Enhance AI Content Safety with the Einstein Trust Layer
Learn how to enhance AI content safety using Einstein Trust Layer features. Understand how to detect prompt injection attacks and flag potentially toxic language in generative AI applications.
Important: This session is first come, first seated. You do not have a reserved seat.
, Senior Director, Product Management, Salesforce
, Senior Product Designer, Salesforce
Role: Administrator, Architect, IT
Product: Einstein, Data 360
Topic: Artificial Intelligence
Session Level: Intermediate
Session Type: Theater
Tuesday, Sep 171:30 PM - 1:50 PM PDT
(8:30 PM - 8:50 PM GMT)
Moscone West, L2, Einstein Theater
Session Summary by Einstein: The recent conference session focused on the critical topic of AI content safety, emphasizing the importance of robust systems to ensure the security of user-generated prompts and AI responses. The presenters discussed the Einstein Trust Layer's role in preventing the spread of harmful content and the necessity of upholding safety standards, as informed by surveys where 77% of IT leaders expressed concern over security risks. They introduced a framework for risk detection and scoring, customer controls and monitoring, and a responsible AI system, all aimed at creating a repeatable, reliable, and responsible AI environment. The session concluded by underscoring AI content safety as a commitment, with the Salesforce team ready to assist with any questions offstage.
Key Takeaways by Einstein:
• AI content safety is defined as a system encompassing prevention, detection, diagnostics, and mitigation of risks to maintain trust in AI applications.
• The Einstein Trust Layer provides features and guardrails to protect data privacy and promote the responsible use of AI, highlighting Salesforce's dedication to safety by design.
• Salesforce's session highlighted the introduction of new tools and benchmarks for evaluating Large Language Models (LLMs) based on trust and safety, ensuring customer control over AI content.
With sessions and hands-on activities led by product experts, visionaries, and fellow Trailblazers, Dreamforce offers a deep dive into the latest in CRM + AI + Data + Trust.
Merlinda Lu
Salesforce Developer, IBM
We use cookies on our website to improve website performance, to analyze website usage and to tailor content and offers to your interests.
By clicking “Accept All Cookies”, you consent to us placing these cookies. By clicking “Do Not Accept”, you reject the usage of such cookies. We always place cookies that do not require consent, which are necessary for the website to work properly.
For more information about the different cookies we are using, read the Privacy Statement. To change your cookie settings and preferences, click the Cookie Consent Manager button.
Cookie Consent Manager
Cookie Consent Manager
General Information
Required Cookies
Functional Cookies
Advertising Cookies
General Information
We use three kinds of cookies on our websites: required, functional, and advertising. You can choose whether functional and advertising cookies apply. Click on the different cookie categories to find out more about each category and to change the default settings.
Privacy Statement
Required Cookies
Always Active
Required cookies are necessary for basic website functionality. Some examples include: session cookies needed to transmit the website, authentication cookies, and security cookies.
Functional Cookies
Functional cookies enhance functions, performance, and services on the website. Some examples include: cookies used to analyze site traffic, cookies used for market research, and cookies used to display advertising that is not directed to a particular individual.
Advertising Cookies
Advertising cookies track activity across websites in order to understand a viewer’s interests, and direct them specific marketing. Some examples include: cookies used for remarketing, or interest-based advertising.
