Today we're presenting two papers #cysoc2026 #icwsm2026 1. 𝐆𝐫𝐨𝐮𝐩-𝐃𝐢𝐟𝐟𝐞𝐫𝐞𝐧𝐭𝐢𝐚𝐭𝐞𝐝 𝐃𝐢𝐬𝐜𝐨𝐮𝐫𝐬𝐞 𝐨𝐧 𝐆𝐞𝐧𝐞𝐫𝐚𝐭𝐢𝐯𝐞 𝐀𝐈 𝐢𝐧 𝐇𝐢𝐠𝐡 𝐒𝐜𝐡𝐨𝐨𝐥 𝐄𝐝𝐮𝐜𝐚𝐭𝐢𝐨𝐧: 𝐀 𝐂𝐚𝐬𝐞 𝐒𝐭𝐮𝐝𝐲 𝐨𝐟 𝐑𝐞𝐝𝐝𝐢𝐭 𝐂𝐨𝐦𝐦𝐮𝐧𝐢𝐭𝐢𝐞𝐬 led by 𝐏𝐚𝐫𝐭𝐡 𝐆𝐚𝐛𝐚, a talented high school student workshop-proceedings.icwsm.org/abstract.php...

New exciting and timely Trustworthy AI Seminar tomorrow by Ilia Shumailov (AI Sequrity Company) ** What is going on with prompt injections? ** Tomorrow (Friday, May 1) at 9am PDT / 12pm EDT / 6pm CEST Details and Zoom/YouTube links at trust-ai-sem.github.io

Gptzero thinks that the ACM copyright block is written by AI...

Starting in ~15 mins!

Check out our latest article: Improving Peer Review in Top-Tier Cybersecurity Conferences -- A proposal in 10 points linkedin.com/pulse/improv... via LinkedIn

New exciting Trustworthy AI Seminar this Friday! Earlence Fernandes (UC San Diego) will present "The systems security approach to AI agents." Details and Zoom/YouTube stream link on our website : trust-ai-sem.github.io

Can someone explain to me why car dealers agents still exist? If there is profession at all one should be happy to see replaced by AI, car dealers are light years ahead of anything else

I'm excited to teach a Cybersafety class this quarter at UCR. In this first iteration, it'll be offered as a seminar class, but we will switch to a regular class next year. Preliminary syllabus: spalab.cs.ucr.edu/teaching/26s... Looking forward to comments and feedback!

🎙️ New Trustworthy AI Seminar ⏰ April 3 | 9am PDT / 12pm EDT / 6pm CEST 🗣️Sahar Abdelnabi ( @sahar-abdelnabi.bsky.social): "Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs" LLMs can carry hidden state across sessions — with zero external memory! 👉 trust-ai-sem.github.io

📣 The first seminar of the Trustworthy AI Seminars will be given by Peter Kairouz on "Context Matters: A New Paradigm for Differentially Private Synthetic Text Generation." 🕰️ Friday, March 6, at 9am PT / 12pm ET / 5pm UK time 🌎 Details, Zoom link, YouTube stream, etc. at trust-ai-sem.github.io

Hey everyone, @ebagdasa.bsky.social and I are rebooting and widening the old prisec-ml seminar series. Give us a follow at @trust-ai-sem.bsky.social and check out our website at: trust-ai-sem.github.io We already have a couple of amazing speakers booked!

I’m excited to share that the UCR's LOGOS Interest Group is hosting an Open Day on February 27. If you’re a Southern California–based researcher and you’re interested in research problems in cybesafety/computation social science, get in touch! 👉 Event page: logos.cs.ucr.edu/open-day.html

Unapologetically wouldn't consider living anywhere in the US other than California.

PSA if you’re ever in the LA area, don’t miss Raffis place in Glendale. Worth the detour just for their khoobideh. Wow.

UC, 2024: Your health insurance is going up significantly because we cover GLP-1, so go and hate people on it UC 2025: We are no longer covering GLP-1 unless your BMI is above 40 (if you're 5'10", you'd need to weigh >280 lbs) Also UC, 2025: Your health insurance is going up because GLP-1 Wut?

Congrats to Sundar -- his paper "To Shuffle or not to Shuffle: Auditing DP-SGD with Shuffling" was just accepted to #NDSS2026! Only 21 out of 950 straight accepts this round 😳 Joint work with Borja Balle, Jamie Hayes, & @emilianodc.com Pre-print: arxiv.org/abs/2411.10614

Hey folks! My Fall quarter class (OS capstone project) has been canceled, which means I'm on an impromptu short sabbatical until Xmas. I'm happy to travel a bit to visit and give talks if anyone is interested!

I'm aware that I'm known as a hater, but can someone explain to me why on earth anyone would willingly use Overleaf to work on papers? The only use cases that I can think of are: 1) emergency editing from someone else's device or iPad 2) non-CS co-authors not familiar with LaTeX

Ever struggled with managing your pubs to create an NSF BioSketch using MyNCBI's My Bibliography? I think I have finally found a decent way to handle stuff, sharing in case it helps... (Step 5 is the one that took me the longest!) www.linkedin.com/posts/activi...

