Matthew Jagielski
19 papers · 2019–2025 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (21) π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π¬
Deep Specialist
(11)
π€
Dynamic Duo
(10)
π
Grand Slam
β‘
Prolific Year Β· Productive
β
The Questioner
(2)
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(74)
Top co-authors
Research topics
Machine Learning
(15)
Application Areas
(12)
Artificial Intelligence
(8)
Natural Language Processing
(7)
Core AI
(7)
Resources & Methods
(5)
Deep Learning
(4)
Security & Privacy
(4)
Learning Types Β· Machine Learning
(3)
Learning Types Β· Deep Learning
(3)
Core Methods
(2)
Differential Privacy
(2)
Generation
(2)
Learning Paradigms
(2)
Optimization & Theory
(2)
Keywords
differential privacy
(8)
privacy auditing
(3)
language model
(3)
training data
(3)
large language model
(3)
privacy attack
(2)
membership inference
(2)
privacy leakage
(2)
stochastic gradient descent
(2)
machine learning
(2)
non-convex optimization
(1)
machine unlearning
(1)
model forgetting
(1)
privacy-preserving learning
(1)
model distillation
(1)
adversarial robustness
(1)
knowledge distillation
(1)
prototype learning
(1)
model training
(1)
adversarial perturbation
(1)
Papers
Differentially Private Prototypes for Imbalanced Transfer Learning
AAAI 2025
Exploring and Mitigating Adversarial Manipulation of Voting-Based Leaderboards
ICML 2025
Language Models May Verbatim Complete Text They Were Not Explicitly Trained On
ICML 2025
On Evaluating the Durability of Safeguards for Open-Weight LLMs
ICLR 2025
Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training
ACL 2025
Scalable Extraction of Training Data from Aligned, Production Language Models
ICLR 2025
The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
ICLR 2025
Auditing Private Prediction
ICML 2024
Stealing part of a production language model
ICML 2024
Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Models
NAACL 2024
Are aligned neural networks adversarially aligned?
NeurIPS 2023
Counterfactual Memorization in Neural Language Models
NeurIPS 2023
Measuring Forgetting of Memorized Training Examples
ICLR 2023
Privacy Auditing with One (1) Training Run
NeurIPS 2023
Quantifying Memorization Across Neural Language Models
ICLR 2023
Students Parrot Their Teachers: Membership Inference on Model Distillation
NeurIPS 2023
The Privacy Onion Effect: Memorization is Relative
NeurIPS 2022
Auditing Differentially Private Machine Learning: How Private is Private SGD?
NeurIPS 2020
Differentially Private Fair Learning
ICML 2019