Congratulations, @jiayuan_ye_ ! This is an amazing achievement.
Congratulations to amazing Jiayuan Ye @jiayuan_ye_ for receiving the Apple Scholars in AIML PhD fellowship, for her outstanding contributions to ML privacy, half way through her PhD. Well deserved!!!
scholar.google.com/citations…
machinelearning.apple.com/up…
Shruti Tople retweeted
Looking to recruit PhD students (in both ECE + CS @ UIUC) with STRONG interests in ML+Sec, Applied Crypto, Systems, and demystifying foundation models. Deadline: Dec 15. Ping with any questions. Please RT and help amplify?
Shruti Tople retweeted
I'll be presenting our work "Bayesian Estimation of Differential Privacy" at #ICML2023.
Join me from 1:30pm at the poster session (poster #708) to learn how to estimate the actual privacy of ML training pipelines using membership inference attacks.
Shruti Tople retweeted
Concerned about language models leaking sensitive information regarding the identities of individuals in the training data? Curious about the effectiveness of techniques like PII scrubbing and DP in preventing such leakage? Join us on May 22,11:20 @IEEESSP'23 to know the answers!
Shruti Tople retweeted
Tired of diverse definitions of machine learning privacy risks? Curious about game-based definitions? In our paper, we present privacy games as a tool for describing and analyzing privacy risks in machine learning. Join us on May 22nd, 11 AM @IEEESSP '23 arxiv.org/abs/2212.10986
Shruti Tople retweeted
Only a few seats left!
Join us to listen to @BorjaBalle, @shrutitople, @realhamed, @b_mittelstadt, Smera, @aurelien_bellet, @DrXiaoLiu, Alisha, Blaise, Cliodhna and Mark from @DeepMind @MSFTResearch @imperialcollege @turinginst @Inria @UniofOxford @NICEComms @CDEIUK @uhbtrust
Curious about novel risks that AI introduces for patients and healthcare providers?
We're hosting an #AIUK Fringe event to explore Privacy and Fairness in AI for Health – Register now!
private-fair-ai.github.io/
Date: 27 March, 10:00-16:30 GMT
Location: @turinginst, London
1/6
Great talk by @teobaluta on our work on systematically identifying causes of membership inference attacks in machine learning models @acm_ccs. Check out the paper ‘Membership inference attacks and Generalization: A causal perspective’ here: arxiv.org/abs/2209.08615
Shruti Tople retweeted
Seminar this Wednesday (June 1st) @ 1:30 PM London
Shruti Tople (@shrutitople, Microsoft Research)
"Causal vs Associational Machine Learning: A Privacy Perspective"
Details: prisec-ml.github.io
Shruti Tople retweeted
1/8 The new High Potential UK Visa that opens on May 30, 2022 allows those who have completed a degree from one of 37 universities outside of the UK in the last 5 years to move there freely without an employer for 2 or 3 years (for PhD grads).
This is a HUGE deal!
Shruti Tople retweeted
This has got much less attention than the one by Miller @socrates1024, Möser @maltemoeser, Lee and Narayanan @random_walker /cc @shrutitople teapawt.org/IACR_News/status/85445…
#ePrint A Traceability Analysis of Monero's Blockchain: A Kumar, C Fischer, S Tople, P Saxena ia.cr/2017/338
Shruti Tople retweeted
Check our paper OblivP2P w/ @shrutitople @jiayaoqijia and P. Saxena to be presented at @USENIXSecurity this Friday usenix.org/conference/usenix…














