Arrived this week, now it’s super official @spectrum.ieee.org #ieee #SeniorMember

New differential #privacy textbook in town: "DP in Artificial Intelligence: From Theory to Practice", by @nandofioretto.bsky.social and @vanhentenryck.bsky.social. Open access, w/ chapters by @jubaz.bsky.social, @grahamrc.bsky.social, and @stein.ke! www.nowpublishers.com/article/Book...

Philip Doldo 's first @cvprconference.bsky.social paper, 𝑆𝑡𝑜𝑝 𝑊𝑎𝑙𝑘𝑖𝑛𝑔 𝑖𝑛 𝐶𝑖𝑟𝑐𝑙𝑒𝑠! 𝐵𝑎𝑖𝑙𝑖𝑛𝑔 𝑂𝑢𝑡 𝐸𝑎𝑟𝑙𝑦 𝑖𝑛 𝑃𝑟𝑜𝑗𝑒𝑐𝑡𝑒𝑑 𝐺𝑟𝑎𝑑𝑖𝑒𝑛𝑡 𝐷𝑒𝑠𝑐𝑒𝑛𝑡, is a rare free lunch for 10x faster AML 🧵👇 openaccess.thecvf.com/content/CVPR...

Utterly incredible thread by a pilot on when everything hits the fan with radios, radar, and "ATC Zero." https://threadreaderapp.com/thread/1919686227001053361.html

Would you like to have the world's most accurate malware label predictor? RJ #BoozAllen has you covered w/ ClarAVy: A Tool for Scalable and Accurate Malware Family Labeling, arxiv.org/abs/2502.02759 work 🧵👇 to appear at thewebconf.org

Just had someone reach back 4 years later to say my advice was helpful to them and they just had their first @cvprconference.bsky.social paper accepted. So that is cool 😁

ai.umbc.edu/news/post/14... Manas Gaur, Edward Raff, and Ali Mohammadi helped present a half-day tutorial at 2025 AAAI on Neurosymbolic AI and how it can be applied to LLMs to help solve key challenges in NLP tasks like explainability, grounding & instructability. See their slides & material here.

One more day until the paper submission deadline! ⏰ Time to dot those i's and send it off 🦕 OpenReview: openreview.net/group?id=nes... Call for papers: 2025.nesyconf.org/call-for-pap...

Don't know why @cvprconference.bsky.social meta-reviews took a bit to come up, but ❤️ mine!: "The reviewers have mixed feelings about this paper. They generally agree that: (1) the work described here has practical value (as it allows to speed up considerably the well-known PGD algorithm), and

🧵New paper on arXiv: Optimal Differentially Private Sampling of Unbounded Gaussians. With @uwcheritoncs.bsky.social undergrad Valentio Iverson and PhD student Argyris Mouzakis (@argymouz.bsky.social). The first O(d) algorithm for privately sampling arbitrary Gaussians! arxiv.org/abs/2503.01766 1/n

I'm currently working through/implementing the Hager Zhang line search b/c I need it for some research, and it's a monster! Would anyone care if I made a tech report on "so you want to implement LBFGs/CG just give me the details"? B/c its really not well documented anywhere.

The submission page for #ICCV2025 is now OPEN! openreview.net/group?id=the...

If you are at #AAAI2025 come and see our oral presentation today in Room 122A at 11:15AM. The paper "Fairness Issues and Mitigations in (Differentially Private) Socio-demographic Data Processes" shows how sampling errors in survey data can introduce (1/2)

🚨 Only 7 days left to submit to #SciPy2025! 🔥 Don't miss this chance to share your work with the scientific Python community! Submit your talk now: https://buff.ly/3W5Lsl9 👀 Not submitting? Sign up as a reviewer and help curate an amazing program: https://buff.ly/3QyjR9n

My blog post on Ryan Williams' new inclusion of t(n) time in nearly square root of t(n) space using Cook-Mertz tree evaluation. blog.computationalco...

Wow @cvprconference.bsky.social rejected 19 otherwise accepted papers for reviewer authors not participating. Honestly, good this has teeth and hope it will encourage more effortful reviewing! I always thought CVPR does the best in trying to balance the author/reviewer equities!

I’m at @realaaai.bsky.social all week, starting with our tutorial on Neuro-Symbolic AI nesy-egi.github.io , come join us in an hour for needing out and cool work! #BoozAllen @umbc-ai.bsky.social

#CAMLIS 2024 proceedings are now live! ceur-ws.org/Vol-3920/

First, the claims are that ChatGPT o1 scored 80+ points on the Putnam, or 60+ points, or high enough to be in the top 2% of participants, or whatever other impressive-sounding claim someone can make up.

I miss “Weird A.I. Yankovic” arxiv.org/abs/2009.12240. Is it worth updating it to newer models?

AV system is hard in part b/c you are constantly searching for new features. But analysts are also writing Yara rules, can you steal them as features? New paper #IEEEBigData looks are how you can live of the analyst w/ @cmat.bsky.social @cknicholas.bsky.social @csee-umbc.bsky.social 🧵

Reminder: The #FAccT2025 submission deadlines are roughly one month away! Abstracts are due January 15th and full papers on January 22nd. See the full CfP here: facctconference.org/2025/cfp

Touch-down in Vancouver for #NeurIPS and got a notification that my #AAAI paper was accepted! Good start to the conference 🔥

Landing in Vancouver soon, happy to meet up with old friends and make new ones. Just reach out! 👋 #NeurIPS #NeurIPS24

Binary code is pervasive, and binary analysis is a key task in reverse engineering, malware classification, and vulnerability discovery. So, they created Assemblage - the dataset of source-to-binary projects compiled from GitHub. Assemblage - A dataset of binary executable corpuses

