Send message to

Do you want to send the message without a subject?
Please note that your message can be maximum 1000 characters long
Special characters '<', '>' are not allowed in subject and message
reCaptcha is invalid.
reCaptcha failed because of a problem with the server.

Your message has been sent

You can find the message in your personal profile at "My messages".

An error occured

Please try again.

Make an appointment with

So that you can make an appointment, the calendar will open in a new tab on the personal profile of your contact person.

Create an onsite appointment with

So that you can make an onsite appointment, the appointment request will open in a new tab.

Header of Computacenter AG & Co. oHG
Forums it-sa Expo Knowledge Forum E

Security Measures to secure AI systems

AI governance, data security posture management and cyber security measures to secure AI platforms

calendar_today Thu, 24.10.2024, 11:00 - 11:15

event_available On site

place Forum, Booth 9-103

Action description

south_east

Speaker

south_east

Themes

Data protection / GDPR Data security / DLP / Know-how protection Governance, Riskmanagement and Compliance

Event

This action is part of the event Forums it-sa Expo

Action description

The presentation ‘Measures to secure artificial intelligence’ will highlight the key aspects of the security of AI systems, in particular large language models. The presentation focusses on three main topics: AI governance, data security posture management and cyber security measures for AI systems.
AI governance is a central aspect of the security of AI systems. It comprises the definition of guidelines and standards that ensure that artificial intelligence is developed and used responsibly. This includes the implementation of regulatory requirements such as the EU AI Act and the General Data Protection Regulation (GDPR). An important part of AI governance is monitoring compliance with quality criteria in order to minimise risks that could emanate from AI systems. This includes monitoring AI to detect drift.
Data Security Posture Management (DSPM) is crucial for the integration of existing data sets into AI systems. It enables the efficient processing of large data sets and guarantees access rights. DSPM minimises the risk of data misuse and loss and helps to meet data protection and compliance requirements. This includes analysing and adapting the existing ISMS to integrate data governance, developing data scope principles and procedures for assessing high-value/high-risk data and managing access rights
Cyber security measures for AI systems are essential to protect AI systems from cyber attacks. These measures include the implementation of attack detection mechanisms such as prompt injection, the application of best practices to secure the platform and the regular review of the security of AI models. Known challenges are, for example, the vulnerabilities described in the OWASP Top Ten for AI
Overall, the presentation aims to provide a comprehensive understanding of the various aspects of the security of AI systems and to present practical measures for securing these systems. 

Cyber security measures 
... read more

Downloads

Language: German

Questions and Answers: No

Speaker

show more
close

This content or feature is available to the it-sa 365 community. 
Please register or log in with your login data.