bandeauDSN_2021.jpg

final Program > june 21st

Time 

Monday, June 21th






12:00
-
13:20 (GMT+01)


:00
-
:20 ()

Doctoral Forum


Towards Automated Software Testing with Generative Adversarial Networks

  Xiujing Guo (Graduate School of Advanced Science and Engineering, Hiroshima University, Hiroshima,   Japan)


A Useful Parametric Family to Characterize NHPP-based Software Reliability Modelss

  Siqiao Li (Graduate School of Advanced Science and Engineering, Hiroshima University)


Model-Based Design, Analysis and Assessment Framework for Safety-Critical Systems

  Kuen-Long Lu (National Taipei University, Taiwan) and Yung-Yuan Chen (National Taipei University, Taiwan)


On The Sensitivity Analysis for Phase Expansion

  Jiahao Zhang (Graduate School of Advanced Science and Engineering, Hiroshima University)

13:30
-
14:10 (GMT+01)


:30
-
:10 ()




    14:20
       -
    14:50  (GMT+01)


    :20
       -
    :50 ()



    15:00
        -
    15:35   (GMT+01)


    :30
        -
    :35 ()



     15:45
         -
     16:25   (GMT+01)

    :45
       -
    :25 ()




     16:25
        -
     16:55   (GMT+01)


    :25
        -
    :55 ()

Dependable and Secure Machine Learning (DSML 2021)


Keynote 1

  Chair : Homa Alemzadeh

  Presenter : Tao Xie(Peking University)


Session 1:Dependability Analysis of ML Models

  Chair : Ibéria Medeiros (University of Lisboa)

  Paper 1 : Fault-Tolerant Low-Precision DNNs using Explainable AI Evaluation with the actual                  behavior, Muhammad Sabih, Frank Hannig, Jürgen Teich

  Paper 2 : Detecting Deep Neural Network Defects with Data Flow Analysis, Jiazhen Gu, Huanlin                 Xu, Yangfan Zhou, Xin Wang

  Paper 3 : Poisoning Attacks via Generative Adversarial Text to Image Synthesis, Keshav                  Kasichainula,Hadi Mansourifar, Weidong Shi




Keynote 2

  Chair : Karthik Pattabiraman

  Presenter : Michael Paulitsch (Intel Labs)




Session 2:Fault-Tolerant ML Systems

  Chair : Varun Chandrasekaran

  Paper 1 : RADICS: Runtime Assurance of Distributed Intelligent Control Systems                  Evaluation with the actual behavior, Brian Wheatman, Jerry Chen, Tamim Sookoor, Yair                  Amir

  Paper 2 : An Approach for Peer-to-Peer Federated Learning, Tobias Wink, Zoltan Nochta

  Paper 3 : Byzantine Fault-Tolerant Distributed Machine Learning using D-SGD and Norm-Based                 Comparative Gradient Elimination (CGE), Yuta Makino, Tuan Phung-Duc, Fumio Machida







Session 3: Dicussion





13:00
-
13:45 (GMT+01)


:00
-
:45 ()





    14:00
        -
    14:50   (GMT+01)


    :00
      -
    :50 ()







    15:00
        -
    15:30  (GMT+01)


    :00
      -
    :30 ()




    15:30
        -
    16:00  (GMT+01)


    :30
      -
    :00 ()


Data-Centric Dependability and Security (DCDS 2021)


Keynote 1:Process-aware Attack Detection in Cyber-Physical Systems - The good, the    bad,and the ugly

  Chair : Ibéria Medeiros (University of Lisboa)

  Presenter : Nils Ole Tippenhauer (Saarland University)


Session 1:Data-centric for Network Security & Privacy

  Each paper has 10 minutes Presenteration and 2 minutes of Q&A.

