Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions
Michele Miranda, Elena Sofia Ruzzetti, Andrea Santilli et al.
Action editor: Tian Li
https://openreview.net/forum?id=Ss9MTTN7OL
#privacy #anonymizing #secure
18.02.2025 15:07 โ ๐ 3 ๐ 1 ๐ฌ 0 ๐ 0
Our survey on ๐ฃ๐ฟ๐ฒ๐๐ฒ๐ฟ๐๐ถ๐ป๐ด ๐ฃ๐ฟ๐ถ๐๐ฎ๐ฐ๐ ๐ถ๐ป ๐๐๐ ๐ has been published in ๐ง๐ฟ๐ฎ๐ป๐๐ฎ๐ฐ๐๐ถ๐ผ๐ป๐ ๐ผ๐ป ๐ ๐ฎ๐ฐ๐ต๐ถ๐ป๐ฒ ๐๐ฒ๐ฎ๐ฟ๐ป๐ถ๐ป๐ด ๐ฅ๐ฒ๐๐ฒ๐ฎ๐ฟ๐ฐ๐ต (๐ง๐ ๐๐ฅ)! ๐
Check it out!
13.02.2025 08:24 โ ๐ 2 ๐ 0 ๐ฌ 0 ๐ 0
Many LLM uncertainty estimators perform similarly, but does that mean they do the same? No! We find that they use different cues, and combining them gives even better performance. ๐งต1/5
๐ openreview.net/forum?id=QKR...
NeurIPS: Sunday, East Exhibition Hall A, Safe Gen AI workshop
13.12.2024 12:36 โ ๐ 11 ๐ 4 ๐ฌ 1 ๐ 0
Interested in learning how to evaluate uncertainty in LLMs?
Check out our work at NeurIPS!
Feel free to reach out for a chat!
12.12.2024 17:12 โ ๐ 3 ๐ 1 ๐ฌ 1 ๐ 0
Come by to our poster at CLiCit!
04.12.2024 16:19 โ ๐ 3 ๐ 0 ๐ฌ 0 ๐ 0
If youโre interested in mechanistic interpretability, I just found this starter pack and wanted to boost it (thanks for creating it @butanium.bsky.social !). Excited to have a mech interp community on bluesky ๐
go.bsky.app/LisK3CP
19.11.2024 00:28 โ ๐ 36 ๐ 8 ๐ฌ 3 ๐ 2
The largest workshop on analysing and interpreting neural networks for NLP.
BlackboxNLP will be held at EMNLP 2025 in Suzhou, China
blackboxnlp.github.io
Blog: https://sander.ai/
๐ฆ: https://x.com/sedielem
Research Scientist at Google DeepMind (WaveNet, Imagen 3, Veo, ...). I tweet about deep learning (research + software), music, generative models (personal account).
MLxBio @vant_ai. Previously, research @Twitter and FabulaAI (acquired by Twitter). PhD in Graph ML at @imperialcollege and @Cambridge_Uni alumnus
Transactions on Machine Learning Research (TMLR) is a new venue for dissemination of machine learning research
https://jmlr.org/tmlr/
The need for independent journalism has never been greater. Become a Guardian supporter https://support.theguardian.com
๐บ๐ธ Guardian US https://bsky.app/profile/us.theguardian.com
๐ฆ๐บ Guardian Australia https://bsky.app/profile/australia.theguardian.com
Staff research scientist at Google DeepMind. AI and neuro.
Former physicist, current human.
Find more at www.janexwang.com
PhD student in Computer Science @ UniTn. NLP & CogSci
leobertolazzi.github.io
Music, audio, and deep learning research at Stability AI ~ Building bridges between audio signal processing wisdom and deep learning.
artintech.substack.com
www.jordipons.me
Researcher @nousresearch.com
Twitter: https://twitter.com/Teknium1
Github: http://github.com/teknium1
HuggingFace: http://huggingface.co/teknium
The AI Accelerator Company. https://discord.gg/nousresearch
Assistant Professor at CSD CMU. https://www.cs.cmu.edu/~aditirag/
The 2025 Conference on Language Modeling will take place at the Palais des Congrรจs in Montreal, Canada from October 7-10, 2025
Research Scientist at Apple Machine Learning Research. Previously ServiceNow and Element AI in Montrรฉal.
Apple ML Research in Barcelona, prev OxCSML InfAtEd, part of MLinPL & polonium_org ๐ต๐ฑ, sometimes funny
https://unireps.org
Discover why, when and how distinct learning processes yield similar representations, and the degree to which these can be unified.
Computer Science PhD @ Sapienza University
AI, philosophy, spirituality
Head of interpretability research at EleutherAI, but posts are my own views, not Eleutherโs.
