Cybersecurity of Machine Learning and Artificial Intelligence
Faculty
Sergey Gordeychik
CEO at CyberOK
Course length
Duration
Total hours
Credits
Language
Course type
Fee for single course
Fee for degree students
Skills you’ll learn
Overview
The module covers different aspects of cybersecurity and cyber resilience of systems and applications based on Artificial Intelligence and Machine Learning.
Machine learning and AI technologies are turning from rocket science into daily engineering life. On the other hand, massive implementation of AI in various areas brings about problems, and security is one of the greatest concerns. What is "state of the art" in AI security? Yesterday it was a PoC, not a product, today becoming a “We will fix it later”, tomorrow it will be a “if it works, don't touch it”. To make it better we should rethink Cyber Resilience for the AI process, systems and applications to make sure that they continuously deliver the intended outcome despite adverse cyber events. Make sure that security is genuinely integrated into innovation that AI brings into our lives. To trust AI and earn its trust, perhaps?
During this course we will learn cybersecurity of AI in various aspects: from threat modeling and requirements development to vulnerability research and practical attacks against AI models such as Adversarial ML, Model Backdooring etc.
The course is delivered by an expert with a wealth of practical experience and member of the SCADA StrangeLove team who has participated in dozens of security assessment and incident response projects devoted to analyzing the security of systems in various sectors of the industry.
Learning highlights
- An understanding of modern AI applications components, purposes, deployments, significant drivers, and constraints
- An understanding of threats and vulnerabilities in AI Applications on different layers – from hardware security to model privacy
- Practical experience in the security assessment of AI systems during their development lifecycle
- Industrial-specific governance, risk assessment and compliance models
- Practical experience in AI specific attacks such as Adversarial ML, Model Backdooring etc.
Course outline
15 classes
AI as a product
- AI systems Development Life Cycle
- AI Threat Model
- Secure SDL touchpoints
AI infrastructure security
- Hardware and GPU
- Network infrastructure
- Data storage
- Dockers and virtualization
ML frameworks
- TensorFlow, PyTorch, Keras
- Built-in Security features
- Vulnerabilities in machine learning frameworks
- Model backdooring
AI Model Security
- Adversarial training
- Scaling Attack
- Model backdoor
- Adversarial ML
Adversarial Examples (1/2)
- White, gray and black box attacks
- Fast Gradient Sign Method (FGSM)
- Basic Iterative Method (BIM)
- Projected Gradient Descent (PGD)
- Deepfool
Adversarial Examples (2/2)
- Transferability Attack
- Adversarial examples for voice and text models
- Model testing framework (DeepSec and ART)
Adversarial Robustness
- Adversarial robustness approaches
- Input modification methods
- Model modification methods
- Attack detection
AI and confidentiality
- Data collection and privacy
- Model data extraction
- Model reuse
- Black and graybox reverse engineering
Cognitive City Security
- Cognitive City AI applications
- Public safety
- Environment monitoring
Cognitive City Security
- Geospatial and geomarketing technologies
- Smart transportation
Healthcare AI Security
- Healthcare threat model
- Scanners, DICOM and PACS security
- Medical Imaging machine learning pipelines vulnerabilities
AI and Cyber
- Defensive AI applications
- Offensive AI applications
- AI vs AI
AI and Privacy
- Large-scale AI implementations
- Privacy issues
- Legislation frameworks
- International best-practice
Future of AI security
- Distributed learning
- Self-learning
- Brain-computer interfaces
- Cognitive security
Final Exam
- Final Exam
Prerequisites
This course is one of three in a wholistic series.
Students that have already taken MSL-111 and those with prior experience with HTML, CSS, and Javascript building simple web pages will be good candidates for this module.
Sergey Gordeychik is CEO and Co-Founder of CyberOK, a cybersecurity company delivering advanced services and research. He is also a Visiting Professor at Harbour.Space University (Barcelona, Spain), contributor of different social and educational initiatives. Previously, he was CIO at the Inception Institute of Artificial Intelligence (UAE), where he led AI-driven product development and secure infrastructure design. As Deputy CTO at Kaspersky Lab, he launched Security Intelligence Services and Managed Detection and Response solutions. Earlier, as CTO of Positive Technologies, he led development of award-winning enterprise security products and co-created Positive Hack Days (PHDays), the largest cybersecurity event in Eastern Europe.
Sergey is the author of two books and multiple scientific publications, with three patents in cybersecurity. He has created several training programs including "Critical Infrastructure Protection" and "Web Application Security Assessment." A regular speaker at top-tier conferences such as S4, CCC, CodeBlue, POC, and ZeroNights, Sergey holds CISSP, MCSE, MCT, CWNA, and was recognized as a Microsoft MVP in Enterprise Security R&D.
See full profileApply for this course
Cybersecurity of Machine Learning and Artificial Intelligence
by Sergey Gordeychik
Total hours
45 Hours
Dates
Jul 06 - Jul 24, 2020
Fee for single course
€1500
Fee for degree students
€750
How to secure your spot
Complete the form below to kickstart your application
Schedule your Harbour.Space interview
If successful, get ready to join us on campus
FAQ
Will I receive a certificate after completion?
Yes. Upon completion of the course, you will receive a certificate signed by the director of the program your course belonged to.
Do I need a visa?
This depends on your case. Please check with the Spanish or Thai consulate in your country of residence about visa requirements. We will do our part to provide you with the necessary documents, such as the Certificate of Enrollment.
Can I get a discount?
Yes. The easiest way to enroll in a course at a discounted price is to register for multiple courses. Registering for multiple courses will reduce the cost per individual course. Please ask the Admissions Office for more information about the other kinds of discounts we offer and what you can do to receive one.