English
Related papers

Related papers: Turning Black Box into White Box: Dataset Distilla…

200 papers

To prevent unintentional data leakage, research community has resorted to data generators that can produce differentially private data for model training. However, for the sake of the data privacy, existing solutions suffer from either…

Cryptography and Security · Computer Science 2022-06-02 Tian Dong , Bo Zhao , Lingjuan Lyu

In recent years, the rapid development of deep neural networks has brought increased attention to the security and robustness of these models. While existing adversarial attack algorithms have demonstrated success in improving adversarial…

Machine Learning · Computer Science 2025-02-25 Wenyuan Wu , Zheng Liu , Yong Chen , Chao Su , Dezhong Peng , Xu Wang

Deep neural networks (DNNs) have achieved tremendous success in many tasks of machine learning, such as the image classification. Unfortunately, researchers have shown that DNNs are easily attacked by adversarial examples, slightly…

Computer Vision and Pattern Recognition · Computer Science 2017-11-17 Yujia Liu , Weiming Zhang , Shaohua Li , Nenghai Yu

Federated Learning (FL) allows users to share knowledge instead of raw data to train a model with high accuracy. Unfortunately, during the training, users lose control over the knowledge shared, which causes serious data privacy issues. We…

Machine Learning · Computer Science 2024-11-05 ShiMao Xu , Xiaopeng Ke , Xing Su , Shucheng Li , Hao Wu , Sheng Zhong , Fengyuan Xu

How much information about training samples can be leaked through synthetic data generated by Large Language Models (LLMs)? Overlooking the subtleties of information flow in synthetic data generation pipelines can lead to a false sense of…

Computation and Language · Computer Science 2026-02-13 Matthieu Meeus , Lukas Wutschitz , Santiago Zanella-Béguelin , Shruti Tople , Reza Shokri

The sharp increase in data-related expenses has motivated research into condensing datasets while retaining the most informative features. Dataset distillation has thus recently come to the fore. This paradigm generates synthetic datasets…

Machine Learning · Computer Science 2024-11-20 Jiawei Du , Xin Zhang , Juncheng Hu , Wenxin Huang , Joey Tianyi Zhou

Black-box risk scoring models permeate our lives, yet are typically proprietary or opaque. We propose Distill-and-Compare, a model distillation and comparison approach to audit such models. To gain insight into black-box models, we treat…

Machine Learning · Statistics 2018-10-12 Sarah Tan , Rich Caruana , Giles Hooker , Yin Lou

Dataset Distillation is used to create a concise, yet informative, synthetic dataset that can replace the original dataset for training purposes. Some leading methods in this domain prioritize long-range matching, involving the unrolling of…

Computer Vision and Pattern Recognition · Computer Science 2024-07-22 Dai Liu , Jindong Gu , Hu Cao , Carsten Trinitis , Martin Schulz

Deep ensembles excel in large-scale image classification tasks both in terms of prediction accuracy and calibration. Despite being simple to train, the computation and memory cost of deep ensembles limits their practicability. While some…

Machine Learning · Computer Science 2021-10-28 Giung Nam , Jongmin Yoon , Yoonho Lee , Juho Lee

With the rapid scaling of neural networks, data storage and communication demands have intensified. Dataset distillation has emerged as a promising solution, condensing information from extensive datasets into a compact set of synthetic…

Computer Vision and Pattern Recognition · Computer Science 2024-12-09 Ali Abbasi , Shima Imani , Chenyang An , Gayathri Mahalingam , Harsh Shrivastava , Maurice Diesendruck , Hamed Pirsiavash , Pramod Sharma , Soheil Kolouri

The digitization of medical records ushered in a new era of big data to clinical science, and with it the possibility that data could be shared, to multiply insights beyond what investigators could abstract from paper records. The need to…

Machine Learning · Computer Science 2021-06-03 Ofer Mendelevitch , Michael D. Lesh

Knowledge distillation is one of the most popular and effective techniques for knowledge transfer, model compression and semi-supervised learning. Most existing distillation approaches require the access to original or augmented training…

Machine Learning · Computer Science 2020-12-11 Liangchen Luo , Mark Sandler , Zi Lin , Andrey Zhmoginov , Andrew Howard

Data is used widely by service providers as input to inference systems to perform decision making for authorized tasks. The raw data however allows a service provider to infer other sensitive information it has not been authorized for. We…

Cryptography and Security · Computer Science 2020-10-26 Chong Xiao Wang , Wee Peng Tay

Fine-tuning through knowledge transfer from a pre-trained model on a large-scale dataset is a widely spread approach to effectively build models on small-scale datasets. In this work, we show that a recent adversarial attack designed for…

Machine Learning · Computer Science 2021-04-30 Ting-Wu Chin , Cha Zhang , Diana Marculescu

Knowledge distillation, i.e., one classifier being trained on the outputs of another classifier, is an empirically very successful technique for knowledge transfer between classifiers. It has even been observed that classifiers learn much…

Machine Learning · Computer Science 2021-05-28 Mary Phuong , Christoph H. Lampert

Dataset distillation compresses large-scale datasets into compact, highly informative synthetic data, significantly reducing storage and training costs. However, existing research primarily focuses on balanced datasets and struggles to…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Chenyang Jiang , Hang Zhao , Xinyu Zhang , Zhengcen Li , Qiben Shan , Shaocong Wu , Jingyong Su

Knowledge distillation, model extraction, and behavior transfer have become central concerns in frontier AI. The main risk is not merely copying, but the possibility that useful capability can be transferred more cheaply than the governance…

Artificial Intelligence · Computer Science 2026-03-27 Peng Wei , Wesley Shu

Dataset distillation seeks to condense datasets into smaller but highly representative synthetic samples. While diffusion models now lead all generative benchmarks, current distillation methods avoid them and rely instead on GANs or…

Computer Vision and Pattern Recognition · Computer Science 2025-10-09 Brian B. Moser , Federico Raue , Sebastian Palacio , Stanislav Frolov , Andreas Dengel

The current RAG system requires uploading plaintext documents to the cloud, risking private data leakage. Parametric RAG (PRAG) encodes documents as LoRA parameters within LLMs, offering a possible way to reduce exposure of raw content.…

Computation and Language · Computer Science 2025-12-01 Jinwen Chen , Hainan Zhang , Liang Pang , Yongxin Tong , Haibo Zhou , Yuan Zhan , Wei Lin , Zhiming Zheng

Public image diffusion models are now powerful enough that an attacker without the resources to train a tabular-specific generator may repurpose one off the shelf. This study tests that possibility directly. An unmodified Stable Diffusion…

Cryptography and Security · Computer Science 2026-05-04 Adam Arthur , Christopher Schwartz
‹ Prev 1 8 9 10 Next ›