Reza Shokri
19 papers · 2018–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π Renaissance Researcher (5) π Interdisciplinary Bridge π Conference Polyglot (7) π Academic Marathon (7) πΊοΈ Taxonomy Completionist (19)
π
Conference Polyglot
(7)
π
Renaissance Researcher
(5)
π₯
Unstoppable
(5)
β‘
Prolific Year
(5)
π
Century Club
(18)
β
The Questioner
(2)
Conferences
ICLR (5)
NIPS (4)
EMNLP (3)
ICML (3)
EACL (2)
AISTATS (1)
IJCAI (1)
Top co-authors
Research topics
Keywords
membership inference
(3)
differential privacy
(3)
stochastic gradient descent
(2)
privacy leakage
(2)
privacy bound
(2)
language model
(2)
large language model
(2)
masked language model
(1)
kl divergence
(1)
privacy attack
(1)
non-parametric model
(1)
graphical model
(1)
gradient norm
(1)
generative adversarial network
(1)
hallucination detection
(1)
bayesian network
(1)
privacy risk
(1)
adversarial attack
(1)
watermark detection
(1)
trajectory generation
(1)
Papers
Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity
EACL 2026
The Canaryβs Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text
ICML 2025
Context-Aware Membership Inference Attacks against Pre-trained Large Language Models
EMNLP 2025
Watermark Smoothing Attacks against Language Models
EMNLP 2025
Minerva: A Programmable Memory Test Benchmark for Language Models
ICML 2025
How much of my dataset did you use? Quantitative Data Usage Inference in Machine Learning
ICLR 2025
Low-Cost High-Power Membership Inference Attacks
ICML 2024
Leave-one-out Distinguishability in Machine Learning
ICLR 2024
Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
ICLR 2024
Smaller Language Models are Better Zero-shot Machine-Generated Text Detectors
EACL 2024
Share Your Representation Only: Guaranteed Improvement of the Privacy-Utility Tradeoff in Federated Learning
ICLR 2023
Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks
NIPS 2023
Unified Enhancement of Privacy Bounds for Mixture Mechanisms via $f$-Differential Privacy
NIPS 2023
Bias Propagation in Federated Learning
ICLR 2023
Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks
EMNLP 2022
Differentially Private Learning Needs Hidden State (Or Much Faster Convergence)
NIPS 2022
Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent
NIPS 2021
Quantifying the Privacy Risks of Learning High-Dimensional Graphical Models
AISTATS 2021
A Non-Parametric Generative Model for Human Trajectories
IJCAI 2018