Sign up to save your podcasts
Or
Share Information Security in AI, and the Impact of LLMs on User’s Privacy: ex-Google Kritika Prakash | Tech My Breath Away # 3
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Information Security in AI, and the Impact of LLMs on User’s Privacy: ex-Google Kritika Prakash | Tech My Breath Away # 3
Abbhinav (123 of AI), and co-host Debayan (Microsoft) are joined by AI reseacher Kritika Prakash, now pursing her Ph.D., at the University of Chicago.
The discussion revolves around the Kritika’s academic journey before and at IIIT-Hyderabad, differential privacy in AI, and her thoughts on the need for regulations to ensure a machine learning model's trustworthiness. We discuss the privacy issues in machine learning, including the challenges of protecting textual data and the impact of large language models on a user’s privacy.
KRITIKA REVEALS:
BEST MOMENTS:
“I did have exposure... where I can appreciate... lot of South Indian cultures.”
“Repeating an extra year: It felt like I am not really losing time... just learning more.”
“Talking to him [father]... understanding his perspective on things... He urged me... go for this risky thing.”
“I got do computer science but my first 3 semesters I was just so bored.”
“Discovered that there is this element of strategy & games that you can work with.”
“Explored various research areas before delving into differential privacy.”
“You might not have anything to hide. But, you do have something to protect”
“Adding noise during training reduce your accuracy; it actually helps improve generalization.”
“Real-world applications include healthcare research... where preserving individual [data]privacy is crucial.”
“Differential Privacy is not going cover all kinds of cases; we are looking at because this is the worst case guarantee.”
”The text itself doesn't have clear distinctions between people's data, and internet’s data; it's a huge mess just because that's how the text domain is.”
“Privacy will always be important no matter where the machine learning field is headed.”
ABOUT THE FOUNDER
Abbhinav Venkat, is the founder of 123 of AI, an ed-tech company enabling working professionals upskill in AI/ML. He is an entrepreneur, AI researcher, and podcaster. Prior to starting 123 of AI, he spent several years at multiple Silicon Valley startups as a Computer Vision Scientist. His academic career involved AI research at IIIT-H and Stanford University with several top-tier publications in BMVC, ICCV, ACPR. For his research, he was awarded Qualcomm’s Innovation Fellowship, felicitated by the Department of Science and Technology (DST), GOI, as well as invited for talks in 4 continents.
CONTACT
123 of AI’s website https://www.123ofai.com/contact
LinkedIn: https://linkedin.com/in/abbhinavvenkat
View all episodes
By 123 of AIAbbhinav (123 of AI), and co-host Debayan (Microsoft) are joined by AI reseacher Kritika Prakash, now pursing her Ph.D., at the University of Chicago.
The discussion revolves around the Kritika’s academic journey before and at IIIT-Hyderabad, differential privacy in AI, and her thoughts on the need for regulations to ensure a machine learning model's trustworthiness. We discuss the privacy issues in machine learning, including the challenges of protecting textual data and the impact of large language models on a user’s privacy.
KRITIKA REVEALS:
BEST MOMENTS:
“I did have exposure... where I can appreciate... lot of South Indian cultures.”
“Repeating an extra year: It felt like I am not really losing time... just learning more.”
“Talking to him [father]... understanding his perspective on things... He urged me... go for this risky thing.”
“I got do computer science but my first 3 semesters I was just so bored.”
“Discovered that there is this element of strategy & games that you can work with.”
“Explored various research areas before delving into differential privacy.”
“You might not have anything to hide. But, you do have something to protect”
“Adding noise during training reduce your accuracy; it actually helps improve generalization.”
“Real-world applications include healthcare research... where preserving individual [data]privacy is crucial.”
“Differential Privacy is not going cover all kinds of cases; we are looking at because this is the worst case guarantee.”
”The text itself doesn't have clear distinctions between people's data, and internet’s data; it's a huge mess just because that's how the text domain is.”
“Privacy will always be important no matter where the machine learning field is headed.”
ABOUT THE FOUNDER
Abbhinav Venkat, is the founder of 123 of AI, an ed-tech company enabling working professionals upskill in AI/ML. He is an entrepreneur, AI researcher, and podcaster. Prior to starting 123 of AI, he spent several years at multiple Silicon Valley startups as a Computer Vision Scientist. His academic career involved AI research at IIIT-H and Stanford University with several top-tier publications in BMVC, ICCV, ACPR. For his research, he was awarded Qualcomm’s Innovation Fellowship, felicitated by the Department of Science and Technology (DST), GOI, as well as invited for talks in 4 continents.
CONTACT
123 of AI’s website https://www.123ofai.com/contact
LinkedIn: https://linkedin.com/in/abbhinavvenkat