Vitaly Shmatikov
{{Short description|American computer scientist}}
{{Infobox scientist
| name = Vitaly Shmatikov
| image_size =
| birth_date =
| birth_place =
| death_date =
| death_place =
| citizenship =
| nationality =
| ethnicity =
| field = Computer Security
| work_institutions = Cornell Tech
| alma_mater = Stanford University (PhD)
| doctoral_advisor = John C. Mitchell
| doctoral_students =
| known_for =
| author_abbrev_bot =
| author_abbrev_zoo =
| prizes =
| religion =
| signature =
| footnotes =
| thesis_title = Finite-State Analysis of Security Protocols
| thesis_year = 2000
| caption =
}}
Vitaly Shmatikov is a professor in computer security at Cornell Tech.
Biography
Shmatikov obtained his M.S. in engineering-economic systems at Stanford University, and then Ph.D. in computer science from Stanford University in 2000 under the supervision of John C. Mitchell, where he wrote his dissertation on Finite-State Analysis of Security Protocols.{{Cite web |title=Vitaly Shmatikov - The Mathematics Genealogy Project |url=https://www.mathgenealogy.org/id.php?id=71115&fChrono=1 |access-date=2024-02-28 |website=www.mathgenealogy.org}} He currently has over 100 publications in the area of computer security, privacy, and cryptography. {{Cite web |title=Vitaly Shmatikov |url=https://scholar.google.com/citations?user=rejZUEkAAAAJ&hl=en |access-date=2024-02-28 |website=scholar.google.com}}
Research
The Netflix Prize was a competition to predict how users would rate films based on their previous ratings of other films. The dataset contained data from 480,189 users who rated 17,770 movies. In 2008, with Arvind Narayanan, Shmatikov showed that it was possible to de-anonymize individual people from this dataset.{{Cite magazine |last=Schneier |first=Bruce |title=Why 'Anonymous' Data Sometimes Isn't |url=https://www.wired.com/2007/12/why-anonymous-data-sometimes-isnt/ |access-date=2024-02-28 |magazine=Wired |language=en-US |issn=1059-1028}}{{Cite web |last=Singer |first=Natasha |date=2015-01-29 |title=With a Few Bits of Data, Researchers Identify 'Anonymous' People |url=https://archive.nytimes.com/bits.blogs.nytimes.com/2015/01/29/with-a-few-bits-of-data-researchers-identify-anonymous-people/ |access-date=2024-02-28 |website=Bits Blog |language=en}} To do this, Shmatikov used a second auxiliary dataset of various user's IMDb ratings. By correlating users who made similar reviews, it was possible to nearly perfectly de-identify several people who were present in both datasets. For this work, IEEE awarded Shmatikov the "Test of Time" award in 2019.{{Cite web |title=Vitaly Shmatikov and Arvind Narayanan Receive Inaugural "Test of Time" Award from the IEEE Symposium on Security and Privacy {{!}} Department of Computer Science |url=https://www.cs.cornell.edu/information/news/newsitem10467/vitaly-shmatikov-and-arvind-narayanan-receive-inaugural-test-time |access-date=2024-02-28 |website=www.cs.cornell.edu}}
More recently Shmatikov has studied the privacy of machine learning. With Reza Shokri, Shmatikov introduced the first "Membership Inference" attacks on machine learning models. This allows an attacker to learn what data a machine learning model has been trained on.{{Cite web |title=Artificial intelligence may put private data at risk {{!}} Cornell Chronicle |url=https://news.cornell.edu/stories/2018/08/artificial-intelligence-may-put-private-data-risk |access-date=2024-02-28 |website=news.cornell.edu |language=en}}
Shmatikov has also studied how machine learning can be used to attack user privacy. For example, in 2016 he showed that "pixelization" used to obfuscate user's faces is insecure and it is still possible to identify people whose faces have been pixelated.{{Cite magazine |last=Newman |first=Lily Hay |title=AI Can Recognize Your Face Even If You're Pixelated |url=https://www.wired.com/2016/09/machine-learning-can-identify-pixelated-faces-researchers-show/ |access-date=2024-02-28 |magazine=Wired |language=en-US |issn=1059-1028}}
Awards
Shmatikov received the Caspar Bowden PET Award for Outstanding Research in Privacy Enhancing Technologies in 2008, 2014, and 2018. {{Cite web |title=PET Award |url=https://petsymposium.org/award/winners.php |access-date=2024-02-28 |website=petsymposium.org}} He received the Test of Time award at IEEE S&P 2019, and a Test of Time award from the ACM Conference on Computer and Communications Security.{{Cite web |title=Shmatikov |url=https://www.dli.tech.cornell.edu/members/shmatikov |access-date=2024-02-28 |website=dli-cornell-tech |language=en}} In 2023 he received the Outstanding Paper Award at EMNLP 2023.
References
{{Reflist}}
External links
- [https://www.cs.cornell.edu/~shmat/ Home Page]
{{DEFAULTSORT:Shmatikov, Vitaly}}
Category:Year of birth missing (living people)