Helping analysts with their reverse engineering work and finding similar functions is a problem. A lot of existing literature doesn't really work on real data. We can get better results by being dumber! @NeurIPSConf #NeurIPS2024 @BoozAllen w/ @krismicinski.bsky.social @rjzak.bsky.social

#NeurIPS2024 paper 3, Assemblage - the dataset of source-to-binary projects compiled from GitHub that you've dreamed of bet never had before! Collab with @krismicinski.bsky.social and a multi-year effort to get to @NeurIPSConf @BoozAllen arxiv.org/abs/2405.03991

More neuro-symbolic AI/ML fun, Mohammad helps derive a simpler, easier, and more accurate Vector Symbolic Architecture (VSA) for all your fun needs! w/ @stellaathena.bsky.social to appear @NeurIPSConf #NeurIPS2024 #BoozAllen

Say you are doing online learning, and your algorithm is unstable - the results can change depending on the last data point you saw very dramatically. WAT do you do? Get Skyler Wu and Fred Lu on it @NeurIPSConf #NeurIPS @BoozAllen 🧵👇 📄 arxiv.org/abs/2410.23601

Conference Twitter accounts are super useful, hope to see more of them over here!

The 41st Conference on #Uncertainty in #AI will be held in Rio de Janeiro 🇧🇷, July 21-25! The CfP is out 👉 www.auai.org/uai2025/call... 🚨 Feb 10: Paper submission 🗣️ Apr 3-10: rebuttal period 🎉/💀 May 6: Author notification #UAI2025 #ML #stats #learning #reasoning #uncertainty

One #AISTATS paper I love got decent reviews that seem like they could be lifted 🤞 please be active reviewers - this paper has been so unfairly maligned!

If you or a loved one want ta high level discussion about what is changing in AI, LLMs, and the near-term future of what is possible - check out @BoozAllen 's new AI Primer with @nudro and lots of accessible text and video!

I need an emergency reviewer for anyone with familiarity of privacy in ML, facial recognition/biometrics, and/or hyper-dimensional computing/VSAs. Please DM me if you can do a quick emergency review for @RealAAAI #AAAI25

Derek Everett presenting on awesome work @CamlisOrg @BoozAllen

I have it on good authority that California has declared war on the French. Yes there is another cookie baked to the inside of the croissant

#aaai paper im AC for had 2x accept scores for phase 1 and just withdrew 🤷‍♂️wonder what the authors are thinking on the other side

"0 Official Reviews Submitted" give me my reviews that are almost invariably off-the-reservation so I can be angry about the next stage already! 😤 Cortisol is like a fine wine, can't make it in the wrong soil/mood!

That’s 4 papers accepted to @NeurIPSConf #NeurIPS2024 🥳 pre-prints coming soon!

The AI for Cyber Security workshop has been accepted to @RealAAAI #AAAI25 ! Start getting your papers and work ready! Anyone @CamlisOrg should be interested too. #AICS @aruneshsinha

Can someone do me the most vain of favors? Off by one CS BS 😤

Fewer features is better for DP regression, but the cost to do so is surprisingly high in DP methods. See 𝐹𝑒𝑎𝑡𝑢𝑟𝑒 𝑆𝑒𝑙𝑒𝑐𝑡𝑖𝑜𝑛 𝑓𝑟𝑜𝑚 𝐷𝑖𝑓𝑓𝑒𝑟𝑒𝑛𝑡𝑖𝑎𝑙𝑙𝑦 𝑃𝑟𝑖𝑣𝑎𝑡𝑒 𝐶𝑜𝑟𝑟𝑒𝑙𝑎𝑡𝑖𝑜𝑛𝑠 from @rswope_ai @philipdoldo @AmolKhanna00 @BoozAllen 🧵👇

Pretty happy with my @RealAAAI batch of papers as AC, looking forward to the reviews!

Looking like only 1 or 2 of the papers in my #NeurIPS AC batch of 13 will get accepted :-/ A lot of work that had promise and could have gotten in with better rebuttal writing.

Some fun interdisciplinary work coming to a @IEEEDSAA near you, 𝑀𝑜𝑟𝑒 𝑂𝑝𝑡𝑖𝑜𝑛𝑠 𝑓𝑜𝑟 𝑃𝑟𝑒𝑙𝑎𝑏𝑜𝑟 𝑅𝑢𝑝𝑡𝑢𝑟𝑒 𝑜𝑓 𝑀𝑒𝑚𝑏𝑟𝑎𝑛𝑒𝑠, 𝐴 𝐵𝑎𝑦𝑒𝑠𝑖𝑎𝑛 𝐴𝑛𝑎𝑙𝑦𝑠𝑖𝑠. Done with physicians w/ @UpstateHealth & @BoozAllen @umbccsee 📑

Now a Senior Member of ⁦@IEEEorg⁩ ! 😊

Also @jsylvest has cursed my paper writing. I can't use good fancy words that make sense because people don't think they are real words. I had a reviewer call out typos like "satisfice", which is not a typo! Its a word! It means a thing!

Oh man, am I annoyed at some rejection reviews citing me to myself and making wildly academic takes on what "real world" issues/constraints are.

I am really glad with some light prodding/comms, I was able to avoid needing any emergency reviewers for my batch of papers! Thank you @NeurIPSConf reviewers!

There are four #AISec papers that I want to review the most, and I am apparently conflicted out of all four of them, and I have no idea who wrote any of them, and they all sound like things I want to do. Who is torturing me like this? If I'm conflicted out let me work with you!