ReDS (Responsible Data Sci.) Lab @ VT

AI Security & Privacy & More | PI @ruoxijia | Responsible Data Science Lab (ReDS) @VT_ECE

[ReDS (Responsible Data Sci.) Lab @ VT @reds_lab_vt]

@acm_ccs @kzp14633386

[Yi Zeng 曾祎 @EasonZeng623]

Just wrapped up a fantastic time at @USENIXSecurity . From #ICML to #UsenixSecurity23, this travel season has been a blast. Sadly, won't make it to #ACMCCS in person. Can't wait to reunite with everyone at the next event!

[Yi Zeng 曾祎 @EasonZeng623]

Post-ICML vibes! Eyes on @USENIXSecurity'23 (Aug 9-11) next.📅

1. Enter 'Meta-Sift':🕵️‍♂️ we unravels existing methods (humans included) fails to spot a pure, clean subset in the presence of data poisoning. Guess what? We've got a bi-level solution in our pocket!

2. Say hello to 'ASSET': 🛡️ In a world where backdoor detection methods often falter across different training paradigms (supervised learning, SSL, or transfer learning), we bring to the table an ingenious solution. Meet active separation via offset, or ASSET—a strategy as robust as it sounds!

Stay tuned! 🎢 #UsenixSecurity23 #AIResearch

[Ruoxi Jia @ruoxijia]

🌺 Aloha! Excited to attend ICML in beautiful Hawaii! Our group will present 2 posters and 6 workshop papers, showcasing our latest efforts in data-centric AI, ML security, and privacy. Thrilled that our whole group is here too! Can't wait to meet old & new friends.😄 #ICML2023

[Virginia Tech Academy of Data Science @VT_DataScience]

Congrats to Dr. Jia, who will be providing the closing keynote during the Women in Data Science Blacksburg conference next Friday, April 21. Don't miss your chance to register for this free hybrid event! https://t.co/FoLSX2vGWs

[Virginia Tech ECE @VT_ECE]

Congratulations to assistant professor Ruoxi Jia on her @NSF CAREER award!👏

This $500k grant will allow Jia & her team to develop reliable data valuation & acquisition techniques that can help improve machine learning tools like AI chatbots. 🙌

https://t.co/95SjWa4e3K

[The Sanghani Center at Virginia Tech @SanghaniCtrVT]

In top @vtnews today, read how Ruoxi Jia (@ruoxijia), assistant professor @VT_ECE and core faculty @SanghaniCtrVT, will use her @NSF CAREER Award to advance data valuation techniques to improve machine learning models. https://t.co/davL7qXX0p

[Ruoxi Jia @ruoxijia]

Bad data hinders machine learning due to human error or malicious attacks. Advanced bad data mitigation techniques often require trusted clean data. But what if we don't have one? Our recent paper, MetaSift, provides a solution. @USENIXSecurity

[The Sanghani Center at Virginia Tech @SanghaniCtrVT]

Hoang Anh Just (@reds_tiger), @VT_ECE Ph.D. student, takes the Student Spotlight @SanghaniCtrVT for his work on valuating data. He will be presenting a paper @iclr_conf in May that offers a new perspective. Read more here: https://t.co/Er01goI2lf

[Yi Zeng 曾祎 @EasonZeng623]

"Meta-Sift" got Accepted to @USENIXSecurity'23!

Ever wondered how existing methods or humans can help identify enough clean data (e.g., 1000 for CIFAR-10) from a corrupted dataset to enable effective data poisoning defenses? They can't!

Our solution: https://t.co/DZyaMhGm7a

[Yi Zeng 曾祎 @EasonZeng623]

����🏆👏 IEEE Trojan Removal Competition (IEEE TRC'22) is a wrap!

Huge congrats to all participants 🙌
You've made neural networks safer (emojis by ChatGPT)!
#AI #Security #IEEE #cybersecurity #MachineLearning

🏆👀@trustworthy_ml Check out the winners: https://t.co/iyPhWKDrEu

[Yi Zeng 曾祎 @EasonZeng623]

🧵TLDR: We generalize LiRPA to UP via a MILP and give theoretical generalization bound! 🤯

Amazing collaborators: @zhouxingshi, @MingJin80233626, Feiyang Kang, Lingjuan Lyu, Cho-Jui Hsieh and @ruoxijia

💻 Github: https://t.co/cANqvibKys
🔍 OpenReview: https://t.co/c9u8XnBq29

[Yi Zeng 曾祎 @EasonZeng623]

🧵Our ICLR'23 paper time!
📄 Check out the first practical robustness certification of trained models against UP ( #UAP/ #Backdoor) & how to theoretically generalize results to the whole population (👀Figure🔍t*(∙) denotes estimation error).

#iclr2023 #ai #security #robustness

[Ruoxi Jia @ruoxijia]

Thrilled to announce that our group has received the NSF CAREER award. Heartfelt thanks to our amazing students, collaborators, and colleagues and the support from @VT_ECE and @SanghaniCtrVT!

[Yi Zeng 曾祎 @EasonZeng623]

🚨Hey all, the IEEE Trojan Removal Competition deadlines are extended by one week! 🎉

Now's your chance to get closer to Responsible AI, win the grand prize of $8,000, and present at the ICLR'23 workshop!

@ https://t.co/A0MwMXjZ07 🔗

#IEEE #AI #Security #ICLR2023 #ICLR

[Keunwoo Choi @keunwoochoi]

whoa, this is bigger than ChatGPT to me.
google almost solved music generation, i'd say.

https://t.co/s9PQaJ5R6A

[NeurIPS Conference @NeurIPSConf]

The CfP for #NeurIPS2023 is out. The full-paper submission deadline is on May 17, 1pm PDT.

https://t.co/Mp3N9iU8bs

[ICML Conference @icmlconf]

The Call for Papers for #ICML2023 is out:
https://t.co/qro0w6DSV2

Submission deadline is: Jan 26th, 2023 3pm EST

[Yi Zeng 曾祎 @EasonZeng623]

🚨Technophiles and AI security specialists! The IEEE Trojan Removal Competition is ongoing, and we want you to participate! Design end-to-end neural network Trojan removal methods for a chance to win $8,000 and present at the ICLR'23 workshop! Join us @ https://t.co/MZABopU1ZG

[Arvind Narayanan @random_walker]

The best way to edit your writing is to have someone else do it. The second best way is to put it away for a few weeks before editing it, so the text isn't fresh in your mind.

Back-to-front editing is always worthwhile, but especially when the first two options aren't available.