5 accepted papers
Aligning large language models (LLMs) to heterogeneous and rapidly evolving safety requirements remains a critical challenge. Existing instruction-tuned LLMs and standalone safety classifiers often fail to generalize to new safety configurations, motivating the need for Reward Models (RMs) that are …
We present a black-box model-stealing attack that recovers private vision-tokenizer configurations of deployed vision-language models (VLMs), including the visual patch size and input preprocessing pipeline. The key idea is a task-level side channel induced by ViT-style patchification: when a synthe…
Experiment design has a rich history dating back over a century and has found many critical applications across various fields since then. The use and collection of users’ data in experiments often involve sensitive personal information, so additional measures to protect individual privacy are requi…
We consider the federated frequency estimation problem, where each user holds a private item $X_i$ from a size-$d$ domain and a server aims to estimate the empirical frequency (i.e., histogram) of $n$ items with $n \ll d$. Without any security and privacy considerations, each user can communicate it…
Federated analytics seeks to compute accurate statistics from data distributed across users’ devices while providing a suitable privacy guarantee and being practically feasible to implement and scale. In this paper, we show how a strong (epsilon, delta)-Differential Privacy (DP) guarantee can be ach…