Pinned Tweet
Hello world! We're the MURI for Cybersecurity Assurance for Teams of Computers and Humans (CATCH). Will post ground-breaking research from our group of researchers, and developments in the areas of robust human-AI teams and cybersecurity. We're also here: catch-muri.org/
Humbled and excited to receive MURI on the general
topic of robust learning. PIs are from US (UW, UCSD, CMU, PSU) and Australia (University of Melbourne, Macquarie University, University of Newcastle).
cto.mil/wp-content/uploads/2…
1
Congratulations to @catch_muri lead PI @jhasomesh for his test-of-time award!
Congrats to @jhasomesh, who recently received the prestigious “Test of Time” award during the 33rd @USENIXSecurity Symposium!
“This paper was highly influential,” said @kamalikac, professor of @ucsd_cse and director of the (FAIR) team at @AIatMeta.
cs.wisc.edu/2024/09/10/uw-ma…
38
Congrats to Matt, @catch_muri PI on his tenure and startup launch!
It is always a source of pride when your students succeed. Recently, Matt Fredrikson (middle name "not on Twitter":-)) got tenure at @CSDatCMU
Matt was an integral part of my group at @WisconsinCS and did some amazing work.
He is also a co-founder of grayswan.ai/
The company focusses on security/safety of AI.
Congrats Matt! Proud advisor moment.
56
CATCH MURI retweeted
Replying to @christodorescu
@christodorescu and I hosted a panel at the CRA snowbird conference. The title of the panel was:
Security Risks of Generative AI: From Identification and Mitigation to Responsible Use
Our amazing panelists were John Mitchell (Stanford University), Rebecca Wright (Barnard College), Matt Turek (DARPA)
CATCH MURI retweeted
Last year, we had so much fun at this workshop! Come join @chhaviyadav_ and the rest of us at @NeurIPSConf and send your best interpretability papers here.
📰 Excited to be organizing a workshop on Interpretability @NeurIPSConf'24, called 'Interpretable AI : Past, Present and Future'
Submit to our workshop for all things inherently interpretable!
Submission ddl : 30 Aug
🔗 interpretable-ai-workshop.gi…
Follow this account for updates!
Congrats to @catch_muri PI Matt Fredrikson!
Congratulations to @CyLab faculty members Matt Fredrikson of @S3DatCMU and Bryan Parno of @SCSatCMU, @CMU_ECE on winning “Test of Time” Awards at last week’s @USENIXSecurity Symposium in Philadelphia! Learn more about their research: cylab.cmu.edu/news/2024/08/2…
#usesec24
3
28
CATCH MURI retweeted
I thought a lot about this...
(Attack->fix->..)^* cycle is fundamental to the crypto/security community. In fact, a lot of cool technical results won't be possible unless we had that cycle. For example, lattice based crypto came after a long sequence of crypto schemes that were broken (maybe someone can put actual examples).
Having the (attack->fix)^* is fundamental to the security/crypto field.
*Must read* for anyone interested in ML security, by Nicholas Carlini. Attacks are the only way we know whether or not a purportedly secure system actually is.
Moreover, I consider personal attacks like this unacceptable in my research communities.
nicholas.carlini.com/writing…
Excited to be kicking off a @catch_muri workshop at @CarnegieMellon SV campus. Looking forward to two days of great discussions on robust human-AI teaming.
Congrats @chhaviyadav_ @kamalikac and team!
Delighted to receive a Best Paper Award 🏆for my latest work — FairProof : Confidential and Certifiable Fairness for Neural Networks (arxiv.org/abs/2402.12572)
— at the Privacy-ILR Workshop @iclr_conf ! (my 1st :)
Will also be presented @icmlconf
Slides : bit.ly/fairproof_slides
CATCH MURI retweeted
🚨 New Paper! (arxiv.org/abs/2404.19597)🚨 We uncover significant vulnerabilities in Multilingual LLMs (MLLMs) (e.g., BLOOM, Llama2, Llama3, Gemma, and GPT-3.5-turbo) to cross-lingual transferable backdoor attacks. #AIsafety #LLMs #backdoors
CATCH MURI retweeted
A research community is only as strong as its members. That's why #SaTML2024's indebted to our PC, esp these ten members who went beyond the call of duty:
@asia_biega
@mlsec
@gchers
Jamie Hayes
@UdacityDave
@zakynthinou
@AlinaMOprea
@DavidSKrueger
@RyanSheatsley
@fraboeni
🥳👏👏Congratulations to the 2024 ACM #SIGCHI awardees!
We recognize 13 SIGCHI members receiving lifetime research and practice, societal impact, and outstanding dissertation awards, as well as 10 being inducted into the SIGCHI Academy! medium.com/sigchi/announcing…
1/6🧵
1
36
CATCH MURI retweeted
Excellent venue on a very important topic. Also, some very interesting keynote talks are being arranged by the organizers of this workshop at @IEEESSP
(Second Call for Papers)
Submit your work on the security for GenAI systems and applications. *Security Architectures for Generative AI (SAGAI'24)* is a new workshop at IEEE S&P this year.
Full CFP: sites.google.com/view/sagai2…
Submission deadline: February 5, 2024
CATCH MURI retweeted
In this new paper, Baptiste Prebot, Yinuo Du (@Yinuo80492608), and Coty Gonzalez (@CotyGonzalez12) use adversarial algorithms to investigate defenders’ learning using interactive cyber-defense games.
academic.oup.com/cybersecuri…
@CarnegieMellon @OxUniPress
#CyberSecurity #Algorithms
CATCH MURI retweeted
It was amazing to have @lujobauer from CMU at @WisconsinCS
His talk was fantastic and insightful. Thanks for visiting us Lujo.
today.wisc.edu/events/view/1…
CATCH MURI retweeted
I'm on the academic job market
I'm a full-stack data privacy researcher
I build systems that are 1)provably private 2)functionally-rich 3)compatible w/ real-world constraints
I do this by exploring the synergy between cryptography & differential privacy, both in theory & practice
Congrats to @catch_muri co-lead @jhasomesh and his coauthors on this groundbreaking work!
Our paper presents the first provable watermarking scheme for large language models (LLMS) with public detectability or verifiability: we use a private key for watermarking and a public key for watermark detection. Work with Jaiden, Sanjam, Mingyuan, Mohammad, and Saeed.
Comments most welcome. We will update in the next version.
eprint.iacr.org/2023/1661.pd…
@catch_muri researchers have had 7 papers accepted to @NeurIPSConf #NeurIPS2023. Congrats to them and their wonderful co-authors!
CATCH MURI retweeted
We are seeking a Managing Director for the newly announced NSF AI institute on Societal Decision Making (AI-SDM). nsf.gov/awardsearch/showAwar…
Apply here: cmu.wd5.myworkdayjobs.com/CM…

























