Posts

[T42] The Sixth Sense for AI Algorithms: Challenges on Confidentiality, Trust and Security for Mobile Devices – Soumya Banerjee (Trasna)

On Fri, Jan 31th, 2025, 2pm CET, we welcome Soumya Banerjee (Trasna), for another edition of TALK.CYBERcni.fr on “The Sixth Sense for AI Algorithms: Challenges on Confidentiality, Trust and Security for Mobile Devices”. Share and join!

Explore the intricate challenges of protecting AI and machine learning models in hardware-assisted Trusted Execution Environments (TEEs). Soumya will delve into the vulnerabilities of modern mobile devices, from API extraction threats to intellectual property protection for ML models, including attacks targeting Graph Neural Networks and Large Language Models. Gain insights into cutting-edge strategies for safeguarding the confidentiality and security of AI models while addressing fragmentation, transparency, and interoperability in TEEs. Don’t miss this essential discussion for AI and mobile security innovators!

You are cordially invited to join the free live stream on youtube and LinkedIn! Please share the link https://talk.cybercni.fr/42 with your interested friends!

Trailer: 
LinkedIN Event: https://www.linkedin.com/posts/2pahl_confidentiality-security-ai-activity-7276883814243520515-GsXM
Facebook Event: https://www.facebook.com/events/800560978874219/
Youtube: https://www.youtube.com/watch?v=2rj7Uvg4ckE&list=PLdftPKA9mTfaDJxqwexil2mPhUFIA9ITd
Stream redirect (for every edition): https://TALK.cyberCNI.fr/stream

Newsletter with invitations: Subscription on https://TALK.cyberCNI.fr

Help us spreading the news

The best talks are those with an interested diverse audience! Therefore, please use the following media to spread the news in your networks: 

Thank you!

Abstract

The plethora of AI & ML algorithms have impacted different dimensions of use-cases while encompassing hardware and mobile communication devices as well. Hence,there are arguments how and how far the wide spread of AI/ ML algorithms could envisage Confidentiality of the algorithms and there embedded devices.

Significantly, since years Hardware-assisted trusted execution environments (TEEs) foster small pieces of trusted software on a holistic computing device to be distinguished from the rest of the software on the same device, including the OS and other applications. At present TEEs have become more ubiquitous. Almost every smartphone or tablet is likely to have a processor with TEE capabilities. Nevertheless, the availability of 3rd party App ( including AI)on each mobile devices also offers crucial challenges in protecting Intellectual Property associated with machine learning models, when the machine learning application needs to be distributed to the client with the ML model aggregated within it. However, already there exists potential attack vectors against TEEs and concerns relating to fragmentation, interoperability, and transparency. With Secured TEEs to protect AI/machine learning models can be trespassed through API extraction. Therefore, Confidentiality, trust and security of mobile devices can be compromised. This talk will usher substantial measures to protect the Confidentiality, trust and security of machine learning models for device oriented TEEs. The content will cover various ML model based attacks with respect to Graph Neural Networks, Large Language Model & Deep Learning and also certain progressive measures towards ownership resolution of the trusted ML models . As the area is still unexplored, therefore as future research it could envisage extreme importance for medium and large enterprises both for device manufacturers or mobile communication.

Motivational Refernce: https://arxiv.org/pdf/2308.09552

Watch the trailer linked above!

Soumya Banerjee

Dr. Soumya Banerjee, Senior Vice President Innovation (Trasna-Solutions Ltd. ) & Senior researcher, University College Cork, Ireland has been specialized with Computational Intelligence, Machine Learning, Security and Blockchain across smart & connected environmnets almost for 2 decades envisaging both research & teaching. Prior to Trasna & UCC , he was invited research professor CNRS-INSA De Lyon, France, TU Ostrava Cz Republic, CNAM-CEDRIC, Paris and still he is an adjunct senior researcher INRIA-EVA, Paris, France. He has more than 150 peer reviewd publications (IEEE, Elsevier, Springer-Verlag, et.) and he has an European patent on bio-inspired Algorithm during 2009-2011.

TRASNA SOLUTIONS

TRASNA SOLUTIONS is a well-known manufacturer of SIM Cards and eSIMs / eUICCs enabling amongst others the connectivity of IoT boards and IoT devices. Based is in Ireland, Germany, Bostnia, Slovenia, France & Turkey across Europe,  Trasna has its own GSMA accredited facility. Furthermore, Trasna offers solutions to address connectivity challenges across IoT paradigms. They are actively participating in industrial research &  development on Post Quantum Cryptography, Identity Mangement, Blockchain and Machine Learning to explore industrial use-csaes.

