RESUMEN
Graph neural networks (GNN) are widely used in recommendation systems, but traditional centralized methods raise privacy concerns. To address this, we introduce a federated framework for privacy-preserving GNN-based recommendations. This framework allows distributed training of GNN models using local user data. Each client trains a GNN using its own user-item graph and uploads gradients to a central server for aggregation. To overcome limited data, we propose expanding local graphs using Software Guard Extension (SGX) and Local Differential Privacy (LDP). SGX computes node intersections for subgraph exchange and expansion, while local differential privacy ensures privacy. Additionally, we introduce a personalized approach with Prototype Networks (PN) and Model-Agnostic Meta-Learning (MAML) to handle data heterogeneity. This enhances the encoding abilities of the federated meta-learner, enabling precise fine-tuning and quick adaptation to diverse client graph data. We leverage SGX and local differential privacy for secure parameter sharing and defense against malicious servers. Comprehensive experiments across six datasets demonstrate our method's superiority over centralized GNN-based recommendations, while preserving user privacy.
RESUMEN
Fine-grained hashing is a new topic in the field of hashing-based retrieval and has not been well explored up to now. In this paper, we raise three key issues that fine-grained hashing should address simultaneously, i.e., fine-grained feature extraction, feature refinement as well as a well-designed loss function. In order to address these issues, we propose a novel Fine-graIned haSHing method with a double-filtering mechanism and a proxy-based loss function, FISH for short. Specifically, the double-filtering mechanism consists of two modules, i.e., Space Filtering module and Feature Filtering module, which address the fine-grained feature extraction and feature refinement issues, respectively. Thereinto, the Space Filtering module is designed to highlight the critical regions in images and help the model to capture more subtle and discriminative details; the Feature Filtering module is the key of FISH and aims to further refine extracted features by supervised re- weighting and enhancing. Moreover, the proxy-based loss is adopted to train the model by preserving similarity relationships between data instances and proxy-vectors of each class rather than other data instances, further making FISH much efficient and effective. Experimental results demonstrate that FISH achieves much better retrieval performance compared with state-of-the-art fine-grained hashing methods, and converges very fast. The source code is publicly available: https://github.com/chenzhenduo/FISH.
RESUMEN
The publish/subscribe model has gained prominence in the Internet of things (IoT) network, and both Message Queue Telemetry Transport (MQTT) and Constrained Application Protocol (CoAP) support it. However, existing coverage-based fuzzers may miss some paths when fuzzing such publish/subscribe protocols, because they implicitly assume that there are only two parties in a protocol, which is not true now since there are three parties, i.e., the publisher, the subscriber and the broker. In this paper, we propose MultiFuzz, a new coverage-based multiparty-protocol fuzzer. First, it embeds multiple-connection information in a single input. Second, it uses a message mutation algorithm to stimulate protocol state transitions, without the need of protocol specifications. Third, it uses a new desockmulti module to feed the network messages into the program under test. desockmulti is similar to desock (Preeny), a tool widely used by the community, but it is specially designed for fuzzing and is 10x faster. We implement MultiFuzz based on AFL, and use it to fuzz two popular projects Eclipse Mosquitto and libCoAP. We reported discovered problems to the projects. In addition, we compare MultiFuzz with AFL and two state-of-the-art fuzzers, MOPT and AFLNET, and find it discovering more paths and crashes.