Efficient passive membership inference attack in federated learning
- URL: http://arxiv.org/abs/2111.00430v1
- Date: Sun, 31 Oct 2021 08:21:23 GMT
- Title: Efficient passive membership inference attack in federated learning
- Authors: Oualid Zari, Chuan Xu, Giovanni Neglia
- Abstract summary: In cross-device federated learning (FL) setting, clients such as mobiles cooperate with the server to train a global machine learning model, while maintaining their data locally.
Recent work shows that client's private information can still be disclosed to an adversary who just eavesdrops the messages exchanged between the client and the server.
We propose a new passive inference attack that requires much less power and memory than existing methods.
- Score: 12.878319040684211
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In cross-device federated learning (FL) setting, clients such as mobiles
cooperate with the server to train a global machine learning model, while
maintaining their data locally. However, recent work shows that client's
private information can still be disclosed to an adversary who just eavesdrops
the messages exchanged between the client and the server. For example, the
adversary can infer whether the client owns a specific data instance, which is
called a passive membership inference attack. In this paper, we propose a new
passive inference attack that requires much less computation power and memory
than existing methods. Our empirical results show that our attack achieves a
higher accuracy on CIFAR100 dataset (more than $4$ percentage points) with
three orders of magnitude less memory space and five orders of magnitude less
calculations.
Related papers
- Efficient Federated Unlearning under Plausible Deniability [1.795561427808824]
Machine unlearning addresses this by modifying the ML parameters in order to forget the influence of a specific data point on its weights.
Recent literature has highlighted that the contribution from data point(s) can be forged with some other data points in the dataset with probability close to one.
This paper introduces an efficient way to achieve federated unlearning, by employing a privacy model which allows the FL server to plausibly deny the client's participation.
arXiv Detail & Related papers (2024-10-13T18:08:24Z) - Boosting Communication Efficiency of Federated Learning's Secure Aggregation [22.943966056320424]
Federated Learning (FL) is a decentralized machine learning approach where client devices train models locally and send them to a server.
FL is vulnerable to model inversion attacks, where the server can infer sensitive client data from trained models.
Google's Secure Aggregation (SecAgg) protocol addresses this data privacy issue by masking each client's trained model.
This poster introduces a Communication-Efficient Secure Aggregation (CESA) protocol that substantially reduces this overhead.
arXiv Detail & Related papers (2024-05-02T10:00:16Z) - Robust Federated Learning Mitigates Client-side Training Data Distribution Inference Attacks [48.70867241987739]
InferGuard is a novel Byzantine-robust aggregation rule aimed at defending against client-side training data distribution inference attacks.
The results of our experiments indicate that our defense mechanism is highly effective in protecting against client-side training data distribution inference attacks.
arXiv Detail & Related papers (2024-03-05T17:41:35Z) - Blockchain-enabled Trustworthy Federated Unlearning [50.01101423318312]
Federated unlearning is a promising paradigm for protecting the data ownership of distributed clients.
Existing works require central servers to retain the historical model parameters from distributed clients.
This paper proposes a new blockchain-enabled trustworthy federated unlearning framework.
arXiv Detail & Related papers (2024-01-29T07:04:48Z) - FedBayes: A Zero-Trust Federated Learning Aggregation to Defend Against
Adversarial Attacks [1.689369173057502]
Federated learning has created a decentralized method to train a machine learning model without needing direct access to client data.
malicious clients are able to corrupt the global model and degrade performance across all clients within a federation.
Our novel aggregation method, FedBayes, mitigates the effect of a malicious client by calculating the probabilities of a client's model weights.
arXiv Detail & Related papers (2023-12-04T21:37:50Z) - FedDefender: Client-Side Attack-Tolerant Federated Learning [60.576073964874]
Federated learning enables learning from decentralized data sources without compromising privacy.
It is vulnerable to model poisoning attacks, where malicious clients interfere with the training process.
We propose a new defense mechanism that focuses on the client-side, called FedDefender, to help benign clients train robust local models.
arXiv Detail & Related papers (2023-07-18T08:00:41Z) - Client-specific Property Inference against Secure Aggregation in
Federated Learning [52.8564467292226]
Federated learning has become a widely used paradigm for collaboratively training a common model among different participants.
Many attacks have shown that it is still possible to infer sensitive information such as membership, property, or outright reconstruction of participant data.
We show that simple linear models can effectively capture client-specific properties only from the aggregated model updates.
arXiv Detail & Related papers (2023-03-07T14:11:01Z) - Scalable Collaborative Learning via Representation Sharing [53.047460465980144]
Federated learning (FL) and Split Learning (SL) are two frameworks that enable collaborative learning while keeping the data private (on device)
In FL, each data holder trains a model locally and releases it to a central server for aggregation.
In SL, the clients must release individual cut-layer activations (smashed data) to the server and wait for its response (during both inference and back propagation).
In this work, we present a novel approach for privacy-preserving machine learning, where the clients collaborate via online knowledge distillation using a contrastive loss.
arXiv Detail & Related papers (2022-11-20T10:49:22Z) - Network-Level Adversaries in Federated Learning [21.222645649379672]
We study the impact of network-level adversaries on training federated learning models.
We show that attackers dropping the network traffic from carefully selected clients can significantly decrease model accuracy on a target population.
We develop a server-side defense which mitigates the impact of our attacks by identifying and up-sampling clients likely to positively contribute towards target accuracy.
arXiv Detail & Related papers (2022-08-27T02:42:04Z) - Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets [53.866927712193416]
We show that an adversary who can poison a training dataset can cause models trained on this dataset to leak private details belonging to other parties.
Our attacks are effective across membership inference, attribute inference, and data extraction.
Our results cast doubts on the relevance of cryptographic privacy guarantees in multiparty protocols for machine learning.
arXiv Detail & Related papers (2022-03-31T18:06:28Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.