Posts

Final Demonstration

Final Demonstration

On June 21, the CARAMEL project presented to a panel of external observers the results in the area of cybersecurity for autonomous vehicles that have been developed since the beginning of the CARAMEL project.

The demonstration took place at Panasonic’s facilities in Langen (Hessen) in Germany. Representatives of most of the CARAMEL consortium members attended the meeting, which was attended by approximately 30 people, including external observers.

The activities of June 21 were consolidated into 2 sections, the first half of the day consisted of a technical presentation of the developments to be presented in a live demonstration. During the second part of the day, the technical part and the demonstrations were presented through simulations.

The first section of the day started with a welcome message offered by the organizers of the event (Panasonic Automotive) and by the project coordinator who also presented a technical summary of the project.

After the incredible introduction to the project, we proceeded to the technical explanation of the pillars 1 and 2 that would be presented technically in a live demonstration and with the vehicle in motion in an area of Panasonic prepared for such experiments.

The live demonstration topics correspond to the following:

  • Cyberthreat Detection and Response Techniques (Panasonic)
  • V2X interoperability (i2cat)
  • Revocation of certificates (Atos)
  • OBU HW antitampering (Nextium)
  • CARAMEL backend (Capgemini)

Once the live presentation was over, all the participants met near the conference area to socialize while the food was offered.

The second part of the day took place in the conference room prepared for simulation demonstrations.

Each member had the opportunity to present the results of their research and integrations in mitigating cyber attacks on autonomous vehicles.

The topics were subdivided into the pillars addressed by the project.

Pillar 4: Remote Control Vehicle activities presentation

  • Intrusion detection and estimation algorithm in the Gateway & RCV controller

Pillar 1: Autonomous mobility simulations

  • Location Spoofing attack (AVL)
  • Robust scene analysis and understanding via multimodal fusion (UPAT)
  • DriveGuard countering camera attacks against autonomous vehicles (UCY)
  • Traffic sign tampering detection and mitigation (0Inf)

Pillar 2: Connected Mobility

  • Attack on the V2X Message Transmission  (i2cat)
  • OBU HW antitampering (Nextium)
  • Certificate Revocation (Atos)
  • Collaborative GPS Spoofing (UPAT)
  • Holisitc Situational Awareness with ML Application

Pillar 3: Electromobility

  • Remote detection of cyber attacks on EV Charge Stations from cloud back office (Greenflux)

It only remains to say that we appreciate the participation of each of the attendees at this event, thank you for your excellent participation.  To the readers, we would like to invite you to follow us on our official channels to keep up with the latest news on the project.

CARAMEL Webinar IoTS

CARAMEL Webinar IoTS

During the IoT Solutions World Congress 2022 CARAMEL partners organised a recorded a video webinar that explain some of the most important outcomes of the project.

In such Webinar the CARAMEL’s project coordinator gave a small introduction to introduce the 4 main pillars addressed by the project, after which members of the project presented the innovations being demonstrated as part of the CARAMEL testbed.

This webinar is accessible from CARAMEL’s Youtube channel.

Final Demonstration Preparation

Final Demonstration Preparation

As part of the final demonstration activities to be presented in Frankfurt prior to the final review. A series of preparation activities were carried out at the project’s technical demonstration facilities.

During these 2 days, different integration activities were carried out aiming to avoid or identify and mitigate any kind of adverse situation during the final demonstration. The antennas were integrated to provide interoperability between the different radio communication technologies targeted by the project. The OBU modules that contain the security mechanism against hardware modification were tested. Additionally, the project members integrated the communication from the anti-hacking device with the CARAMEL backend. This backend service communication can collect, analyse and inform other devices about threats detected previously by the connected vehicles. This whole ecosystem of technology allows strengthening the idea that would allow the future to achieve safe roads for connected vehicles.

MEC and Road Side Unit Controller
Radio commmunication devices
CARAMEL at the IoT Solutions World Congress

CARAMEL at the IoT Solutions World Congress

The CARAMEL project had a successful participation in the activities of the IoTS WC, thanks to the participation of more than 400 people who were interested in the project and who were offered a personalised explanation through the official project tours or the individual conversation, to inform them about the most outstanding results of the project.

