paper-with-me

홈 › Papers

Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks

2023-10-10 · Lukas Struppek, Dominik Hintersdorf, Kristian Kersting

Label smoothing -- using softened labels instead of hard ones -- is a widely adopted regularization method for deep learning, showing diverse benefits such as enhanced generalization and calibration. Its implications for preserving model privacy, however, have remained unexplored. To fill this gap, we investigate the impact of label smoothing on model inversion attacks (MIAs), which aim to generate class-representative samples by exploiting the knowledge encoded in a classifier, thereby inferring sensitive information about its training data. Through extensive analyses, we uncover that traditional label smoothing fosters MIAs, thereby increasing a model's privacy leakage. Even more, we reveal that smoothing with negative factors counters this trend, impeding the extraction of class-related information and leading to privacy preservation, beating state-of-the-art defenses. This establishes a practical and powerful novel way for enhancing model resilience against MIAs.

📄 PDF Abstract BibTeX arXiv:2310.06549

Code (1)

LukasStruppek/Plug-and-Play-Attacks 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Towards a Better Understanding of Label Smoothing in Neural Machine Translation

2020-12-01 · Asian Chapter of the Association for Computational Linguistics 2020 · Yingbo Gao, Weiyue Wang, Christian Herold, Zijian Yang 외

In order to combat overfitting and in pursuit of better generalization, label smoothing is widely applied in modern neural machine translation systems. The core idea is to penalize over-confident outputs and regularize t…

Machine TranslationTranslation

Node Dependent Local Smoothing for Scalable Graph Learning

2021-10-27 · NeurIPS 2021 12 · Wentao Zhang, Mingyu Yang, Zeang Sheng, Yang Li 외

Recent works reveal that feature or label smoothing lies at the core of Graph Neural Networks (GNNs). Concretely, they show feature smoothing combined with simple linear regression achieves comparable performance with th…

Graph Learning

PairNorm: Tackling Oversmoothing in GNNs

2019-09-26 · ICLR 2020 1 · Lingxiao Zhao, Leman Akoglu

The performance of graph neural nets (GNNs) is known to gradually decrease with increasing number of layers. This decay is partly attributed to oversmoothing, where repeated graph convolutions eventually make node embedd…

Label Smoothing Improves Machine Unlearning

2024-06-11 · Zonglin Di, Zhaowei Zhu, Jinghan Jia, Jiancheng Liu 외

The objective of machine unlearning (MU) is to eliminate previously learned data from a model. However, it is challenging to strike a balance between computation cost and performance when using existing MU techniques. Ta…

Machine Unlearning

Does label smoothing mitigate label noise?

2020-03-05 · ICML 2020 1 · Michal Lukasik, Srinadh Bhojanapalli, Aditya Krishna Menon, Sanjiv Kumar

Label smoothing is commonly used in training deep learning models, wherein one-hot training labels are mixed with uniform label vectors. Empirically, smoothing has been shown to improve both predictive performance and mo…

Learning with noisy labels