Adapter-based Federated Large Language Models (FedLLMs) are widely adopted to reduce the computational, storage, and communication overhead of full-parameter fine-tuning for web-scale applications while preserving user privacy. By freezing the backbone and training only compact low-rank adapters, these methods appear to limit gradient leakage and thwart existing Gradient Inversion Attacks (GIAs). Contrary to this assumption, we show that low-rank adapters create new, exploitable leakage channels. We propose the Unordered-word-bag-based Text Reconstruction (UTR) attack, a novel GIA tailored to the unique structure of adapter-based FedLLMs. UTR overcomes three core challenges—low-dimensional gradients, frozen backbones, and combinatorially large reconstruction spaces—by: (i) inferring token presence from attention patterns in frozen layers, (ii) performing sentence-level inversion within the low-rank subspace of adapter gradients, and (iii) enforcing semantic coherence through constrained greedy decoding guided by language priors. Extensive experiments across diverse models (GPT2-Large, BERT, Qwen2.5-7B) and datasets (CoLA, SST-2, Rotten Tomatoes) demonstrate that UTR achieves near-perfect reconstruction accuracy (ROUGE-1/2 > 99), even with large batch sizes—settings where prior GIAs fail completely. Our results reveal a fundamental tension between parameter efficiency and privacy in FedLLMs, challenging the prevailing belief that lightweight adaptation inherently enhances security. Our code and data are available at https://github.com/shwksnshwowk-wq/GIA

Streaming graphs widely exist in various application domains due to their excellent capability to capture temporal relationships between different entities. In recent years, outsourcing streaming graphs to the cloud for storage and analytics has become increasingly popular. Among others, pattern detection on streaming graphs, which aims to continuously detect subgraphs matching a given query pattern, benefits practical applications like credit card fraud detection and cyber-attack detection. However, conducting such streaming graph analytics in the cloud also raises critical privacy concerns. This paper introduces GraphGuard, the first system aimed at privacy-preserving pattern detection on outsourced streaming graphs. GraphGuard is designed through a tailored synergy of insights from graph modeling, lightweight secret sharing, edge differential privacy, and data encoding/padding. It conceals edge and vertex labels, as well as the relationship between vertices, for both the outsourced streaming graph and query pattern. We implement GraphGuard and perform comprehensive performance evaluations. The results show that GraphGuard is able to securely perform one detection on a streaming graph's snapshot (with a sliding time window of size 50,000) in just a few seconds. In comparison to a baseline utilizing general secure multiparty computation techniques, GraphGuard is up to 60× faster in query latency and achieves up to 98% savings in communication.

Betweenness centrality is one of the key centrality measures in many applications including community detections in biological networks, vulnerability detections in communication networks, misinformation filtering in social networks, etc. The top-K group betweenness centrality problem is to find a group of K nodes from a network so that the total fraction of shortest paths that pass through the K nodes is maximized. Existing studies proposed randomized sampling algorithms for the problem. We notice that the existing studies ensured that, the maximum deviation of the estimated centrality of every group from its expectation is no greater than a small given threshold for all potential groups with no more than K nodes, thereby generating too many samples, as the number of such groups is prohibitively large. In contrast, in this paper we first devise a novel algorithm that enables to estimate the centrality of a tentative group adaptively, and the algorithm immediately stops once the centrality is large enough; otherwise, the algorithm uses more samples to find a better group. We then theoretically show that, even the proposed algorithm uses much less samples, it still can find a performance-guaranteed group with high probability. Experimental results with real-world networks demonstrate that the number of samples used by the proposed algorithm is up to 36 times smaller than the state-of-the-art, while the centrality of the group found by the algorithm is no more than 4.5% smaller than the latter.

Data valuation quantifies the contribution of each training data, enabling harmful data detection and enhancing model robustness. However, existing methods are typically post-hoc and require fully trained models, making them computationally expensive and unable to detect harmful data early in training. We propose LiveVal, a real-time and trajectory-based data valuation method that assesses training data by analyzing their influence on the optimization trajectory. LiveVal includes three key innovations: 1) a real-time valuation framework with minimal overhead, seamlessly integrated into standard training processes; 2) an adaptive reference point mechanism that assesses data impact on generalization; and 3) a normalization technique that ensures fair comparisons across training stages. Theoretical analysis shows that LiveVal achieves directional alignment, boundedness, stability, and fairness. Experiments demonstrate that LiveVal achieves up to 180× speedup over baseline methods while maintaining robust performance across diverse models and datasets.