We are grateful for the participation of all the members of the consortium who prepared the videos shown during the days of the congress. We highlight the participation of I2Cat, Capgemini, Panasonic, Atos and Nextium who had the opportunity to be in the testbed offering specific information about the project to each of the visitors to the CARAMEL testbed.

It is relevant to mention that thanks to the participation in this event we were able to establish communication with several cybersecurity organisations through which we will look for future collaboration opportunities.

We appreciate the participation of each visitor because without their visit the CARAMEL testbed demonstration would not have been the same.

We invite you to follow the official project channels where we share the latest news and upcoming events of the project.

H2020 Caramel Project (@caramel_project) / Twitter

https://www.linkedin.com/company/13066014

21st GA meeting

21st GA meeting

Today is being held the CARAMELs 21st general assembly among all members of the consortium. After some months of reluctance to have these live conversations, it is the first face-to-face meeting.

The meeting takes place on the premises of the University of Cyprus, in the library. (Learning Resource Centre – Library “Stelios Ioannou”) Aglantzia, Nicosia.

In this meeting, the project focuses on organising the activities necessary to carry out the final demonstrations of the project, i.e. the participation of the IoTS WC as well as during the final evaluation.

It is also planned to synchronise the activities carried out during the duration of the project so that they are completed on time.

One of the objectives of CARAMEL focuses on designing and implementing detection and response techniques based on artificial intelligence and multimodal fusion of sensors available on autonomous vehicles to mitigate attacks on autonomous vehicles.

CARAMEL at DATE 2022

CARAMEL at DATE 2022

During this event the CARAMEL project participated in the discussion session dedicated to providing a platform for discussion of opportunities and collaborations for innovation and research in Europe, in which the project’s technical coordinator Peter Hofmann took part in the important panel session “The Good, the Bad and the Trendy of Multi-Partner Research Projects in Europe”. Although the conference was originally scheduled to be held in a face-to-face format, it had to be reorganised at short notice to an online format.

Besides the presentation of CARAMEL project a CARAMEL paper was presented as part of conference’s activities

A Comprehensive Solution for Securing Connected and Autonomous Vehicles

  1. What makes the project concept unique?
    In the CARAMEL project, we strive to implement machine-learning based detection of attacks against the connected and/or autonomous vehicle by analysing sensor data, V2X data, and the status of embedded controllers like the OBU (on-board unit) in real-time using a tamper-proof device that directly integrated into the car – the anti-hacking device (AHD). This architecture and concept are novel and innovative, and CARAMEL is the first project to implement and demonstrate this.
  2. What project outcomes can be of use to the DATE 2022 community?
    Even as CARAMEL implements its concepts and architectures in the automotive space, the key CARAMEL innovations are transferable to other IoT and Embedded applications domains as well, such as factory floors, building automation systems or others. Therefore, the CARAMEL presentation and presence of CARAMEL representatives during the conference would be of value to the DATE 2022 community.
  3. What inputs (solutions) are expected from the DATE 2022 community?
    In the CARAMEL project, several integration options for the anti-hacking device based on different IoT devices have been pursued already. However, for the concept to be commercially viable and cost-effective, the concept of a machine-learning-based intrusion device must be even better integrated into commercial offerings for the Automotive and IoT market. The DATE 2022 community could provide valuable input for that endeavour.
  4. What new research topics and trends does the project introduce?
    CCAM and IoT both will face important security challenges in the future as bad actors discover these new areas for their activities. Since bad actors will use machine learning to subvert machine-learning-based processes and algorithms in the CCAM and IoT world (eg. using Generative Adversarial Networks (GAN)), a trend in the security industry is also to use machine learning to detect and counter these attacks. The CARAMEL project showcases this approach in the Automotive context.