📣 Upcoming CCS'25 paper 📣 The Importance of Being Discrete: Measuring the Impact of Discretization in End-to-End Differentially Private Synthetic Data We investigate the critical yet overlooked role of discretization in end-to-end differentially private (DP) tabular synthetic data generation

Conditional congrats to Georgi and Sundar - their paper on Discretization in DP Synthetic Data was accepted with shepherding to CCS’25. Very important work on an overlooked aspect of end-to-end DP pipelines. Preprint: arxiv.org/abs/2504.06923 -- feedback welcome!

Really interesting work on CCPA-mandated compliance of data brokers with access/deletion requests: arxiv.org/abs/2506.21914 Highlights: - Almost half of the brokers don't respond - Only <5% of brokers provided personal data - No standard/easy way to submit requests - Requests for even more PII

TIL my Internet provider (Cox Communications) creates an access point ("CoxWiFi") from your WiFi router where other Cox customers can connect to at no charge. This was enabled by default and without my explicit consent. How is that legal?

Online abuse self-defense training for scientists "who appear in media and other public outlets, as well as their allies and employers" www.sciline.org/learn/online...

Once in a while, I stumble upon an old email of mine — the writing and grammar are awful. I used to feel embarrassed, riddled with imposter syndrome, etc. But for the last couple of years, I’ve focused instead on how much I’ve improved. Cognitive restructuring is such an underrated power…

Unlike traditional finances, all someone needs to access all your crypto is your passwords and they can steal your money and disappear without a trace. This incentivizes some horrific behavior all over the world.

Hi Everyone, I'm teaching a new UG class on privacy at UCR and I'm planning a lecture on human factors of privacy. Has anyone taught anything on this topic and would like to share notes/topics covered? I'd be super grateful!

Huge congrats to @spalab.cs.ucr.edu's Georgi Ganev for receiving the Distinguished Paper Award at IEEE S&P for his work "The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against “Truly Anonymous” Synthetic Datasets." Paper: arxiv.org/pdf/2312.051...

Georgi's paper, Understanding the Impact of Data Domain Extraction on Synthetic Data Privacy, will be presented at the ICLR SynthData workshop next week. A "tiny" paper studying the impact of how you extract the data domain from tabular datasets while training generative models for synthetic data.

I'm quoted in this @wired.com article about the recent (alleged) 4chan hack www.wired.com/story/2025-4...

📢 Deadline Extended for submissions to #CySoc2025 to ensure broader participation. 💡Share your research on generative AI, online safety, harms and threats, or political conflict in online platforms, with the leading minds in the field. We’d love to see your submissions. 📆New Deadline: April 10 AoE

And it was also amazing to be physically with Georgi (at Schloss Dagstuhl of all places) for the first time in 1.5 years when we got the news! :)

Happy to announce that Georgi's paper, “The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against “Truly Anonymous” Synthetic Datasets,” has been accepted to IEEE Security & Privacy. Pre-print: arxiv.org/pdf/2312.05114

Not an urban legend — the sausage vending machine near the Schloss Dagstuhl exists! And they seem very successful too as it’s almost empty! Just outside a small backerei in the middle of nowhere. When in a Germany…

On my way to NDSS on the most amazing train. See y’all in a bit.

Waiting for S&P reviewers to respond to our rebuttal

I couldn't sleep last night.

The adjective sounds very superfluous

I’m proverbially humbled and manifestly honored by the ACM’s recognition as Distinguished Member. This is obviously an achievement that would have never been possible without my amazing students and collaborators or the support and mentorship of so many people. www.acm.org/media-center...

The final version of Georgi's TMLR paper, "The Elusive Pursuit of Reproducing PATE-GAN: Benchmarking, Auditing, Debugging," is now available at: arxiv.org/abs/2406.13985

Reposting this here, would love to hear your thoughts!

Sundar's upcoming WWW paper on browser fingerprinting is now available on arXiv arxiv.org/abs/2502.01608

It was fun to give an interview to Italian TV's TG3 Mondo, talking about our research on the toxic manosphere/womanosphere ecosystems. The segment (in Italian) starts around minute 25 at this link: www.rainews.it/rubriche/tg3...

Congrats to Sundar and Igor — our new paper on browser fingerprinting has been accepted to WWW’25. G’day, mate!

Happy to report that the paper "The Elusive Pursuit of Reproducing PATE-GAN: Benchmarking, Auditing, Debugging" led by SPALab's Georgi Ganev has been accepted, pending minor revision, to the prestigious TMLR journal. Pre-print: arxiv.org/abs/2406.13985

Want to connect with the brightest minds shaping the future of network and computer security? The NDSS Symposium (Feb 24-28) in sunny San Diego is THE place to be! We're talking 5 tracks, 220+ cutting-edge OPEN ACCESS papers, and world-class workshops. https://www.ndss-symposium.org/ 1/

I'm quoted in this Guardian article on the "femosphere," featuring our research on online women's ideological spaces (arxiv.org/abs/2303.07099). Joint work with Utkucan Balci, Chen Ling, @megansquire.bsky.social , @gianlucastringhini.com , @mrjimmyblack.com www.theguardian.com/world/2024/d...

Today at #NeurIPS2024, Sundar will present his paper "Nearly Tight Black-Box Auditing of Differentially Private Machine Learning." Starting 4:30pm in West Ballroom A-D, poster #6208. Paper: arxiv.org/abs/2405.14106

Yay, UCR approved our proposal for a new undergrad course on Privacy. Can't wait to teach it this Spring!