paper-with-me

Papers

FaceLeaks: Inference Attacks against Transfer Learning Models via Black-box Queries

2020-10-27 · Seng Pei Liew, Tsubasa Takahashi

Transfer learning is a useful machine learning framework that allows one to build task-specific models (student models) without significantly incurring training costs using a single powerful model (teacher model) pre-trained with a large amount of data. The teacher model may contain private data, or interact with private inputs. We investigate if one can leak or infer such private information without interacting with the teacher model directly. We describe such inference attacks in the context of face recognition, an application of transfer learning that is highly sensitive to personal privacy. Under black-box and realistic settings, we show that existing inference techniques are ineffective, as interacting with individual training instances through the student models does not reveal information about the teacher. We then propose novel strategies to infer from aggregate-level information. Consequently, membership inference attacks on the teacher model are shown to be possible, even when the adversary has access only to the student models. We further demonstrate that sensitive attributes can be inferred, even in the case where the adversary has limited auxiliary information. Finally, defensive strategies are discussed and evaluated. Our extensive study indicates that information leakage is a real privacy threat to the transfer learning framework widely used in real-life situations.

📄 PDF Abstract BibTeX arXiv:2010.14023

Code (0)

등록된 구현이 없습니다.

Tasks

Face RecognitionTransfer Learning

Similar Papers 제목 키워드 기반

RobustBlack: Challenging Black-Box Adversarial Attacks on State-of-the-Art Defenses

2024-12-30 · Mohamed Djilani, Salah Ghamizi, Maxime Cordy

Although adversarial robustness has been extensively studied in white-box settings, recent advances in black-box attacks (including transfer- and query-based approaches) are primarily benchmarked against weak defenses, l…

Adversarial Robustness

Exploring the Space of Black-box Attacks on Deep Neural Networks

2017-12-27 · ICLR 2018 1 · Arjun Nitin Bhagoji, Warren He, Bo Li, Dawn Song

Existing black-box attacks on deep neural networks (DNNs) so far have largely focused on transferability, where an adversarial instance generated for a locally trained model can "transfer" to attack other learning models…

Practical Black-box Attacks on Deep Neural Networks using Efficient Query Mechanisms

2018-09-01 · ECCV 2018 9 · Arjun Nitin Bhagoji, Warren He, Bo Li, Dawn Song

Existing black-box attacks on deep neural networks (DNNs) have largely focused on transferability, where an adversarial instance generated for a locally trained model can “transfer” to attack other learning models. I…

Model Inversion Attack against Transfer Learning: Inverting a Model without Accessing It

2022-03-13 · Dayong Ye, Huiqiang Chen, Shuai Zhou, Tianqing Zhu 외

Transfer learning is an important approach that produces pre-trained teacher models which can be used to quickly build specialized student models. However, recent research on transfer learning has found that it is vulner…

modelTransfer Learning

SEGA: A Transferable Signed Ensemble Gaussian Black-Box Attack against No-Reference Image Quality Assessment Models

2025-09-23 · Yujia Liu, Dingquan Li, Zhixuan Li, Tiejun Huang arxiv

No-Reference Image Quality Assessment (NR-IQA) models play an important role in various real-world applications. Recently, adversarial attacks against NR-IQA models have attracted increasing attention, as they provide va…

No-Reference Image Quality Assessment