Matthew Jagielski

Venues

Frequent coauthors

Papers

1. AISec '25: 18th ACM Workshop on Artificial Intelligence and SecurityBibTeX ⧉
   CCS 2025 ·

   Maura Pintor

   , Matthew Jagielski,

   Ruoxi Jia
2. Cascading Adversarial Bias from Injection to Distillation in Language ModelsBibTeX ⧉
   CCS 2025 ·

   Harsh Chaudhari

   ,

   Jamie Hayes

   , Matthew Jagielski,

   Ilia Shumailov

   ,

   Milad Nasr

   ,

   Alina Oprea
3. Differentially Private Prototypes for Imbalanced Transfer LearningBibTeX ⧉
   AAAI 2025 ·

   Dariush Wahdany

   , Matthew Jagielski,

   Adam Dziedzic

   ,

   Franziska Boenisch
4. Exploring and Mitigating Adversarial Manipulation of Voting-Based LeaderboardsBibTeX ⧉
   ICML 2025 ·

   Yangsibo Huang

   ,

   Milad Nasr

   ,

   Anastasios Nikolas Angelopoulos

   ,

   Nicholas Carlini

   ,

   Wei-Lin Chiang

   ,

   Christopher A. Choquette-Choo

   ,

   Daphne Ippolito

   , Matthew Jagielski,

   Katherine Lee

   ,

   Ken Liu

   ,

   Ion Stoica

   ,

   Florian Tramèr

   ,

   Chiyuan Zhang
5. Exploring the limits of strong membership inference attacks on large language modelsBibTeX ⧉
   NeurIPS 2025 ·

   Jamie Hayes

   ,

   Ilia Shumailov

   ,

   Christopher A. Choquette-Choo

   , Matthew Jagielski,

   Georgios Kaissis

   ,

   Milad Nasr

   ,

   Meenatchi Sundaram Muthu Selva Annamalai

   ,

   Niloofar Mireshghallah

   ,

   Igor Shilov

   ,

   Matthieu Meeus

   ,

   Yves-Alexandre de Montjoye

   ,

   Katherine Lee

   ,

   Franziska Boenisch

   ,

   Adam Dziedzic

   ,

   A. Feder Cooper
6. Language Models May Verbatim Complete Text They Were Not Explicitly Trained OnBibTeX ⧉
   ICML 2025 ·

   Ken Liu

   ,

   Christopher A. Choquette-Choo

   , Matthew Jagielski,

   Peter Kairouz

   ,

   Sanmi Koyejo

   ,

   Percy Liang

   ,

   Nicolas Papernot
7. Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and ResearchBibTeX ⧉
   NeurIPS 2025 ·

   A. Feder Cooper

   ,

   Christopher A. Choquette-Choo

   ,

   Miranda Bogen

   ,

   Kevin Klyman

   , Matthew Jagielski,

   Katja Filippova

   ,

   Ken Liu

   ,

   Alexandra Chouldechova

   ,

   Jamie Hayes

   ,

   Yangsibo Huang

   ,

   Eleni Triantafillou

   ,

   Peter Kairouz

   ,

   Nicole Mitchell

   ,

   Niloofar Mireshghallah

   ,

   Abigail Z. Jacobs

   ,

   James Grimmelmann

   ,

   Vitaly Shmatikov

   ,

   Christopher De Sa

   ,

   Ilia Shumailov

   ,

   Andreas Terzis

   ,

   Solon Barocas

   ,

   Jennifer Wortman Vaughan

   ,

   danah boyd

   ,

   Yejin Choi

   ,

   Sanmi Koyejo

   ,

   Fernando A. Delgado

   ,

   Percy Liang

   ,

   Daniel E. Ho

   ,

   Pamela Samuelson

   ,

   Miles Brundage

   ,

   David Bau

   ,

   Seth Neel

   ,

   Hanna M. Wallach

   ,

   Amy Cyphert

   ,

   Mark A. Lemley

   ,

   Nicolas Papernot

   ,

   Katherine Lee
8. On Evaluating the Durability of Safeguards for Open-Weight LLMsBibTeX ⧉
   ICLR 2025 ·

