Description
Federated Learning (FL) enables the distributed training of a model across multiple data owners under the orchestration of a central server responsible for aggregating the models generated by the different clients. However, the original approach of FL has significant shortcomings related to privacy and fairness requirements. Specifically, the observation of the model updates may lead to privacy issues, such as membership inference attacks, while the use of imbalanced local datasets can introduce or amplify classification biases, especially for minority groups. In this work, we show that these biases can be exploited to increase the likelihood of privacy attacks against these groups. To do so, we propose a novel inference attack exploiting the knowledge of group fairness metrics during the training of the global model. Then to thwart this attack, we define a fairness-aware encrypted-domain aggregation algorithm that is differentially-private by design thanks to the approximate precision loss of the threshold multi-key CKKS homomorphic encryption scheme. Finally, we demonstrate the good performance of our proposal both in terms of fairness and privacy through experiments conducted over three real datasets.
Next sessions
-
Black-Box Collision Attacks on Widely Deployed Perceptual Hash Functions and Their Consequences
Speaker : Diane Leblanc-Albarel - KU Leuven
Perceptual hash functions identify multimedia content by mapping similar inputs to similar outputs. They are widely used for detecting copyright violations and illegal content but lack transparency, as their design details are typically kept secret. Governments are considering extending the application of these functions to Client-Side Scanning (CSS) for end-to-end encrypted services: multimedia[…]-
Cryptography
-
SoSysec
-
-
Malware Detection with AI Systems: bridging the gap between industry and academia
Speaker : Luca Demetrio - University of Genova
With the abundance of programs developed everyday, it is possible to develop next-generation antivirus programs that leverage this vast accumulated knowledge. In practice, these technologies are developed with a mixture of established techniques like pattern matching, and machine learning algorithms, both tailored to achieve high detection rate and low false alarms. While companies state the[…]-
SoSysec
-
Intrusion detection
-
Machine learning
-
-
CHERIoT RTOS: An OS for Fine-Grained Memory-Safe Compartments on Low-Cost Embedded Devices
Speaker : Hugo Lefeuvre - The University of British Columbia
Embedded systems do not benefit from strong memory protection, because they are designed to minimize cost. At the same time, there is increasing pressure to connect embedded devices to the internet, where their vulnerable nature makes them routinely subject to compromise. This fundamental tension leads to the current status-quo where exploitable devices put individuals and critical infrastructure[…]-
SoSysec
-
Compartmentalization
-
Operating system and virtualization
-
Hardware/software co-design
-
Hardware architecture
-