The Cyber CNI Lecture Series is a free monthly event that typically takes place on the last Friday of the month from 2pm to 3h30pm CET.

The Cyber CNI Speaker series aims to raise awareness and understanding of cyber security issues among all audiences. It aims to enable an ongoing dialogue between experts from industry and academia and the general public (citizens, families, small and large businesses, public organizations, etc.). All of us are concerned.

The events are broadcast live on Youtube (https://talk.cybercni.fr/) and LinkedIn, allowing worldwide remote participation – including a tool to participate in the discussion.

You can add the event calendar via ICSwebcalHTML.

How the digital transformation is changing our lives

Our society relies more and more on information and operational technologies. Examples include water, energy, heat and cooling supply, communications, healthcare, production and processing of goods, transportation, national security, banking, research and education, and food production.

What all these areas have in common is that they make intensive use of networked distributed computer systems. These systems can be attacked in many ways. This is no longer just a problem for computer “pros” because computer systems are essential to all of us. The effects of “cyber-attacks” range from power outages to the collapse of the health care or banking sectors.

Program and registration: https://talk.cybercni.fr/

Recap of the GFA Startup Learning Expedition 2024 in Munich


During this second part of the Learning Expedition, which took place on Sept.30 until October 2, 2024, French startups from the IMT and Inria incubators came to Munich to discover the Bavarian startup ecosystem.

[T36] Dynamic Cybersecurity Risk Management with Responsible AI Practice  for Enhancing Security and Resilience of Digital Infrastructure – Shareeful Islam

On Fri, July 26th, 2024, 2h00pm CET, we welcome Shareeful Islam from Anglia Ruskin University, UK for another edition of TALK.CYBERcni.fr on “Dynamic Cybersecurity Risk Management with Responsible AI Practice  for Enhancing Security and Resilience of Digital Infrastructure – Shareeful Islam”. Share and join!
We are excited to welcome Dr. Shareeful Islam from Anglia Ruskin University for a compelling talk on “Dynamic Cybersecurity Risk Management with Responsible AI Practice for Enhancing Security and Resilience of Digital Infrastructure.” In this session, Dr. Islam will address the growing sophistication of cyberattacks and the critical need for dynamic cybersecurity risk management. Learn how hybrid AI-enabled models, combining linear regression and deep learning, can help manage risks more effectively and ensure the development of trustworthy AI systems.

You are cordially invited to join the free live stream on youtube and LinkedIn! Please share the link https://talk.cybercni.fr/36 with your interested friends!

Trailer: https://youtu.be/lcDndbVe8ds
LinkedIN Event: https://www.linkedin.com/events/7221126855918063619
Facebook Event: https://www.facebook.com/events/366087109924061/
Youtube: https://www.youtube.com/watch?v=3ZSARwpfwgA&list=PLdftPKA9mTfaDJxqwexil2mPhUFIA9ITd
Stream redirect (for every edition): https://TALK.cyberCNI.fr/stream

Newsletter with invitations: Subscription on https://TALK.cyberCNI.fr

Help us spreading the news

The best talks are those with an interested diverse audience! Therefore, please use the following media to spread the news in your networks: 

Thank you!

Abstract

The sophistication of cyberattacks has significantly increased, making it almost certain that organizations can be victims of cyberattacks at any time. Managing cybersecurity risk is critical for any organization so that informed decisions can be made to tackle risks before they materialize. However, performing effective risk management is always challenging due to the constant changes in organizational infrastructure and security posture, including the adoption of new applications and the reconfiguration or updating of existing assets and their dependencies, as well as the potential exploitation of vulnerabilities. Despite the wider adoption of AI enabled solution in  cybersecurity , but lack of focus on the analysing  dynamic parameters using AI models  and their integration into cybersecurity  risk management. Additionally, AI-enable cybersecurity solution needs to assure the Responsible AI practice for trustworthy AI system development and use 

This talk presents dynamic Cyber Security Risk Management (d-CSRM)) to tackle this challenge by integrating for assessing and managing the risk. It considers hybrid AI-enabled model that combines both linear regression and deep learning,  with responsible AI practice to assess the risk.

Watch the trailer linked above!

