This paper presents a holistic approach to gradient leakage resilient distributed Stochastic Gradient Descent (SGD). First , we analyze two types of strategies for privacy-enhanced federated learning: (i) gradient pruning with random selection or low-rank filtering and (ii) gradient perturbation with additive random noise or differential privacy noise. We analyze the inherent limitations of these approaches and their underlying impact on privacy guarantee, model accuracy, and attack resilience. Next , we present a gradient leakage resilient approach to securing distributed SGD in federated learning, with differential privacy controlled noise as the tool. Unlike conventional methods with the per-client federated noise injection and fixed noise parameter strategy, our approach keeps track of the trend of per-example gradient updates. It makes adaptive noise injection closely aligned throughout the federated model training. Finally , we provide an empirical privacy analysis on the privacy guarantee, model utility, and attack resilience of the proposed approach. Extensive evaluation using five benchmark datasets demonstrates that our gradient leakage resilient approach can outperform the state-of-the-art methods with competitive accuracy performance, strong differential privacy guarantee, and high resilience against gradient leakage attacks.

Local Differential Privacy (LDP) is a popular standard for privacy-preserving data collection. Numerous LDP protocols have been proposed in the literature which differ in how they provide higher utility in different settings. Yet, few have engaged in analyzing the privacy relationships of these protocols under varying settings, and consequently, it is non-trivial to select which LDP protocol is best to use in a newly emerging application. In this paper, we present an adversarial approach to protocol analysis and selection and make three original contributions. First, we introduce a Bayesian adversary to analyze the privacy relationships of LDP protocols under varying settings. We show that different protocols have substantially different responses to the attack effectiveness of the Bayesian adversary, measured in terms of Adversarial Success Rate (ASR). Second, we provide a formal and empirical analysis on a set of privacy and utility-critical factors, including encoding parameters, privacy budget, data domain, adversarial knowledge, and statistical distribution. We show that different settings of these factors have significant effects on the ASRs of LDP protocols, and no protocol provides consistently low ASR across all settings. Third, we design and develop LDPLens, a prototype implementation of our proposed framework. Given a data collection scenario with various factors and constraints, LDPLens enables optimized selection of a desirable LDP protocol for the given scenario. We evaluate the effectiveness of LDPLens using three case studies with real-world datasets. Results show that LDPLens recommends a different protocol in each case study, and the protocol recommended by LDPLens can yield up to 1.5–2 fold reduction in utility loss, ASR or privacy budget compared to a randomly selected protocol.

Language models (LMs) have demonstrated superior performance in detecting fraudulent activities on Blockchains. Nonetheless, the sheer volume of Blockchain data results in excessive memory and computational costs when training LMs from scratch, limiting their capabilities to large-scale applications. In this paper, we present ZipZap, a framework tailored to achieve both parameter and computational efficiency when training LMs on large-scale transaction data. First, with the frequency-aware compression, an LM can be compressed down to a mere 7.5% of its initial size with an imperceptible performance dip. This technique correlates the embedding dimension of an address with its occurrence frequency in the dataset, motivated by the observation that embeddings of low-frequency addresses are insufficiently trained and thus negating the need for a uniformly large dimension for knowledge representation. Second, ZipZap accelerates the speed through the asymmetric training paradigm: It performs transaction dropping and cross-layer parameter-sharing to expedite the pre-training process, while revert to the standard training paradigm for fine-tuning to strike a balance between efficiency and efficacy, motivated by the observation that the optimization goals of pre-training and fine-tuning are inconsistent. Evaluations on real-world, large-scale datasets demonstrate that ZipZap delivers notable parameter and computational efficiency improvements for training LMs. Our implementation is available at: https://github.com/git-disl/ZipZap.

Locality classification is an important component to enable location-based services. It entails two sequential queries: 1)whether a target is within the site or not, i.e., inside/outside region decision, and 2)if so, which area in the region the target is located, i.e., area classification. Locality classification is hence more coarse-grained and efficient as compared with pinpointing the exact target location in the region. The classification problem is challenging, because fingerprints may not exist outside the region for training. Furthermore, the target may sample an incomplete RSSI vector due to, say, random signal noise, momentary occulsion or scanning duration. The algorithm also has to be computationally efficient.

In fingerprint-based indoor localization, fusing radio frequency (RF) and geomagnetic signals has been shown to achieve promising results. To efficiently collect fingerprints, implicit crowdsourcing can be used, where signals sampled by pedestrians are automatically labeled with their locations on a map. Previous work on crowdsourced fingerprinting is often based on a single signal, which is susceptible to signal bias and labeling error. We study, for the first time, implicit multimodal crowdsourcing for joint RF and geomagnetic fingerprinting. The scheme, termed UbiFin, exploits the spatial correlation among RF, geomagnetic, and motion signals to mitigate the impact of sensor noise, leading to highly accurate and robust fingerprinting without the need for any explicit manual intervention. Using clustering and dynamic programming, UbiFin correlates spatially different signals and filters effectively mislabeled signals. We conduct extensive experiments on our campus and a large multi-story shopping mall. Efficient and simple to implement, UbiFin outperforms other state-of-the-art crowdsourcing schemes to construct RF and geomagnetic fingerprints in terms of accuracy and robustness (cutting fingerprint error by 40 percent in general).