Decentralized social graphs, where no single entity possesses the information of the entire graph, and each user maintains only a limited view of the graph, contain great value for different applications. However, simply collecting local views for analytics raises privacy concerns due to the sensitive information of social relationships they capture. To address this, a canonical approach involves privately fitting a generative graph model to the decentralized social graph, generating a differentially private synthetic graph that serves as a proxy for analytics. Existing solutions, however, often fail to capture the inherent directionality of edges and attribute-edge correlations when dealing with decentralized directed social graphs, leading to synthetic graphs with poor utility. To bridge this gap, we present PrivAGM, a new solution that harnesses the synergies among differential privacy, secure multiparty computation, and generative graph models, enabling the secure construction of differentially private directed attributed graph models on decentralized social graphs while ensuring the privacy preservation of individuals. We evaluate PrivAGM on three real-world directed social graph datasets. The results show that PrivAGM outperforms the state-of-the-art methods, generating synthetic graphs with significantly higher utility.

Multimodal deep learning technologies have advanced significantly, which brings extensive applications in diverse fields. The substantial computational demands of training and prediction in multimodal deep learning have made the End-Edge-Cloud (EEC) framework popular. It is essential to protect multimodal data and model privacy in such a framework. However, traditional cryptographic methods, though secure for data and models at edge nodes, cause efficiency limitations. In this paper, we propose SecMdp, an SGX-assisted secure computational framework for multimodal data in the EEC architecture. Edge nodes are equipped with the trusted execution environment (e.g., Intel SGX) to run multimodal algorithms. Additionally, to address the side-channel attacks of SGX, we present an enhanced PathORAM algorithm, MM_PathORAM, for the multimodal training and prediction processes, which are tailored for multimodal deep learning scenarios. It accelerates multimodal data access while protecting data privacy and model security. Experimental evaluation supports the effectiveness of our design in preserving edge computing efficiency. It demonstrates negligible impact on the speed of multimodal data loading, the configuration of model parameters during training, or the accuracy of predictions.

Federated learning has emerged as a promising paradigm for large-scale collaborative training tasks, harnessing diverse local datasets from different clients to jointly train global models. In real-world implementations, client data could have label noise, causing the quality of the global model to be influenced. Existing label-correction solutions assume all the clients are discreet and fail to consider detecting the malicious clients, thus are not practical or privacy-preserving. In this paper, we present zkCor, an efficient and reliable label noise correction scheme with zero-knowledge confidentiality. Our method is designed upon FedCorr [1], but with more relaxed security assumptions. zkCor is established from the ingenious synergy of the label noise correction protocol and the zero-knowledge proof (ZKP), requiring each client to provide a computation integrity proof to the aggregator in each iteration. Thus, clients are forced to jointly guarantee label-correction reliability. We further devise a batch ZKP that is efficient and more suitable for federated learning settings. We rigorously illustrate the building blocks of zkCor and complete the prototype implementation. The extensive experiments demonstrate that zkCor can gain at least 2 to 30 times better performance than the baseline approach on verification workloads with nearly no extra proof time cost from clients.

Decentralized storage platforms based on consortium blockchains have emerged in the spotlight of research and industry communities because they are flexible, transparent, and eliminated trust in contrast to the traditional centralized data-sharing model. However, due to wide attacking surfaces in a blockchain network, this decentralized data-sharing paradigm is subject to malicious data breaches. Untrusted blockchain nodes can directly obtain sensitive information from the query processing and their local storage. Several studies have been made for solving this dilemma, but they only focus on single-user settings and cannot be directly applied to multi-owners blockchain-based data sharing scenarios. In this paper, we introduce FedEDB, a federated and encrypted data store by using consortium blockchains. Unlike existing solutions that focus on single-user settings, our proposed schemes can efficiently support privacy-preserving and reliable multi-owner queries in the decentralized setting. We start from the practical key aggregation technique to construct the multi-owner search schemes and further refine the underling building blocks to enhance the security. Besides, we integrate the smart contract with our tailored zero-knowledge proof to enforce secure and reliable result verification protocol with fairness. We implement a prototype and thorough security analysis and comprehensive evaluation results confirm the practicability of our design.