Project partners:

  • Fundació Privada i2CAT, Internet i Innovació digital a Catalunya, Spain
  • DEUTSCHE TELEKOM SECURITY GMBH, Germany
  • ALTRAN DEUTSCHLAND SAS & CO KG, Germany
  • EIGHT BELLS LTD, Cyprus
  • UBIWHERE LDA, Portugal
  • CYBERLENS BV, Netherlands
  • GREENFLUX ASSETS BV, Netherlands
  • SIDROCO HOLDINGS LIMITED, Cyprus
  • 0 INFINITY LIMITED, UK
  • UNIVERSITY OF CYPRUS, Cyprus
  • University of Patras, Greece
  • Idneo Technologies SAU, Spain
  • AVL LIST GmbH, Austria
  • PANASONIC AUTOMOTIVE SYSTEMS EUROPE GMBH, Germany
  • ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, South Korea
  • KOREA AUTOMOTIVE TECHNOLOGY INSTITUTE, South Korea
  • MOBIGEN CO LTD, Republic of Korea
  • ATOS IT SOLUTIONS AND SERVICES IBERIA SL, Spain
CARAMEL at the DATE2022

CARAMEL at the DATE2022

The DATE2022 conference is intended as a meeting point for researchers, software and hardware designers, manufacturers of electronic circuitry, among others, to focus on technology and systems.

During this event the CARAMEL project participated in the discussion session dedicated to providing a platform for discussion of opportunities and collaborations for innovation and research in Europe, in which the project’s technical coordinator Peter Hofmann took part in the panel session “The Good, the Bad and the Trendy of Multi-Partner Research Projects in Europe“.

Although the conference initially had to be held face-to-face, it had to be reorganized in the short term towards an online format.

  • What makes the project concept unique?
    In the CARAMEL project, we strive to implement machine-learning based detection of attacks against the connected and/or autonomous vehicle by analysing sensor data, V2X data, and the status of embedded controllers like the OBU (on-board unit) in real-time using a tamper-proof device that directly integrated into the car – the anti-hacking device (AHD). This architecture and concept are novel and innovative, and CARAMEL is the first project to implement and demonstrate this.
  • What project outcomes can be of use to the DATE 2022 community?
    Even as CARAMEL implements its concepts and architectures in the automotive space, the key CARAMEL innovations are transferable to other IoT and Embedded applications domains as well, such as factory floors, building automation systems or others. Therefore, the CARAMEL presentation and presence of CARAMEL representatives during the conference would be of value to the DATE 2022 community.
  • What inputs (solutions) are expected from the DATE 2022 community?
    In the CARAMEL project, several integration options for the anti-hacking device based on different IoT devices have been pursued already. However, for the concept to be commercially viable and cost-effective, the concept of a machine-learning-based intrusion device must be even better integrated into commercial offerings for the Automotive and IoT market. The DATE 2022 community could provide valuable input for that endeavour.
  • What new research topics and trends does the project introduce?
    CCAM and IoT both will face important security challenges in the future as bad actors discover these new areas for their activities. Since bad actors will use machine learning to subvert machine-learning-based processes and algorithms in the CCAM and IoT world (eg. using Generative Adversarial Networks (GAN)), a trend in the security industry is also to use machine learning to detect and counter these attacks. The CARAMEL project showcases this approach in the Automotive context.
  • Technical Meeting

    Technical Meeting




    Today, the CARAMEL consortium started a technical meeting among all participants to synchronise the activities carried out to achieve the proposed goals and present the challenges related to the integration of the various research tasks carried out over the last months.
     
    We can recall that one of the objectives of CARAMEL focuses on designing and implementing detection and response techniques based on artificial intelligence and multimodal fusion of the sensors available in autonomous vehicles. In addition, to obtain a deep learning technique that can be used in anticipation of cyber-attacks that intend to perform malicious activities on the autonomous vehicle.
     
    The meeting was opened by Petros Kapsalas, who updated the activities carried out as part of Work Package #6.
     
    Thus, the advantages of artificial intelligence as a mitigation technique to counter elaborate attacks were mentioned.
    Later, the consortium members were reminded about the used vehicle to demonstrate the project’s outcomes in the final review.
     
