The first 15 pioneering projects in the @ARIA_research Trust Everything Everywhere Opportunity Space are LIVE ๐ฅณ
Each project has been awarded up to ยฃ20k and a three-month sprint to bridge the gap between digital security & physical reality
https://t.co/M8eiI0dlmz
This week @TheOfficialACM@ACMMobiCom 2025, Josh Millar will present his paper "Benchmarking Ultra-Low-Powerย ฮผNPUs" , joint work another with folks at Imperial and Cambridge:
https://t.co/mM5xaek0rY
Appearing at @PET_Symposium next week, work from our group at @ImperialX_AI :
โTeleSparse: Practical Privacy-Preserving Verification of Deep Neural Networksโ
Paper: https://t.co/w7yUopcqwf
Code: https://t.co/6NNyBMrzEs
Following Prof. Hamed Haddadiโs (@ICComputing & I-X) fantastic Inaugural Lecture last week, we are excited to share our latest Research Spotlight delving into his research on IoT, Privacy & Security, and Human-Centred Systems.
@realhamed@Imperial_NetSys
https://t.co/bzalcv0MId
Event News! Prof. Hamed Haddadi (@ICComputing & I-X) is organising the Multi-Service Networks workshop, focusing on the latest trends in networks and systems. ๐
๐ย 8 January
๐ย 1-5 pm
๐ย Huxley Building (@imperialcollege)
https://t.co/M57j1ivVG9
@realhamed@Imperial_NetSys
๐ข
Our new paper "Low-Energy On-Device Personalization for MCUs," will be presented at ACM/IEEE SEC'24 (@ACM_IEEE_SEC)
I worked on this research with @RanyaAloufi, Xavier Cadet, @yc_york, @PBarnaghi, @realhamed
๐ฐPaper: https://t.co/3eRgMfm3CO
๐ปCode : https://t.co/MGPJIFSWgw
Apply for the I-X WAI Early Career Grant! ๐
The grant supports women and non-binary individuals engaged in #AI or wanting to enter the field. If you are a Masterโs or PhD student or a Postdoc at @imperialcollege, apply now! ๐ค
๐๏ธ Deadline: 31 August
๐ https://t.co/UtLb2JnLQE
Welcome to our live stream of #IXOpenDay. Throughout the day, weโll be reporting on the event. If youโre attending, please tag us and use our hashtag. Weโd love to hear from you! ๐
โMitigating Hallucinations in Large Language Models via Self-Refinement-Enhanced Knowledge Retrievalโ, new work from @NiuMengjia to appear at GenAI workshop at @SIGIRConf https://t.co/2ygNJrcnO2
Looking forward to attending the Confidential Computing Summit @confcompsummit this week!
Presenting a poster about our ongoing research in trusted and private on-device learning. More details: https://t.co/px7CqCnZfs
If you're around and want to know more, come say hi!
How do you know if an ML model was trained privately?
Confidential-DPproof, our spotlight #ICLR2024 paper, allows institutions to directly prove to you through the execution of a Zero Knowledge Proof protocol that they train ML models in a privacy-preserving manner.
1/n
I'm looking for a postdoc to join my group at @NYUAbuDhabi in sunny Abu Dhabi this fall! โ๏ธ๐๏ธ๐ปApply here: https://t.co/GbJqNJfPeo
Three good reasons to apply: 1/2
Two papers from NetSys / @ImperialX_AI at @euromlsys today:
@sansib presenting "Towards Attestable and private ML with CCAโ https://t.co/Q6xXR3XwIB
@j0shmillar presenting "Towards Low-Energy Adaptive Personalization for Resource-Constrained Devices" https://t.co/oP8qla9cps