activity
20142025
most citedUnleashing the Power of Randomization in Auditing Differentially Private ML

5 citations · 10 across the 9 of their papers we have counts for

collaborators

9 papers

cs.LG2025

Text-to-Image Models Leave Identifiable Signatures: Implications for Leaderboard Security

Ali Naseh, Anshuman Suri, Yuefeng Peng +3

Generative AI leaderboards are central to evaluating model capabilities, but remain vulnerable to manipulation. Among key adversarial objectives is rank manipulation, where an atta…

cs.CL2025

R1dacted: Investigating Local Censorship in DeepSeek's R1 Language Model

Ali Naseh, Harsh Chaudhari, Jaechul Roh +3

DeepSeek recently released R1, a high-performing large language model (LLM) optimized for reasoning tasks. Despite its efficient training pipeline, R1 achieves competitive performa…

cs.LG2023

Dropout Attacks

Andrew Yuan, Alina Oprea, Cheng Tan

Dropout is a common operator in deep learning, aiming to prevent overfitting by randomly dropping neurons during training. This paper introduces a new family of poisoning attacks a…

cs.CR20231 cited

Poisoning Network Flow Classifiers

Giorgio Severi, Simona Boboila, Alina Oprea +3

As machine learning (ML) classifiers increasingly oversee the automated monitoring of network traffic, studying their resilience against adversarial attacks becomes critical. This…

cs.LG20235 cited

Unleashing the Power of Randomization in Auditing Differentially Private ML

Krishna Pillutla, Galen Andrew, Peter Kairouz +3

We present a rigorous methodology for auditing differentially private machine learning algorithms by adding multiple carefully designed examples called canaries. We take a first pr…

cs.CR20221 cited

Network-Level Adversaries in Federated Learning

Giorgio Severi, Matthew Jagielski, Gökberk Yar +3

Federated learning is a popular strategy for training models on distributed, sensitive data, while preserving data privacy. Prior work identified a range of security threats on fed…