  Chair : Ibéria Medeiros (University of Lisboa)

  Paper 1 : USB-IDS-1: a Public Multilayer Dataset of Labeled Network Flows for IDS                  Evaluation with the actual behavior, Marta Catillo, Andrea Del Vecchio, Luciano Ocone,                  Antonio Pecchia and Umberto Villano

  Paper 2 : SMS Goes Nuclear: Fortifying SMS-Based MFA in Online Account Ecosystem, Marta                 Catillo, Andrea Del Vecchio, Luciano Ocone, Antonio Pecchia and Umberto Villano

  Paper 3 : Statistical Approach For Cloud Security: Microsoft Office 365 audit logs case study,                 Louis-Simon Létourneau, Marc Frappier and Pierre-Martin Tardif






Keynote 2:Secure and Trustworthy Federated Learning

  Chair : Ibéria Medeiros (University of Lisboa)

  Presenter : Michael Kanmp (Monash University)











Session 2:Discussion & Finals remarks








13:00
-
14:00 (GMT+01)


:00
-
:00 ()













14:10
-
15:10 (GMT+01)


:10
-
:10 ()

Application of Intelligent Technology in Security(AITS 2021)


Session 1:Vulnerability detection and Attack detection

  Each paper has 10 minutes Presenteration and 2 minutes of Q&A.

  Chair : Juhua Pu

  Paper 1 : BBregLocator: A vulnerability detection system based on bounding box regression

  Paper 2 : Automatically Constructing Peer Slices via Semantic- and Context-Aware Security                 Checks in the ;Linux Kernel

  Paper 3 : Detection Algorithm of the Mimicry Attack based on Variational Auto-Encoder

  Paper 4 : Network Intrusion Detection Based on Active Semi-supervised Learning

  Paper 5 : A Statistical Learning Model with Deep Learning Characteristics


—10 minutes break—


Session 2:IoT and Traffic secuirty

  Each paper has 10 minutes Presenteration and 2 minutes of Q&A.

  Chair : Junfeng Tian

  Paper 1 : Whether the sensitive information statement of the IoT privacy policy is consistent                  with the actual behavior

  Paper 2 : Sensitive Instruction Detection Based on the Context of IoT Sensors

  Paper 3 : Insight into traffic security: A correlation discovery of urban spatial features and                  traffic flow patterns

  Paper 4 : Authenticating Mobile Wireless Device Through Per-packet Channel State                  Information

  Paper 5 : Ant Hole: Data Poisoning Attack Breaking out the Boundary of Cluster










14:00
 -
14:50 (GMT+01)


:00
-
:50 ()
















    15:00
        -
    15:25  (GMT+01)


    :00
        -
    :25 ()





    15:25
        -
    15:50  (GMT+01)


    :25
        -
    :50
()







    16:00
        -
    16:25  (GMT+01)


    :00
        -
    :25 ()





    16:25
        -
    16:50  (GMT+01)


     :25
         -
     :50 ()

Safer Autonomous Systems (SAS 2021)


● Welcome by Hélène Waeselynck (LAAS-CNRS)

● Presenter of SAS project by Prof. Davy Pissoort (KU Leuven)

Keynote 1:SafeOps: Why we need more Monitoring and Automation in Safety Management                       and Engineering

  Chair : Hélène Waeselynck (LAAS-CNRS)

  Presenter : Peter Munk (Bosch)

  Abstract :

  As of today, the automotive industry's development processes follow the V model described in its prevalent functional safety standard, the ISO 26262:2018. Most effort is spent to achieve an acceptable residual risk at start of production (SoP) and to address safety issues  occurring ;during operating, but only little effort is put in continuously improving a product's ;safety concept after SoP. With upcoming autonomous systems functioning without a driver responsible for safe operation and operating in an open context that changes continuously, his strategy needs to be adapted. In this keynote, I will outline why we should switch to DevOps development processes that established in the IT industry and extend these to support the requirements of safety-critical autonomous systems. The first key concept to achieve this change is to identify and remove gaps in automation of mandatory safety management and engineering tasks during development. The second key concept is to leverage the available connectivity features and monitor product internal and external safety properties during operation in a live manner. Only this way we quickly identify and react to safety issues as well as thus continuously adapt and improve the safety concept of safety-critical autonomous systems to increase societies trust in them.



Keynote 2:Industry talk

  Chair : Jérémie Guiochet (LAAS-CNRS)

  Presenter : Magnus Albert (Sick AG)

  Title : Methods for Ensuring Safe Perception for Safer Autonomous Systems

  Abstract :

  Safer Autonomous Systems require safe perception. Safe perception requires a sufficiently low probability of critical malfunctions and sufficiently high detection capabilities. This talk presents methods for ensuring both aspects and gives examples of the application of these methods in an industrial setting.




