@SpaLabUCR profile picture
SpaLab Research Lab @SpaLabUCR

Security and Privacy Advanced research Laboratory (SpaLab), bridging UCR and UCL. PI: Emiliano De Cristofaro

Joined December 2023
  • Tweets 87
  • Following 162
  • Followers 110
18 Photos and videos
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/

Trustworthy AI Seminar Series

trust-ai-sem.github.io
1
29
Starting in ~10 mins
SpaLab Research Lab@SpaLabUCR
Apr 14
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
36
Check out our latest article: Improving Peer Review in Top-Tier Cybersecurity Conferences -- A proposal in 10 points linkedin.com/pulse/improving… via @LinkedIn

Improving Peer Review in Top-Tier Cybersecurity Conferences -- A proposal in 10 points

1. Introduction The peer review process at top-tier cybersecurity conferences faces well-documented challenges: inconsistent review quality, overburdened program committees, scope creep in submission...

linkedin.com
1
36
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

Trustworthy AI Seminar Series

trust-ai-sem.github.io
1
204
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/2… Looking forward to comments and feedback!
38
🎙️ 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

Trustworthy AI Seminar Series

trust-ai-sem.github.io
2
410
📣 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

Trustworthy AI Seminar Series

trust-ai-sem.github.io
2
204
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

Trustworthy AI Seminar Series

trust-ai-sem.github.io
2
4
642
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

SMOTE and Mirrors: Exposing Privacy Leakage from Synthetic...

The Synthetic Minority Over-sampling Technique (SMOTE) is one of the most widely used methods for addressing class imbalance and generating synthetic data. Despite its popularity, little attention...

arxiv.org
1
107
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

To Shuffle or not to Shuffle: Auditing DP-SGD with Shuffling

The Differentially Private Stochastic Gradient Descent (DP-SGD) algorithm supports the training of machine learning (ML) models with formal Differential Privacy (DP) guarantees. Traditionally,...

arxiv.org
1
5
564
1
35
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/
1
146
SpaLab Research Lab retweeted
Konrad Rieck 🌈@mlsec
1 Jul 2025
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-papers/ ⏰ Deadline: Sept 24
15
37
5,737
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.pdf
4
3
29
910
.@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
1
1
174
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
1
1
46
Pre-print: arxiv.org/pdf/2504.08254.pdf Co-authored by @sundarmsa, Sofiane Mahou, and Emiliano De Cristofaro
40
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
3
98
Happy to announce that Dr. Emiliano De Cristofaro was recently recognized as a Distinguished Member of the ACM acm.org/media-center/2025/fe…

ACM has named 56 new Distinguished Members. All the 2024 inductees are registered members of the...

This year’s class of Distinguished Members are cited for contributions in a wide range of computing research areas including AI for healthcare, computing education, data management, human-computer...

acm.org
4
15
649
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

1
1
123
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
67
Load more