Shubhi
Asthana
Sr Research Software Engineer at IBM Research
"PIIGuardRails on LLMs - Protecting Personally Identifiable Information"
"PIIGuardRails on LLMs - Protecting Personally Identifiable Information"
24 - 5:50 PM EDT/New York (See in local time)
Add to Calendar
04/24/2024 5:50 PM
04/24/2024 06:10 PM
America/New_York
#WTGC2024
"PIIGuardRails on LLMs - Protecting Personally Identifiable Information"
#WTGC2024
"PIIGuardRails on LLMs - Protecting Personally Identifiable Information"
https://app.events.ringcentral.com/events/women-in-tech-global-conference-2024/reception
https://www.womentech.net/vfairs
"PIIGuardRails on LLMs - Protecting Personally Identifiable Information"
"PIIGuardRails on LLMs - Protecting Personally Identifiable Information"
Don’t miss out and join visionaries, innovators, and thought leaders from all over the world at the Women in Tech Global Conference.
Vote by Sharing
Unite 100 000 Women in Tech to Drive Change with Purpose and Impact.
Do you want to see this session? Help increase the sharing count and the session visibility. Sessions with +10 votes will be available to career ticket holders.
Please note that it might take some time until your share & vote is reflected.
Session: PIIGuardRails on LLMs - Protecting Personally Identifiable Information
PII (Personally Identifiable Information ) relates to any data that can be used to identify a specific person. In LLM models, there is a risk that PII sensitive information may get leaked. Non-sensitive personal information can become a risk when that data is pieced together to identify a person indirectly. For instance, gender, birthday, ethnicity, or medical information may disclose a person’s identity when combined with other information.This talk provides a novel ML-based engine to identify Personally Identifying Information for vast unstructured documents. It is the state-of-the-art engine which provides comprehensive PII coverage across multiple detectors, thus providing guardrails to LLM outputs.
Key Takeaways
- 1. Audience will acquaint themselves with PII detectors, and how sensitive information leaks in LLM
- 2. Audience will gain knowledge on state-of-the-art in Guardrails, and how to safeguard their PII
- 3. Audience will gain expertise in risk mitigation in vast unstructured documents.
Bio
Shubhi Asthana is a Sr Research Software Engineer who build AI & ML Solutions. She is SME in AI and ML models for Financial Services, along with leading the PII effort in Unstructured Data & NLP. Her research and development work spans the areas of Data Analytics, NLP and Cloud Services.