Course : AI Security Professional (AISP), EXIN Certification
Practical course - 2d
- 14h00 - Ref. EXP
|
Download in PDF format
Share this course by email
 | Explain the challenges of AI security within an organization |
| Distinguishing AI Security from Conventional Cybersecurity |
| Identify AI-specific assets and their main threats |
| Analyze the risks associated with input attacks, prompt injection, data or model poisoning, exfiltration, and leaks of sensitive data |
| Implement controls for governance, limiting sensitive data, and reducing undesirable behavior |
| Understanding the Role of AI Security Testing Beyond Traditional Security Testing |
| Apply the principles of privacy, compliance, and risk management in AI scenarios |
| How to Effectively Prepare for the EXIN AI Security Professional Exam |
Intended audience
Anyone involved in the design, use, security, governance, or compliance of AI systems.
Prerequisites
Prior knowledge of the fundamental concepts of artificial intelligence is recommended.line breakA certification such as EXIN BCS Artificial Intelligence Essentials or EXIN BCS Artificial Intelligence Foundation provides a solid foundation for preparation.
Certification
The exam is taken remotely under individual webcam supervision by the certifying body. It consists of a multiple-choice test with 40 questions, to be completed in one hour and thirty minutes (plus 15 minutes if the exam is in English and English is not the candidate’s native language). A minimum score of 65% is required to pass the exam.
Course schedule
1 AI Security in the Organization
- Implementing the G.U.A.R.D. steps to organize AI security.
- Responsible and trustworthy use of AI within the organization.
- Differences Between Conventional Cybersecurity and AI Security.
- Identification of specific AI assets and their key threats.
- A Threat Modeling Approach with Controls for AI Security.
- Typical risks associated with agentic AI.
2 Security Threats Specific to AI
- Types of evasion based on the attacker's access: zero-knowledge, partial-knowledge, perfect-knowledge, transfer attack, and evasion after poisoning.
- Direct and indirect prompt injection.
- 7 layers of protection against sudden injections.
- Disclosure of sensitive data in model outputs.
- Model inversion, membership inference, and model exfiltration.
- Risks of resource depletion driven by inflows.
- Data poisoning and model poisoning during development.
- Direct contamination of the product and contamination through the supply chain.
- Leaks of sensitive data during the development phase: data, models, source code, and configuration.
- Impact of Conventional Security Threats on AI Components in Production.
- Direct model poisoning at runtime and associated leaks.
- Injection embedded in the AI outputs and data leakage at the input.
- Leakage and manipulation of salary increase data.
3 AI Security Checks
- General Governance Controls for AI Safety Oversight.
- Coverage of governance controls and their scope.
- Division of responsibilities between the third-party model provider and the user organization (off-the-shelf model).
- Implement controls to limit sensitive data and strengthen confidentiality and integrity.
- Understanding how limiting sensitive data reduces risks.
- Measures to limit the effects.
- Improving performance and reducing the risk of undesirable behaviors in the operational model.
4 AI Security Testing
- Importance and Scope of AI Security Testing.
- Differences from conventional security tests.
- Threats to be tested specifically for predictive and generative systems.
- General Testing Strategies Applied to AI Security.
5 Privacy, Compliance, and Regulation
- Privacy Principles Applied to AI Systems.
- Privacy Concerns Related to AI Applications.
- Contribution of ISO/IEC 23894, ISO/IEC 27005, ISO/IEC 42001, and ISO/IEC 5338 to AI regulatory compliance.
- Compliance Issues Related to the AI Act and the GDPR.
- Risks of Copyright Infringement and Mitigation Strategies.
PARTICIPANTS
Anyone involved in the design, use, security, governance, or compliance of AI systems.
PREREQUISITES
Prior knowledge of the fundamental concepts of artificial intelligence is recommended.line breakA certification such as EXIN BCS Artificial Intelligence Essentials or EXIN BCS Artificial Intelligence Foundation provides a solid foundation for preparation.
TRAINER QUALIFICATIONS
The experts leading the training are specialists in the covered subjects. They have been approved by our instructional teams for both their professional knowledge and their teaching ability, for each course they teach. They have at least five to ten years of experience in their field and hold (or have held) decision-making positions in companies.
ASSESSMENT TERMS
The trainer evaluates each participant’s academic progress throughout the training using multiple choice, scenarios, hands-on work and more.
Participants also complete a placement test before and after the course to measure the skills they’ve developed.
TERMS AND DEADLINES
Registration must be completed 24 hours before the start of the training.
ACCESSIBILITY FOR PEOPLE WITH DISABILITIES
Do you need special accessibility accommodations? Contact Mrs. Fosse, Disability Manager, at psh-accueil@orsys.fr to review your request and its feasibility.
Anyone involved in the design, use, security, governance, or compliance of AI systems.
PREREQUISITES
Prior knowledge of the fundamental concepts of artificial intelligence is recommended.line breakA certification such as EXIN BCS Artificial Intelligence Essentials or EXIN BCS Artificial Intelligence Foundation provides a solid foundation for preparation.
TRAINER QUALIFICATIONS
The experts leading the training are specialists in the covered subjects. They have been approved by our instructional teams for both their professional knowledge and their teaching ability, for each course they teach. They have at least five to ten years of experience in their field and hold (or have held) decision-making positions in companies.
ASSESSMENT TERMS
The trainer evaluates each participant’s academic progress throughout the training using multiple choice, scenarios, hands-on work and more.
Participants also complete a placement test before and after the course to measure the skills they’ve developed.
TEACHING AIDS AND TECHNICAL RESOURCES
• The main teaching aids and instructional methods used in the training are audiovisual aids, documentation and course material, hands-on application exercises and corrected exercises for practical training courses, case studies and coverage of real cases for training seminars.
• At the end of each course or seminar, ORSYS provides participants with a course evaluation questionnaire that is analysed by our instructional teams.
• A check-in sheet for each half-day of attendance is provided at the end of the training, along with a course completion certificate if the trainee attended the entire session.
• The main teaching aids and instructional methods used in the training are audiovisual aids, documentation and course material, hands-on application exercises and corrected exercises for practical training courses, case studies and coverage of real cases for training seminars.
• At the end of each course or seminar, ORSYS provides participants with a course evaluation questionnaire that is analysed by our instructional teams.
• A check-in sheet for each half-day of attendance is provided at the end of the training, along with a course completion certificate if the trainee attended the entire session.
TERMS AND DEADLINES
Registration must be completed 24 hours before the start of the training.
ACCESSIBILITY FOR PEOPLE WITH DISABILITIES
Do you need special accessibility accommodations? Contact Mrs. Fosse, Disability Manager, at psh-accueil@orsys.fr to review your request and its feasibility.
This programme is an original creation, developed by the teaching teams at ORSYS Formation. Any reproduction, representation, adaptation or use, in whole or in part, without the prior written authorisation of ORSYS, is strictly prohibited. ORSYS reserves the right to take any action necessary to protect its intellectual property rights.
Dates and locations
Dernières places
Date garantie en présentiel ou à distance
Session garantie
This programme is an original creation, developed by the teaching teams at ORSYS Formation. Any reproduction, representation, adaptation or use, in whole or in part, without the prior written authorisation of ORSYS, is strictly prohibited. ORSYS reserves the right to take any action necessary to protect its intellectual property rights.