Shareeful Islam

Dr. Shareeful Islam is an Associate Professor  in Cybersecurity at the Faculty of Science and Engineering, Anglia Ruskin University(ARU). He is currently visiting professor LUT School of Engineering Sciences, Lappeenranta, Finland and  previously worked as a visiting professor at the National Institute of Informatics (NII), Japan, and a visiting researcher at SBA Research, Austria. He has over 22 years of experience in teaching , administration, and research. He published more than 90 papers and secured ca 1.5 M £ funding mostly from the national and EU funding agency with experienced with lead and manage project. He has  successfully supervised to timely completion 11 PhDs and MPhils and currently leading Horizon project for ARU. He has published more than 90  papers in different top ranked journals and conferences. His research interest includes cybersecurity risk management, Responsible AI, AI-enabled cyber security, and regulatory compliance.

About the Anglia Ruskin University (ARU)

named one of the top 40 universities in the UK and top 350 institutions in the world, in the Times Higher Education (THE) World University Rankings in 2023.  ARU teaching and research focuses on Chelmsford, Cambridge, Peterborough and rated Gold in the Teaching Excellence Framework   The school of computing and information science  boasts state-of-the-art research facilities, equipped with the latest technology and resources necessary for conducting advanced research in cybersecurity. CIS includes a number of online specialized labs including threat and forensic analysis, penetration testing, and evidence visualization.  CIS is a dynamic hub for academic excellence and innovation in the field of computer science, information technology, and cybersecurity.  Faculty members of CIS are distinguished experts in cybersecurity, artificial intelligence, and network defence.

Talk.cybercni.fr

The Cyber CNI Lecture Series is a free monthly event that typically takes place on the last Friday of the month from 2pm to 3h30pm CET.

The Cyber CNI Speaker series aims to raise awareness and understanding of cyber security issues among all audiences. It aims to enable an ongoing dialogue between experts from industry and academia and the general public (citizens, families, small and large businesses, public organizations, etc.). All of us are concerned.

The events are broadcast live on Youtube (https://talk.cybercni.fr/) and LinkedIn, allowing worldwide remote participation – including a tool to participate in the discussion.

You can add the event calendar via ICSwebcalHTML.

How the digital transformation is changing our lives

Our society relies more and more on information and operational technologies. Examples include water, energy, heat and cooling supply, communications, healthcare, production and processing of goods, transportation, national security, banking, research and education, and food production.

What all these areas have in common is that they make intensive use of networked distributed computer systems. These systems can be attacked in many ways. This is no longer just a problem for computer “pros” because computer systems are essential to all of us. The effects of “cyber-attacks” range from power outages to the collapse of the health care or banking sectors.

Program and registration: https://talk.cybercni.fr/

Recap of the GFA Startup Learning Expedition 2024 in Paris


The GFA’s Startup Learning Expedition in Paris and visit of VivaTechnology on May 21-25, 2024 were a tremendous success, filled with insightful sessions, impactful networking opportunities, and engaging discussions. Here is a detailed recap of the eventful week!

A Recap: GreenHack~IT 2024 – Hackathon on Green AI Solutions


Recap of “GreenHack~IT 2024” our hackathon in AI and ML. We had a great time at TélécomParis. The students did an awesome job and went home happy!

WE.GO.FURTHER – Startup Learning Expedition 2024


Our Startup Learning Expedition 2024 is in the starting blocks. We have selected 5 German and 6 French startups that offer innovative solutions in the field of Industry 4.0. We look forward to showing the startups the partner ecosystem and helping them move forward in the best possible way!

6th Future IoT Summer School “IoT meets Secure Supply Chain”, Sep 30 – Oct 4, 2024 in Paris


Save the date for the 6th edition of the Future IoT Summer School “IoT meets Secure Supply Chain” on Sep 30 – Oct 4, 2024 in Paris!

On July 22-26, 2024: 4th Edition of the Summer School on AI Technologies for Trust, Interoperability, Autonomy and Resilience in Industry of the Future (ai4industry)


The ai4industry summer school is back with their 4th edition this year on July 22-26!

Call for Applications: We.Go.Further – The GFA startup learning expedition


Our second Call for Applications for our Learning Expedition 2024 is online! If you are a startup from IMT/TUM/INRIA Startup Studio and plan to expand to the partner country (🇫🇷🇩🇪), please apply for a grant until March 15th! For more info, follow the link!

New Research Projects – These projects were selected through our CfP “2023Smart Technologies ensuring Secure Operations in Industry” 2023


We are excited to share the journey of our recent research call, “Smart Technologies Ensuring Secure Operations in Industry”. Launched on August 9, the call attracted an array of cutting-edge project proposals from researchers and experts across diverse fields.