    Afterwards, each consortium member involved in activities related to pillar 1: Autonomous Mobility, presented their progress to synchronise efforts in a timely manner.
    CARAMEL 2nd OEM & Partner Workshop

    CARAMEL 2nd OEM & Partner Workshop

    The CARAMEL project will held the second OEM and Partners workshop on 16 November 2021, from 14:00 to 17:00. This workshop aims to present the most outstanding results of the research and development carried out by the different members of the consortium. Furthermore, this workshop is also oriented to OEM representatives, which could increase the visibility of the project and collect opinions on the topics addressed by CARAMEL.

    The objective of this workshop will be to highlight the achieved results toward the development of Artificial Intelligence-based cybersecurity for connected and automated vehicles.

    The CARAMEL project bases its research on 4 fundamental pillars for the safety of connected autonomous vehicles.

    Main Pillars of the project:

    Pillar 1: Autonomous Mobility
    Pillar 2: Connected mobility
    Pillar 3: Electromobility
    Pillar 4: Remote Control Vehicle (RCV)

    Autonomous Mobility

    • Taxonomy of the attacks.
    • Cyber attacks Detection and Mitigation on Sensing and Navigation modalities.
    • Elevation of Perception Engines as core modules for cyber-attack detection  & mitigation engines.
      • Towards robustifying D-CNNs to tackle adversarial attacks on the scene layer.
    • Multimodality and Redundancy of Sensors beat malicious attacks on CAVs.
    • Fall back actions to enhance safety.
    • Key Performance Indicators for assessing Mitigation Performance.

    Connected mobility

    • Interoperability between radio technologies for V2X communications
    • Secure V2X communications and related hardware
    • GNSS, V2X and HW attack detection and response process
    • Vehicle tracking using its signature certificates

    Electromobility

    • Communication architecture of an EV charging network

    Remote Control Vehicle (RCV)

    • ML-based traffic between 5G-RCV 
    • Control Center anomaly detection
    • prediction algorithm development

    Don’t miss this excellent opportunity to learn more about the activities carried out to develop cybersecurity based on artificial intelligence for autonomous and connected vehicles.

    CARAMEL at MMSP 2021

    CARAMEL at MMSP 2021

    The IEEE 23rd International Workshop on Multimedia Signal Processing, organised by the IEEE Signal Processing Society, Centre for Immersive Visual Technologies and Tampere University, will be held from 6th-8th October in Tampere, Finland.

    The congress will be the meeting point for professionals from academia and industry developing or are carrying out projects in the field of multimedia signal processing, aiming to share knowledge, exchange ideas and explore future research directions.

    The IEEE MMSP 2021 is a hybrid event. This includes the face-to-face gathering at Scandic Hotel Rosendahl and online engagement through a virtual platform.

    This event will include the presence of the University of Patras members of the CARAMEL consortium, who will be presenting the paper:

    Deep multi-modal data analysis and fusion for robust scene understanding in CAVs

    Deep learning (DL) tends to be the integral part of Autonomous Vehicles (AVs). Therefore the development of scene analysis modules that are robust to various vulnerabilities such as adversarial inputs or cyber-attacks is becoming an imperative need for the future AV perception systems. In this paper, we deal with this issue by exploring the recent progress in Artificial Intelligence (AI) and Machine Learning (ML) to provide holistic situational awareness and eliminate the effect of the previous attacks on the scene analysis modules. We propose novel multi-modal approaches against which achieve robustness to adversarial attacks, by appropriately modifying the analysis Neural networks and by utilizing late fusion methods. More specifically, we propose a holistic approach by adding new layers to a 2D segmentation DL odel enhancing its robustness to adversarial noise. Then, a novel late fusion technique has been applied, by extracting direct features from the 3D space and project them into the 2D segmented space for identifying inconsistencies. Extensive evaluation studies using the KITTI odometry dataset provide promising performance results under various types of noise.

    7th October 2021

    The IEEE 23rd International Workshop on Multimedia Signal Processing

    Theme: Elation by Kaira.