Session 1: Runtime Monitoring

  Chair : Jeroen Boydens (KU Leuven)

  Paper 1 : Safety monitoring of AI-based perception functions, Raul Sena Ferreira (LAAS-CNRS,                  France)

  Paper 2 : Runtime adaptation of autonomous systems, Yuan Liao (Fraunhofer, Germany)

  Paper 3 : Runtime safety contracts for interacting autonomous systems, João Vitor Zacchi                 (Fraunhofer, Germany)


Keynote 3:Industrial talk

  Chair : Peter Munk (Bosch)

  Presenter : Pascal Traverse (Airbus)

  Title : Autonomy is in the air

  Abstract :

  Autonomy is in the air: on one hand, automation is clearly a lever to improve safety margins; on another hand technologies are maturing, pulled by the automotive market. In this context, Airbus is building a concept airplane from a blank sheet with the objective to improve human-machine teaming for better overall performance. Foundation of this new concept is that when they are made aware of the “big picture” with enough time to analyze it, humans are still the best to make strategic decisions. Autonomy technologies are the main enabler of this concept. Benefit are expected both in a two-crew cockpit and eventually in Single Pilot Operations.


Session 2:Simulation-based testing

  Chair : Mario Trapp (Fraunhofer IKS)

  Paper 1 : Design and testing guidelines for non- functional requirements of autonomous                  systems, Dejana Ugrenovic (KU Leuven, Belgium)

  Paper 2 : Generation of virtual worlds for testing autonomous robots, Luca Vittorio Sartori                 (LAAS-CNRS, France)

  Paper 3 : Design and testing guidelines for non- functional requirements of autonomous                 systems, Dejana Ugrenovic (KU Leuven, Belgium)





14:00
-
14:35 (GMT+01)


:00
-
:35 ()









14:40
-
15:25 (GMT+01)


:40
-
:25 ()







15:30
-
16:15 (GMT+01)


:30
-
:15 ()







16:20
-
17:00 (GMT+01)


:20
-
:00 ()

7th International Workshop on Safety and Security of Intelligent Vehicles – SSIV 2021 Program


● Session 1 : Security Attacks to Road Vehicles

   Chair: Michaël Lauer (LAAS-CNRS, France)

   Welcome address

   Paper 1: Vehicular Platoon Communication: Cybersecurity Threats and Open Challenges, Sean                 Taylor, Farhan Ahmad, Hoang Nga Nguyen, Siraj A. Shaikh, David Evans† and David Price

   Paper 2: SaSeVAL: A Safety/Security-Aware Approach for Validation of Safety-Critical                 Systems, Christian ;Wolschke, Behrooz Sangchoolie, Jacob Simon, Stefan Marksteiner, Tobias                 Braun and Hayk Hamazaryan


—5 minutes break—


Session 2 : Safety Evaluation and Verification of Autonomous Driving

   Chair: João Carlos Cunha (Coimbra Polytechnic, Portugal)

   Paper 3: Suraksha: A Quantitative AV Safety Evaluation Framework to Analyze Safety                  Implications of Perception Design Choices, Hengyu Zhao, Siva Kumar Sastry Hari,                  Timothy Tsai, Michael B. Sullivan, Stephen W. Keckler and Jishen Zhao

   Paper 4: Evaluation of a Fail-Over Mechanism for 1oo2D Architectures in Highly-Automated                  Driving, Rupert Schorn and Wilfried Steiner

   Paper 5: Safety Verification of Neural Network Controlled Systems, Arthur Clavière, Eric Asselin,                 Christophe Garion and Claire Pagetti


—5 minutes break—


Session 3 : Safety Certification, Assessment and Architectures

    Chair: Kalinka Branco (Universidade de São Paulo, Brazil)

    Paper 6: Certifying Emergency Landing for Safe Urban UAV, Joris Guerin, Kevin Delmas and                  Jérémie Guiochet

    Paper 7: CyberGSN: A Semi-formal Language for Specifying Safety Cases, Tewodros A. Beyene                  and Carmen Carlan

    Paper 8: A Safety Architecture for Centralized E/E Architectures, Victor Bandur, Vera Pantelic,                  Timofey Tomashevskiy and Mark Lawford


—5 minutes break—







Session 4 : Panel - Future Challenges in Safety and Security of Intelligent Vehicles