paper-with-me

Papers

Bayesian Perspective on Memorization and Reconstruction

2025-05-29 · Haim Kaplan, Yishay Mansour, Kobbi Nissim, Uri Stemmer

We introduce a new Bayesian perspective on the concept of data reconstruction, and leverage this viewpoint to propose a new security definition that, in certain settings, provably prevents reconstruction attacks. We use our paradigm to shed new light on one of the most notorious attacks in the privacy and memorization literature - fingerprinting code attacks (FPC). We argue that these attacks are really a form of membership inference attacks, rather than reconstruction attacks. Furthermore, we show that if the goal is solely to prevent reconstruction (but not membership inference), then in some cases the impossibility results derived from FPC no longer apply.

📄 PDF Abstract BibTeX arXiv:2505.23658

Code (0)

등록된 구현이 없습니다.

Tasks

Memorization

Similar Papers 제목 키워드 기반

A Law of Data Reconstruction for Random Features (and Beyond)

2025-09-26 · Leonardo Iurada, Simone Bombari, Tatiana Tommasi, Marco Mondelli arxiv

Large-scale deep learning models are known to memorize parts of the training set. In machine learning theory, memorization is often framed as interpolation or label fitting, and classical results show that this can be ac…

Do LLMs Really Memorize Personally Identifiable Information? Revisiting PII Leakage with a Cue-Controlled Memorization Framework

2026-01-07 · Xiaoyu Luo, Yiyi Chen, Qiongxiu Li, Johannes Bjerva arxiv

Large Language Models (LLMs) have been reported to "leak" Personally Identifiable Information (PII), with successful PII reconstruction often interpreted as evidence of memorization. We propose a principled revision of m…

A Bayesian Perspective on the Role of Epistemic Uncertainty for Delayed Generalization in In-Context Learning

2026-04-14 · Abdessamed Qchohi, Simone Rossi arxiv

In-context learning enables transformers to adapt to new tasks from a few examples at inference time, while grokking highlights that this generalization can emerge abruptly only after prolonged training. We study task ge…

A Multi-Perspective Analysis of Memorization in Large Language Models

2024-05-19 · Bowen Chen, Namgi Han, Yusuke Miyao

Large Language Models (LLMs), trained on massive corpora with billions of parameters, show unprecedented performance in various fields. Though surprised by their excellent performances, researchers also noticed some spec…

Memorization

Memorization Control in Diffusion Models from Denoising-centric Perspective

2026-01-29 · Thuy Phuong Vu, Mai Viet Hoang Do, Minhhuy Le, Dinh-Cuong Hoang 외 arxiv

Controlling memorization in diffusion models is critical for applications that require generated data to closely match the training distribution. Existing approaches mainly focus on data centric or model centric modifica…