   Xiangyu Qi

   ,

   Boyi Wei

   ,

   Nicholas Carlini

   ,

   Yangsibo Huang

   ,

   Tinghao Xie

   ,

   Luxi He

   , Matthew Jagielski,

   Milad Nasr

   ,

   Prateek Mittal

   ,

   Peter Henderson
9. Privacy Ripple Effects from Adding or Removing Personal Information in Language Model TrainingBibTeX ⧉
   ACL 2025 ·

   Jaydeep Borkar

   , Matthew Jagielski,

   Katherine Lee

   ,

   Niloofar Mireshghallah

   ,

   David A. Smith

   ,

   Christopher A. Choquette-Choo
10. Scalable Extraction of Training Data from Aligned, Production Language ModelsBibTeX ⧉
    ICLR 2025 ·

    Milad Nasr

    ,

    Javier Rando

    ,

    Nicholas Carlini

    ,

    Jonathan Hayase

    , Matthew Jagielski,

    A. Feder Cooper

    ,

    Daphne Ippolito

    ,

    Christopher A. Choquette-Choo

    ,

    Florian Tramèr

    ,

    Katherine Lee
11. The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGDBibTeX ⧉
    ICLR 2025 ·

    Milad Nasr

    ,

    Thomas Steinke

    ,

    Borja Balle

    ,

    Christopher A. Choquette-Choo

    ,

    Arun Ganesh

    , Matthew Jagielski,

    Jamie Hayes

    ,

    Abhradeep Guha Thakurta

    ,

    Adam Smith

    ,

    Andreas Terzis
12. AISec '24: 17th ACM Workshop on Artificial Intelligence and SecurityBibTeX ⧉
    CCS 2024 ·

    Maura Pintor

    , Matthew Jagielski,

    Xinyun Chen
13. Auditing Private PredictionBibTeX ⧉
    ICML 2024 ·

    Karan Chadha

    , Matthew Jagielski,

    Nicolas Papernot

    ,

    Christopher A. Choquette-Choo

    ,

    Milad Nasr
14. Poisoning Web-Scale Training Datasets is PracticalBibTeX ⧉
    S&P 2024 ·

    Nicholas Carlini

    , Matthew Jagielski,

    Christopher A. Choquette-Choo

    ,

    Daniel Paleka

    ,

    Will Pearce

    ,

    Hyrum S. Anderson

    ,

    Andreas Terzis

    ,

    Kurt Thomas

    ,

    Florian Tramèr
15. Privacy Side Channels in Machine Learning SystemsBibTeX ⧉
    USENIX Security 2024 ·

    Edoardo Debenedetti

    ,

    Giorgio Severi

    ,

    Milad Nasr

    ,

    Christopher A. Choquette-Choo

    , Matthew Jagielski,

    Eric Wallace

    ,

    Nicholas Carlini

    ,

    Florian Tramèr
16. Stealing part of a production language modelBibTeX ⧉
    ICML 2024 ·

    Nicholas Carlini

    ,

    Daniel Paleka

    ,

    Krishnamurthy Dj Dvijotham

    ,

    Thomas Steinke

    ,

    Jonathan Hayase

    ,

    A. Feder Cooper

    ,

    Katherine Lee

    , Matthew Jagielski,

    Milad Nasr

    ,

    Arthur Conmy

    ,

    Eric Wallace

    ,

    David Rolnick

    ,

    Florian Tramèr
17. Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language ModelsBibTeX ⧉
    NAACL 2024 ·

    Aldo G. Carranza

    ,

    Rezsa Farahani

    ,

    Natalia Ponomareva

    ,

    Alexey Kurakin

    , Matthew Jagielski,

    Milad Nasr