ExamGecko
Question list
Search
Search

List of questions

Search

Related questions











Question 88 - Certified AI Specialist discussion

Report
Export

Which feature in the Einstein Trust Layer helps to minimize the risks of jailbreaking and prompt injection attacks?

A.
Secure Data Retrieval and Grounding
Answers
A.
Secure Data Retrieval and Grounding
B.
Data Masking
Answers
B.
Data Masking
C.
Prompt Defense
Answers
C.
Prompt Defense
Suggested answer: C

Explanation:

Prompt Defense is a feature in the Einstein Trust Layer that helps minimize the risks of jailbreaking and prompt injection attacks. These attacks occur when malicious users try to manipulate the AI model by providing unintended inputs. Prompt Defense ensures that the prompts are processed securely, protecting the system from such vulnerabilities.

Option A (Secure Data Retrieval and Grounding) relates to ensuring that data used by AI is securely retrieved but does not address prompt security.

Option B (Data Masking) focuses on protecting sensitive information but does not prevent injection attacks.

For more information, refer to Salesforce's Einstein Trust Layer documentation on Prompt Defense and security features.


asked 26/09/2024
Karen Charllotte Aglipay
30 questions
User
Your answer:
0 comments
Sorted by

Leave a comment first