Graphs are widely used to model complex structured data in many applications. With the proliferation of cloud computing, it is popular to store and query graphs in the cloud. Among others, graph similarity search, which aims to retrieve from a graph database graphs similar to a query graph, has received wide attentions and benefited various domains such as cheminformatics, computer vision, and more. Deploying graph similarity search services on the cloud, however, raises critical privacy concerns on the information-rich graphs. In this article, we initiate the first study on privacy-preserving graph similarity search in cloud computing. We design, implement, and evaluate PrigSim, a novel system allowing the cloud to host an outsourced encrypted graph database and support secure graph similarity search, where the graph similarity is measured by the well-known metric called graph edit distance. PrigSim is built from a customized and delicate synergy of insights on graph modelling, lightweight cryptography, and data encoding and padding, providing protections for the confidentiality of data content associated with graphs, as well as hiding the connections among vertices. Extensive experiments demonstrate that the security design of PrigSim is accuracy-preserving, and presents modest performance overheads (with$9\times$-$15\times$higher query latency than the plaintext baseline).

Analytics over social graphs allows to extract valuable knowledge and insights for many fields like community detection, fraud detection, and interest mining. In practice, decentralized social graphs frequently arise, where the social graph is not available to a single entity and is decentralized among a large number of users, each holding only a limited local view about the whole graph. Collecting the local views for analytics of decentralized social graphs raises critical privacy concerns, as they encode private information about the social interactions among individuals. In this paper, we design, implement, and evaluate PrivGED, a new system aimed at privacy-preserving analytics over decentralized social graphs. PrivGED focuses on the support for eigendecomposition, one popular and fundamental graph analytics task producing eigenvalues/eigenvectors over the adjacency matrix of a social graph and benefits various practical applications. PrivGED is built from a delicate synergy of insights on graph analytics, lightweight cryptography, and differential privacy, allowing users to securely contribute their local views on a decentralized social graph for a cloud-based eigendecomposition analytics service while gaining strong privacy protection. Extensive experiments over real-world social graph datasets demonstrate that PrivGED achieves accuracy comparable to the plaintext domain, with practically affordable performance superior to prior art.

The well-known benefits of cloud computing have spurred the popularity of database service outsourcing, where one can resort to the cloud to conveniently store and query databases. Coming with such popular trend is the threat to data privacy, as the cloud gains access to the databases and queries which may contain sensitive information, like medical or financial data. A large body of work has been presented for querying encrypted databases, which has been mostly focused on secure keyword search. In this paper, we instead focus on the support for secure skyline query processing over encrypted outsourced databases, where little work has been done. Skyline query is an advanced kind of database query which is important for multi-criteria decision-making systems and applications. We propose SecSkyline, a new system framework building on lightweight cryptography for fast privacy-preserving skyline queries. SecSkyline ambitiously provides strong protection for not only the content confidentiality of the outsourced database, the query, and the result, but also for data patterns that may incur indirect data leakages, such as dominance relationships among data points and search access patterns. Extensive experiments demonstrate that SecSkyline is substantially superior to the state-of-the-art in query latency, with up to$813\times$improvement.

Investigates the issues of placing a limited number of Web proxies in an environment where the Web server is replicated (i.e. mirrored Web servers). Two different objectives are considered: (a) minimizing the overall access cost by all clients of the Web server, and (b) minimizing the longest delay for any client to access the Web server. The problems are formulated and solved by using a dynamic programming method. This work can: (1) alleviate the amount of Internet traffic incurred by fast-growing Web accesses; (2) improve the response time of Web server accesses; and (3) maximize Web server performance by using a limited number of proxies.

In order to support the interaction betweeen coexisting traditional short transactions and long cooperative transactions, we propose a novel timestamp ordering approach. With this timestamp ordering method, short transactions can be processed in the traditional way, as if there were no cooperative transactions. Therefore they will not be blocked by cooperative transactions. Cooperative transactions will not be aborted when there is a conflict with short transactions. Rather, they will incorporate the recent updates into their own processing. The serializabilities, among short transactions, and between a cooperative transaction (group) and other short transactions, are all preserved.