SpaLab Research Lab

New exciting and timely Trustworthy AI Seminar tomorrow by @iliaishacked ** 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

Starting in ~10 mins

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

New exciting Trustworthy AI Seminar this Friday! @EarlenceF (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

We're 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-c… Looking forward to comments and feedback!

🎙️ New Trustworthy AI Seminar ⏰ April 3 | 9am PDT / 12pm EDT / 6pm CEST 🗣️Sahar Abdelnabi (@sahar_abdelnabi ) "Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs" 👉 trust-ai-sem.github.io

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

Hey everyone, @ebagdasa and Emiliano De Cristofaro are rebooting and widening the old prisec-ml seminar series. First speaker @KairouzPeter on March 6! Check out: trust-ai-sem.github.io

Congrats to @ganevgv: his paper "SMOTE and Mirrors: Exposing Privacy Leakage from Synthetic Minority Oversampling" was accepted at @iclr_conf! Pre-print arxiv.org/abs/2510.15083

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

Emiliano will be back at UCL for a talk on Monday 📍 169 Euston Road, GF Seminar Room 📅 September 22 🕑 2:00 PM Swing by if you’re in town and interested in synthetic data and privacy or just want to say hi. sec.cs.ucl.ac.uk/seminars/

We're excited to announce the Call for Papers for SaTML 2026, the premier conference on secure and trustworthy machine learning @satml_conf We seek papers on secure, private, and fair learning algorithms and systems. 👉 satml.org/call-for-paper… ⏰ Deadline: Sept 24

Huge congrats to @ganevgv for receiving the Distinguished Paper Award at #ieeesp25 @IEEESSP for his work "The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against “Truly Anonymous” Synthetic Datasets." arxiv.org/pdf/2312.05114…

Pre-print: arxiv.org/pdf/2504.08254… Co-authored by @sundarmsa, Sofiane Mahou, and Emiliano De Cristofaro

Extracting it directly from the input data breaks DP. This well know but, alas, also common practice. Our experiments also show that membership inference attacks may perform well by detecting issues with data domain extraction rather than vulnerabilities of the generative models

.@ganevgv'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 while training generative models for synthetic data

Happy to announce that @ganevgv'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

Happy to announce that Dr. Emiliano De Cristofaro was recently recognized as a Distinguished Member of the ACM acm.org/media-center/2…

TL;DR: 1/ We analyze 6 implementations of PATE-GAN, including 3 by the original authors 2/ None reproduce the utility reported in the original paper 3/ All implementations leak more privacy than intended 4/ We uncover 19 privacy violations and 5 other bugs

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