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.

action image header it logic
Forums it-sa Expo Knowledge Forum C

AI Security: Risks and Challenges in Modern Use Cases

Discover hidden AI threats and learn how to protect against RAG risks and prompt injection!

calendar_today Tue, 22.10.2024, 13:15 - 13:30

event_available On site

place Forum, Booth 7-641

Action Video

south_east

Action description

south_east

Themes

Governance, Riskmanagement and Compliance Trend topic

Key Facts

  • Prompt injection is a highly critical attack vector
  • RAG applications present a highly complex attack surface
  • AI architecture is crucial for IT security

Event

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

Action Video

grafischer Background
close

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

Action description

Join this compelling presentation to uncover the hidden dangers and challenges of AI security in modern use cases. The focus is on analyzing Retrieval Aided Generation (RAG) applications and the associated security risks. Learn how inadequate data permissions in vector databases can lead to unauthorized access and data breaches.

Another exciting focus is the threat of prompt injection. This attack method, where malicious inputs are embedded into the prompt, reveals how severe security vulnerabilities can arise even in non-chatbot scenarios. The presentation highlights how attackers can exploit these weaknesses to trigger unwanted actions or compromise sensitive data.

This presentation offers a comprehensive analysis of current threats and challenges in AI security. Effective solutions and best practices for risk mitigation will be presented. Take the opportunity to gain valuable insights into securing AI systems and learn how to protect your applications against potential attacks.
... read more

Language: German

Questions and Answers: No

close

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