Large Language Models (AI) applications to Cybersecurity
Overview
The field of Artificial Intelligence is taking the industry (and the world) by storm. The launch of ChatGPT started a mass adoption phenomenon, which is now followed by an avalanche of new products and solutions addressing every possible problem space. Malicious hackers have also put AI to good use, but so did the White Hat hackers, such as Frédéric and his team.
This talk will level-set the understanding about Large Language Models (LLM) and Generative AI for computer scientists and software developers who might not be intimately familiar with the field. Frédéric will then take us further into some of the applications in cybersecurity.
Abstract
Large Language Models and Generative AI have completely reshaped the landscape of Artificial Intelligence the last two years. Progresses have been made on architectures, training methods, and the community has shared large datasets along with pre-trained models, allowing for new usages at a relatively low cost. In the cybersecurity defender's path, new malicious tools drove efforts on innovative methods to improve their detection. We propose a modern and effective method of detecting file maliciousness, by using an LLM initially trained on computer code. The focus will be on the process we set up and the decision we made to solve this problem, with an emphasize of the generalization of our approach. We will explain how LLM can help solve a large panel of problems related to texts.
In addition, we will explain the outcomes of this work : in particular, we will explain how we were able to use the trained model and ask it "where it was wrong", shedding lights on errors in the training datasets. We will explain where these errors came from, and how we were able to improve the model iteratively by correcting them, allowing more people to reproduce our findings and fixing pitfalls coming with noisy datasets. Working in a field where sometimes the line is thin between an "administrator" and a "threat actor", we will also open the discussion on how you can define maliciousness depending on your objectives.
Key takeaways :
-What is an LLM and what it is not?
-How much does it cost to use one for our own purpose?
-What are the key steps of a training process?
-An intro to cybersecurity : what are we trying to detect?
-How did we build our datasets?
-The results
-What can the data engineer and the cybersecurity analyst learn from these results?
Date and Time
Location
Hosts
Registration
- Date: 02 Apr 2024
- Time: 06:00 PM to 08:00 PM
- All times are (UTC-04:00) Eastern Time (US & Canada)
-
Add Event to Calendar
- 245 Church Street
- lower level
- Toronto, Ontario
- Canada
- Building: George Vari Engineering and Computing Centre (ENG)
- Room Number: ENGLG11
- Click here for Map
- Contact Event Hosts
-
La French Tech Toronto is a non-profit supporting DeepTech entrepreneurs.
Exaion is pioneering the responsible digital services of tomorrow.
CIS 2024 (Apr 30 - May 1st)
InCyber Forum North America (Oct. 29-30) - Co-sponsored by CIS 2024 | Use this IEEE Promo Code and enjoy 30% off your registration: IEEE_CIS2024
- Starts 17 March 2024 12:00 AM
- Ends 02 April 2024 12:00 AM
- All times are (UTC-04:00) Eastern Time (US & Canada)
- No Admission Charge
Speakers
Frédéric Grelot of GLIMPS
AI and Cybersecurity
GLIMPS is a cybersecurity company established in 2019 by four experts with a background in reverse-engineering. It offers innovative cybersecurity solutions leveraging a proprietary technology capable of automatically reading and understanding computer code. This technology is designed to enhance the detection and automation of binary analysis and threat identification, providing a significant boost to existing defense lines against increasingly sophisticated cyber threats. GLIMPS's solutions, which include GLIMPS Malware, are available in both SaaS and On-premise formats, catering to a broad spectrum of French and international companies and governmental bodies. The firm has achieved recognition within the cybersecurity community, evidenced by prices such as the European Cyber Week award, twice in a row.
At the core of GLIMPS's offerings is its Deep Engine, a specialized AI engine based on Deep Learning. This engine excels in deep file analysis, enabling quick detection and characterization of advanced cyber threats. By conceptualizing code, GLIMPS's technology can identify all forms of malware, providing a comprehensive and scientifically validated approach to cybersecurity. This platform processes over one million files daily and serves more than a hundred customers, demonstrating its effectiveness and the trust it has garnered within the industry. GLIMPS also emphasizes collaboration within the French ecosystem, aiming to integrate its solutions where beneficial. The company's growth is underscored by its successful fundraising efforts, which include a €6 million round in 2021, and its continuous search for new talent to join its expanding team.
