This work applies differential privacy (which adds noise to the model weights before sending across the network) as an added privacy measure to protect sensitive data from being reconstructed in Federated Learning.
Today's digital age has made privacy and data protection a major concern-generally, with the kind of technologies that are turning things around and bringing everything to the cloud. FL will most likely provide a solution to the distance and make things clear in collaboration without exposing raw information from a consortium to boost its privacy. However, existing FL solutions include such challenges as increased overhead communication, risk in leaking data, and even the inefficiency of secure aggregation.To mitigate these constraints, this research proposes the Autoencoder-Based Federated Learning framework by integrating prevailing techniques such as differential privacy and homomorphic encryption that safeguard both the security and efficiency of the model. This method does not only steal model ideas for autoencoders to compress before sciences transmission but hugely reduces the transmission bandwidth and possibly minimizes gradient leakage. However, adaptive normalization is used to handle institutional heterogeneity to maintain better performance for the model. Conclusion of experimentation indicated that this framework could significantly reduce communication overhead while retaining high federated learning accuracy and even better security. Further, the trust-based client evaluation mechanism is presented to detect malicious behavior and improve reliability regarding federated aggregation. The experiment showed that Autoencoder Based Federated Learning was a scalable, secure, and privacy-efficient solution to applications tailored for healthcare, finance, and other sensitive data environments.
Guman Singh Chauhan, venkata Surya Teja Gollapalli, Kannan Srinivasan et al.· Journal of Science & Technol...· 0 citations
An improved defense mechanism that combines adversarial training and differential-privacy-style noise injection to collectively enhance the robustness of the existing KDk defense mechanism with marginal model utility trade-off is introduced.
N. Azeez, Oluwatobi Sunday Malomo, Omotolani Mary Okerinde et al.· Informatics· 0 citations
Federated Learning (FL) enables collaborative model training without centralizing client data, making it well-suited for privacy-sensitive domains. Existing approaches use techniques such as homomorphic encryption, differential privacy, and secure multi-party computation to mitigate attacks including model inversion, membership inference, and gradient leakage. However, these methods often incur high computational and memory overheads and frequently overlook confidentiality of the global model itself, which may be proprietary and sensitive. These limitations reduce the practicality of secure FL in large-scale and compliance-sensitive environments.We present NETFL, a Fully Secure and scalable FL framework that decentralizes training across client pairs using lightweight MPC, while restricting servers to secure aggregation, client pairing, and routing. NETFL eliminates server-side bottlenecks, avoids full data offloading, and preserves confidentiality of data, model parameters, and updates throughout training. Our evaluation shows that NETFL protects against unauthorized observation, reconstruction, gradient leakage, membership inference, and inversion attacks, while achieving up to 13× faster training time and 50% lower server memory usage compared to prior work.
Sahar Ghoflsaz Ghinani, Elaheh Sadredini· International Conference on...· 0 citations
As vehicular networks move toward 5G/6G edge intelligence, federated learning (FL) is widely promoted as a privacy-preserving way for vehicles and infrastructure to train shared models without exposing raw sensor data. Yet the updates clients transmit still leak enough information to identify who sent them, which threatens the anonymity that safety-critical V2X applications assume and adds to existing concerns over adversarial ML, model poisoning, and backdoor attacks. We study server-side client identity inference from transmitted weight deltas using inertial (IMU) measurements, evaluated on the UCI Human Activity Recognition (HAR) benchmark as an accessible proxy for the IMU streams produced onboard connected vehicles. Across five attack classifiers and five non-IID partitions, an honest-but-curious server recovers client identity with near-perfect accuracy (approximately 1.000) from undefended updates, confirming a concrete identifiability risk. We then quantify the privacy-utility trade-off of a lightweight clip-then-noise defense by sweeping Gaussian noise (sigma in {0.00, 0.05, 0.10, 0.20, 0.50, 1.00}) at fixed clipping (C=1.0), and report formal (epsilon, delta)-DP budgets through Renyi accounting. A practical region (sigma in [0.1, 0.2]) drives attack accuracy to near-random while costing under 5% relative FL accuracy. Ensemble FL supplies complementary structural privacy with a 1/K anonymity-set bound and no noise penalty. Results are supported by cryptographic (SHA-256) train/evaluation gradient disjointness, three seeds, and a count-normalized attacker-advantage metric. We position HAR explicitly as a proxy and discuss what validation on true vehicular telemetry would require.
Ali Akarma, Toqeer Ali Syed, Muhammad Khan et al.· 0 citations
Federated learning is a technology that is used to protect data privacy in machine learning. Nonetheless, in federated learning, updating the global model requires the use of gradient descent algorithm, which involves multiple rounds of interaction between entities to complete the iterative updates, inevitably incurring massive computational and communication overhead. In 2020, Wang et al. first proposed a non-interactive federated regression scheme, which effectively improves the training efficiency of regression models while protecting the privacy of local training data. However, like most current federated regressions, it involves a third authority (TA) to generate keys for each entity, which poses a significant privacy risk and results in considerable communication overhead. From the view of security and practicality, this paper first proposes a multi-party homomorphic encryption algorithm named MPaillier. Furthermore, we have designed PNFR, a privacy-preserving federated learning scheme for regressions training built on the MPaillier algorithm. The participating entities of PNFR are the data owners and a cloud server, eliminating the need for a TA, thus enhancing the practicality and efficiency of the scheme. Experimental results demonstrate that our scheme is $\sim 10^{3}$ times faster than interactive federated regressions PrivFL and about 80% faster than non-interactive federated regressions VANE.
This paper proposes a comprehensive framework for privacy-preserving feature engineering (PPFE) within federated learning analytics and explores techniques such as homomorphic encryption, differential privacy, and secure multi-party computation to enable robust, privacy-safe feature selection, transformation, and extraction across clients.
Yuki Nakamura, Olivia Martin· International Journal of Dat...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
