GAN Enhanced Membership Inference: A Passive Local Attack in Federated Learning

Zhang, Jingwen; Zhang, Jiale; Chen, Junjun; Yu, Shui

doi:10.1109/icc40277.2020.9148790

Cited by 75 publications

(33 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to other DL algorithms, GANs have also been shown to be vulnerable to malicious privacy breaches such as membership attacks, which are adversarial attacks designed to identify which images or patients were used in model training. [66][67][68][69][70][71][72][73] These attacks essentially operate on the premise that DL algorithms perform better on images that they were trained on 74 and depend on whether the attacker has access to the code underlying the model (white-box) or not (blackbox). 75 While defense against these attacks remains an active area of research, 71,74 they are costly, 74 and some defense approaches that require re-training the model may even decrease the performance of the original DL algorithm.…”

Section: Privacymentioning

confidence: 99%

Deepfakes in Ophthalmology

Chen

Coyner

Chan

et al. 2021

Ophthalmology Science

View full text Add to dashboard Cite

Section: Privacymentioning

confidence: 99%

Deepfakes in Ophthalmology

Chen

Coyner

Chan

et al. 2021

Ophthalmology Science

View full text Add to dashboard Cite

“…• Passive [82], [83]: the attacker, honest-but-curious, could only read or eavesdrop on communications, the local model, and the dataset.…”

Section: B Targeting Confidentialitymentioning

confidence: 99%

“…Leveraging the inferred information, the authors in [91] performed an improved Model Inversion attack. Similarly, the authors in [82] used a GAN for empowering their attack. The GAN generated data samples that followed the same data distribution as the real one.…”

Section: B Targeting Confidentialitymentioning

confidence: 99%

See 1 more Smart Citation

On the Security & Privacy in Federated Learning

Abad¹,

Picek²,

Ramírez-Durán³

et al. 2021

Preprint

View full text Add to dashboard Cite

Advances in Machine Learning (ML) and its wide range of applications boosted its popularity. Recent privacy awareness initiatives as the EU General Data Protection Regulation (GDPR) -European Parliament and Council Regulation No 2016/679, subdued ML to privacy and security assessments. Federated Learning (FL) grants a privacy-driven, decentralized training scheme that improves ML models' security. The industry's fast-growing adaptation and security evaluations of FL technology exposed various vulnerabilities. Depending on the FL phase, i.e., training or inference, the adversarial actor capabilities, and the attack type threaten FL's confidentiality, integrity, or availability (CIA). Therefore, the researchers apply the knowledge from distinct domains as countermeasures, like cryptography and statistics.This work assesses the CIA of FL by reviewing the state-of-theart (SoTA) for creating a threat model that embraces the attack's surface, adversarial actors, capabilities, and goals. We propose the first unifying taxonomy for attacks and defenses by applying this model. Additionally, we provide critical insights extracted by applying the suggested novel taxonomies to the SoTA, yielding promising future research directions.

show abstract

“…In particular, at each iteration, the attacker, i.e., an honest-but-curious participant, receives the current aggregated updates, from which he can get the aggregated updates from other participants. Melis et [136] Federated CV Zhang [137] Federated CV Yuan [138] Federated NLP Property Hitaj [104] Federated CV Wang [105],Song [139] Federated CV Zhang [140] Centralized NLP…”

Section: B Membership Inferencementioning

confidence: 99%

Robust and Privacy-Preserving Collaborative Learning: A Comprehensive Survey

Guo¹,

Zhang²,

Yang³

et al. 2021

Preprint

View full text Add to dashboard Cite

With the rapid demand of data and computational resources in deep learning systems, a growing number of algorithms to utilize collaborative machine learning techniques, for example, federated learning, to train a shared deep model across multiple participants. It could effectively take advantage of resource of each participant and obtain a more powerful learning system. However, integrity and privacy threats in such systems have greatly obstructed the applications of collaborative learning. And a large amount of works have been proposed to maintain the model integrity and mitigate the privacy leakage of training data during the training phase for different collaborate learning systems. Compared with existing surveys that mainly focus on one specific collaborate learning system, this survey aims to provide a systematic and comprehensive review of security and privacy researches in collaborative learning. Our survey first provides the system overview of collaborative learning, followed by an brief introduction of integrity and privacy threats. In an organized way, we then detail the existing integrity and privacy attacks as well as their defenses. We also list some open problems in this area and opensource the related papers on GitHub: https://github.com/csl-cqu/awesome-secure-collebrativelearning-papers.

show abstract

GAN Enhanced Membership Inference: A Passive Local Attack in Federated Learning

Cited by 75 publications

References 13 publications

Deepfakes in Ophthalmology

Deepfakes in Ophthalmology

On the Security & Privacy in Federated Learning

Robust and Privacy-Preserving Collaborative Learning: A Comprehensive Survey

Contact Info

Product

Resources

About