Tootfinder

Distance Approximating Minors for Planar and Minor-Free Graphs
Hsien-Chih Chang, Jonathan Conroy
https://arxiv.org/abs/2509.17226 https://arxiv.org/pdf/250…

Distance Approximating Minors for Planar and Minor-Free Graphs
Given an edge-weighted graph $G$ and a subset of vertices $T$ called terminals, an $α$-distance-approximating minor ($α$-DAM) of $G$ is a graph minor $H$ of $G$ that contains all terminals, such that the distance between every pair of terminals is preserved up to a factor of $α$. Distance-approximating minor would be an effective distance-sketching structure on minor-closed family of graphs; in the constant-stretch regime it generalizes the well-known Steiner Point Removal problem by allowin…

Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning
Zhaoyang Chu, Yao Wan, Zhikun Zhang, Di Wang, Zhou Yang, Hongyu Zhang, Pan Zhou, Xuanhua Shi, Hai Jin, David Lo
https://arxiv.org/abs/2509.13755

Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning
While Code Language Models (CLMs) have demonstrated superior performance in software engineering tasks such as code generation and summarization, recent empirical studies reveal a critical privacy vulnerability: these models exhibit unintended memorization of sensitive training data, enabling verbatim reproduction of confidential information when specifically prompted. To address this issue, several approaches, including training data de-duplication and differential privacy augmentation, have b…

Substituting Proof of Work in Blockchain with Training-Verified Collaborative Model Computation
Mohammad Ishzaz Asif Rafid, Morsalin Sakib
https://arxiv.org/abs/2508.12138 https…

Substituting Proof of Work in Blockchain with Training-Verified Collaborative Model Computation
Bitcoin's Proof of Work (PoW) mechanism, while central to achieving decentralized consensus, has long been criticized for excessive energy use and hardware inefficiencies \cite{devries2018bitcoin, truby2018decarbonizing}. This paper introduces a hybrid architecture that replaces Bitcoin's traditional PoW with a centralized, cloud-based collaborative training framework. In this model, miners contribute computing resources to train segments of horizontally scaled machine learning models on prepro…

Next Interest Flow: A Generative Pre-training Paradigm for Recommender Systems by Modeling All-domain Movelines
Chen Gao, Zixin Zhao, Lv Shao, Tong Liu
https://arxiv.org/abs/2510.11317

Next Interest Flow: A Generative Pre-training Paradigm for Recommender Systems by Modeling All-domain Movelines
Click-Through Rate (CTR) prediction, a cornerstone of modern recommender systems, has been dominated by discriminative models that react to past user behavior rather than proactively modeling user intent. Existing generative paradigms attempt to address this but suffer from critical limitations: Large Language Model (LLM) based methods create a semantic mismatch by forcing e-commerce signals into a linguistic space, while ID-based generation is constrained by item memorization and cold-start is…

MIA-EPT: Membership Inference Attack via Error Prediction for Tabular Data
Eyal German, Daniel Samira, Yuval Elovici, Asaf Shabtai
https://arxiv.org/abs/2509.13046 https://

MIA-EPT: Membership Inference Attack via Error Prediction for Tabular Data
Synthetic data generation plays an important role in enabling data sharing, particularly in sensitive domains like healthcare and finance. Recent advances in diffusion models have made it possible to generate realistic, high-quality tabular data, but they may also memorize training records and leak sensitive information. Membership inference attacks (MIAs) exploit this vulnerability by determining whether a record was used in training. While MIAs have been studied in images and text, their use …

Position: Privacy Is Not Just Memorization!
Niloofar Mireshghallah, Tianshi Li
https://arxiv.org/abs/2510.01645 https://arxiv.org/pdf/2510.01645

Position: Privacy Is Not Just Memorization!
The discourse on privacy risks in Large Language Models (LLMs) has disproportionately focused on verbatim memorization of training data, while a constellation of more immediate and scalable privacy threats remain underexplored. This position paper argues that the privacy landscape of LLM systems extends far beyond training data extraction, encompassing risks from data collection practices, inference-time context leakage, autonomous agent capabilities, and the democratization of surveillance thr…