Biography:
Frédéric Grelot is the CEO of GLIMPS Inc. Canada.
Frédéric began his career at CNES in Toulouse, spending three years in the Spacecraft's Embedded Computers department. There, he worked on designing a hardened computer chip for satellites and handled its validation from VHDL to integration in a satellite model and simulated space environment. In 2012, he joined the cyberdefense teams of the French Ministry of Armed Forces, specializing in reverse-engineering of computer systems and programs for seven years.
In 2016-2017, Frédéric initiated Artificial Intelligence work at DGA, identifying defense sectors where AI could be applied and helped establish a dedicated AI team. From 2017 to 2019, he led a team of 25 reverse-engineering analysts and continued enhancing his knowledge in Artificial Intelligence and Big Data.
In 2019, Frédéric co-founded GLIMPS, a company specializing in code analysis and malware detection using AI, and served as Scientist Lead. He contributed significantly to the company's outreach and communication. In 2023, he moved to Toronto, Canada, to open GLIMPS's first international office, engaging actively with the local tech and cybersecurity communities. Known for his distinctive profile, he also participated in various conferences and appeared on the national Radio Canada network. Frédéric is committed to ecological sustainability, incorporating this perspective into his entrepreneurial endeavors.
Email:
Address:Toronto, Canada
Marc Lijour of FIC North America Conference
FIC North America conference: Cybersecurity in the age of AI
Over the past 3 years, the InCyber Forum North America has established itself as the benchmark event in Canada, with an international reach. It echoes the InCyber Europe Forum, the continent’s largest cybersecurity event, which attracts 20,000 participants every year.
This Fall, we're expecting 5,000 participants to attend the North America edition in Montreal. The theme for for this year will be Cybersecurity in the age of AI.
The audience of this conference is as large as it topics running from technical operations, demo labs, to policy conversations about the ethical use of AI and the establishment of Open Finance in Canada. Attendees include Ministers, Industry Leaders, Cybersecurity establishment, startups, big IT, and law enforcement. Canada is well represented followed by the US and Europe.
Main stages for this year include:
- Web3 Security Summit
- Cybercrime
- Smart Transportation
- Operational Technology
- and more
The event will take place in English and French. Live translation will be provided.
Learn more at https://northamerica.forum-incyber.com/en/home-en/
Feel free to contact Marc Lijour for more information about the conference, including speaking and sponsorship opportunities.
Biography:
Marc Lijour is the representative of the FIC North America conference in Toronto. Marc also serves as the Region Lead for the Blockchain Technical Community, and the co-chair for the IEEE Toronto Blockchain local group.
Marc is passionate about helping C-level executives craft digital transformation strategies that drive impact for their business. He's currently focusing on usecases such as blockchain (staking), special effects / 3D, videogames, digital twins, and training AI models that leverage data center and cloud infrastructure for highly secure and ecoresponsible high performance compute, with a particular focus on the financial services industry and the creative industries.
Marc is also writing and teaching about strategy at the MBA in Technology, Innovation, and Entrepreneurship at the International Business University (IBU).
Marc holds a degree in Mathematics from France, and two degrees from TMU, one in Computer Science, and another in the Management of Technology and Innovation (MBA). He serves on the board of multiple not-for-profit organizations in the tech industry, such as TechConnex. He is a Founding Member of La French Tech Toronto.
Email:
Address:Toronto, Canada
Agenda
6 pm Welcome and introductions by Marc Lijour
6:30 pm - 7:30 pm Talk: "Demystifying AI and Large Language Models through a concrete use case" by Frédéric Grelot
Followed by Q&As
7:30 pm Networking
8 pm The end
Note: this event will be in English