor_type: CMOS
• resolution: 7296x5472
• dynamic_range: Not specified
• pixel_size: Not specified
• dark_current: Not specified

Optical Data

• focal_length: Not specified
• aperture: Not specified
• field_of_view: Not specified
• distortion: Not specified

Performance Metrics

Applications & Benefits

• cell_imaging: Not specified
• benefits: Not specified

Supporting Organizations

• supported_by: National Key Research and Development Program of China, National Natural Science Foundation of China, European Union’s Horizon 2020 research and innovation programme, HKU-SCF FinTech Academy, theme-based research funding of RGC from the HK Government.

Manuscript Details

• publication_date: 9-11 Dec. 2022

Relevancy Score

• score: 9
• missing_fields:
  • dark_current
  • dynamic_range
  • sensitivity
  • shutter_speed
  • fill_factor
  • quantum_efficiency
  • power_consumption
  • frame_rate
  • signal_to_noise_ratio

Processed JSON Filename

request_2bb0ae44-a41c-4cea-99cb-f6b58d235d3f-mlia_modulated_led_illuminationbased_adversarial_attack_on_traffic_sign_recognition_system_for_autonomous_vehicle.json