Principal Researcher at @Huawei; Alumni at @ImperialCollege @ImperialSysAL; Working in Safety of language models, Privacy-preserving machine learning.
Joined November 2016
- Tweets 107
- Following 262
- Followers 156
- Likes 1,200
8 Photos and videos
Fan Vincent Mo retweeted
The longer people are in academia, the more they realize that when reading papers it's best to ignore Intro, Discussion etc. and just look at Methods and Results
journals.plos.org/plosone/ar…
195
1,115
5,076
961,732
Fan Vincent Mo retweeted
24 Jul 2023
I hit a bug in the Attention formula that’s been overlooked for 8 years. All Transformer models (GPT, LLaMA, etc) are affected.
Researchers isolated the bug last month – but they missed a simple solution…
Why LLM designers should stop using Softmax 👇
evanmiller.org/attention-is-…
73
354
2,298
591,684
Fan Vincent Mo retweeted
21 Mar 2023
Have you ever wondered how we can salvage federated learning?
27 March at 11:15am GMT, @realhamed will utilize Trusted Execution Environments on clients for local training, and on servers for secure aggregation, to hide model updates from adversaries.
6 Mar 2023
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
1
1
6
1,670
Fan Vincent Mo retweeted
11 Nov 2022
Great progress towards efficient and adaptive FL on ultra-constrained devices. Work led by @VincentMo6 during his internship at @BellLabs.
11 Nov 2022
Federated Learning for constrained edge devices need to become more efficient and adaptive. In this preprint, we offer Centaur: a framework that adaptively partitions FL training across multiple clients owned by each user.
PDF: arxiv.org/abs/2211.04175
1/4
1
20
Fan Vincent Mo retweeted
5 Jul 2022
#EarComp is back at @ubicomp 2022! We’re so excited to announce the Call for Papers for the 3rd edition of the workshop on Earable Computing!🎧🦻Check out the call at: esense.io/earcomp2022 #earable #ubicomp2022
7
22
1 Aug 2022
Too many attacks breaking the privacy-by-design principle in federated/collaborative learning? All-in-One. Check out our paper analyzing the private information leakage from neural network gradients using information theory. arxiv.org/pdf/2105.13929.pdf
2
2
26
20 Jun 2022
Super excited to start my internship at Nokia Bell Labs Cambridge today! I will be working on device intelligence in @akhilmathurs and @raswak's team. (meanwhile, I have been using my Nokia phone for 15 years 😃)
1
26
Fan Vincent Mo retweeted
23 Dec 2021
Excited about our upcoming work on "battery-free machine learning for the ocean!", just accepted to @ACMHotMobile 2022 - a cross-pond collaboration between our groups @MIT_SK_Lab and @ImperialSysAL. Stay tuned!
1
7
55
Fan Vincent Mo retweeted
29 Nov 2021
Over the past 5 years, I’ve read >1,000 letters of recommendation to grad programs in MIT - mostly EECS, Media Lab, and MechE. Since it's letter-writing season, here is some concrete advice for anyone writing letters based on my experience
13
257
1,205
Fan Vincent Mo retweeted
29 Sep 2021
How to cope with paper rejection?
Rejection SUCKS! It feels awful that months of hard work did not pay off. 😭 How do we hold a positive outlook when dealing with rejection?
A thread of lessons (learned from many rejections) 🧵
6
71
354
Fan Vincent Mo retweeted
28 Jun 2021
@ACMSIGMOBILE MobiSys 2021 has started. Heartiest Congratulations to the author of the two best paper awards this year. Well done! 🍷Now, on to the first keynote by Shree K. Nayar (Columbia) on "Future Cameras: Redefining the Image." Nice start😀
5
15
Fan Vincent Mo retweeted
28 Jun 2021
I should not trust my Federated Learning provider.But I should still trust my coauthors @VincentMo6,@minoskt,@realhamed,@_EduardMarin_ & @Diego_Perino! Feels great to get best paper @ACMMobiSys for PPFL privacy-preserving FL system! @TEFresearch @concordiah2020 @accordion_h2020
3
8
37
28 Jun 2021
I'm very excited and really honored to get the best paper award. Massive thanks to all the authors and my group/teams.
@ImperialSysAL @TEFresearch
2
2
18
Fan Vincent Mo retweeted
11 Jun 2021
Check our teaser video of our latest work "PPFL: Privacy-preserving Federated Learning with Trusted Execution" to be presented on June 30th at #MobiSys2021. Preprint (arxiv.org/abs/2104.14380) and Code (github.com/mofanv/PPFL) are both available online.
11 Jun 2021
We create an animation, giving a brief fun introduction of privacy-preserving federated learning trusted execution environments. Check it out.
Based on @ACMMobiSys paper, with @realhamed @minoskt @_EduardMarin_ @Diego_Perino @kourtellis
Thanks to @TEFresearch @ImperialSysAL
2
8
11 Jun 2021
We create an animation, giving a brief fun introduction of privacy-preserving federated learning trusted execution environments. Check it out.
Based on @ACMMobiSys paper, with @realhamed @minoskt @_EduardMarin_ @Diego_Perino @kourtellis
Thanks to @TEFresearch @ImperialSysAL
4
5
29
Fan Vincent Mo retweeted
21 May 2021
If you work on privacy-preserving ML and especially Federated Learning, check out our paper and code that we made public ahead of our @ACMMobiSys 2021 presentation!
Powered by: @TEFresearch, @concordiah2020, @accordion_h2020, @PimcityProject
#dataprivacy #CyberSecurity
20 May 2021
Check our codes, for running Federated Learning with (both the server's and the client's) trusted execution environments!
github.com/mofanv/PPFL
9
11
20 May 2021
Check our codes, for running Federated Learning with (both the server's and the client's) trusted execution environments!
github.com/mofanv/PPFL
30 Apr 2021
Preprint of our new paper proposing the 1st Privacy-Preserving Federated Learning Framework with TEEs, accepted @ACMMobiSys 2021, here: arxiv.org/pdf/2104.14380
@VincentMo6,@realhamed,@minoskt,@_EduardMarin_,@Diego_Perino
Powered by @TEFresearch,@concordiah2020,
@accordion_h2020
8
23
Fan Vincent Mo retweeted
7 May 2021
Due to several requests, we are extending the MAISP deadline @ACMMobiSys to 14/5.
If you work on Security/Privacy of ML on mobile/edge/network devices, check it out: maisp.gitlab.io
@iliasl,@minoskt,@cristiancanton
Great keynotes/program!
@concordiah2020 @accordion_h2020
12
12
Fan Vincent Mo retweeted
4 May 2021
This week @iclr_conf DPML, @VincentMo6 presents our paper on “Layer-wise Characterization of Latent Information Leakage in Federated Learning”.
Schedule: dp-ml.github.io/2021-worksho…
Paper: arxiv.org/abs/2010.08762
2
9