Signed graphs with positive and negative edges can model complex relationships in social networks. Leveraging on balance theory that deduces edge signs from multi-hop node pairs, signed graph learning can generate node embeddings that preserve both structural and sign information. However, training on sensitive signed graphs raises significant privacy concerns, as model parameters may leak private link information. Existing methods with differential privacy (DP) typically rely on edge or gradient perturbation for protecting unsigned graphs. Yet, they are not well-suited for signed graphs: edge perturbation may trigger cascading errors in edge sign inference under balance theory, while gradient perturbation necessitates substantial noise injection due to increased gradient sensitivity arising from node interdependence and gradient polarity change caused by sign flips. In this paper, motivated by the robustness of adversarial learning to noisy interactions, we present ASGL, a privacy-preserving adversarial signed graph learning method that preserves high utility while achieving node-level DP. We first decompose signed graphs into positive and negative subgraphs based on edge signs, and then design a gradient-perturbed adversarial module to approximate the true signed connectivity distribution. In particular, the gradient perturbation helps mitigate cascading errors, while the subgraph separation facilitates sensitivity reduction. Further, we devise a constrained breadth-first search tree strategy that fuses with balance theory to identify the edge signs between generated node pairs. This strategy also enables gradient decoupling, thereby effectively lowering gradient sensitivity. Extensive experiments on real-world datasets show that ASGL achieves favorable privacy-utility trade-offs across multiple downstream tasks.

Influence Maximization (IM), aiming to identify a small set of highly influential nodes in social networks, is a critical problem in graph analysis. Recently, Graph Neural Networks (GNNs) have demonstrated superior effectiveness in addressing IM. However, a trained GNN still raises significant privacy concerns, as it may expose sensitive node features and structural information. While Differential Privacy (DP) techniques have been widely applied to GNNs for node-level tasks, they cannot be directly extended to 1M problems. This is because IM requires more complex structural information for training, resulting in an extremely larger DP noise scale than node-level tasks. To tackle these issues, we propose PrivIM, a novel differentially private subgraph-based GNNs framework for IM tasks, which ensures node-level DP guarantees. Within PrivIM, we design a unique dual-stage adaptive frequency sampling scheme to optimize the model utility. First, it reduces the correlation between nodes by dynamically adjusting each node's sampling probability. Then additional subgraphs are incorporated to supplement boundary structural information, enhancing utility without increasing privacy budget. Extensive experiments on six real-world datasets demonstrate that PrivIM maintains high utility in IM compared to baseline methods.

Graph Neural Networks (GNNs) have proven to be highly effective in addressing the link prediction problem. However, the need for large amounts of user data to learn representations of user interactions raises concerns about data privacy. While differential privacy (DP) techniques have been widely used for node-level tasks in graphs, incorporating DP into GNNs for link prediction is challenging due to data dependency. To this end, in this work we propose a differentially private link prediction (DPLP) framework, building upon subgraph-based GNNs. DPLP includes a DP-compliant subgraph extraction module as its core component. We first propose a neighborhood subgraph extraction method, and carefully analyze its data dependency level. To reduce this dependency, we optimize DPLP by integrating a novel path subgraph extraction method, which alleviates the utility loss in GNNs by reducing the noise sensitivity. Theoretical analysis demonstrates that our approaches achieve a good balance between privacy protection and prediction accuracy, even when using GNNs with few layers. We extensively evaluate our approaches on benchmark datasets and show that they can learn accurate privacy-preserving GNNs and outperforms the existing methods for link prediction.

Machine learning models are known to memorize private data to reduce their training loss, which can be inadvertently exploited by privacy attacks such as model inversion and membership inference. To protect against these attacks, differential privacy (DP) has become the de facto standard for privacy-preserving machine learning, particularly those popular training algorithms using stochastic gradient descent, such as DPSGD. Nonetheless, DPSGD still suffers from severe utility loss due to its slow convergence. This is partially caused by the random sampling, which brings bias and variance to the gradient, and partially by the Gaussian noise, which leads to fluctuation of gradient updates. Our key idea to address these issues is to apply selective updates to the model training, while discarding those useless or even harmful updates. Motivated by this, this paper proposes DPSUR, a Differentially Private training framework based on Selective Updates and Release, where the gradient from each iteration is evaluated based on a validation test, and only those updates leading to convergence are applied to the model. As such, DPSUR ensures the training in the right direction and thus can achieve faster convergence than DPSGD. The main challenges lie in two aspects --- privacy concerns arising from gradient evaluation, and gradient selection strategy for model update. To address the challenges, DPSUR introduces a clipping strategy for update randomization and a threshold mechanism for gradient selection. Experiments conducted on MNIST, FMNIST, CIFAR-10, and IMDB datasets show that DPSUR significantly outperforms previous works in terms of convergence speed and model utility.

Most previous studies on matrix factorization (MF)-based collaborative filtering (CF) have focused solely on user rating information for predicting recommendations. However, to further enhance the performance of recommender systems (RSs), it is important to also consider review information and rating reliability in the model. This article proposes a new probabilistic MF (PMF)-based CF method that integrates multiple information sources to provide reliable predictions. First, we introduce a sentiment-based PMF to handle user reviews and fit the normalized sentiment information obtained from our previously proposed sentiment analysis method. We also consider the helpfulness of reviews to highlight their reliability and effectiveness in this model. Subsequently, our proposed noise detection method is adopted to determine the reliability of user ratings, and then the rating matrix is transformed into a binary reliability matrix. A rating reliability-based PMF through Bernoulli distribution is then proposed to factorize it. To effectively integrate three types of information (ratings, reviews, and rating reliability) into a PMF procedure, we design a weight matrix using the proposed weighting strategy to generate a set of comprehensive prediction ratings with corresponding reliability probabilities. Experiments on four Amazon datasets demonstrate that our model outperforms comparison methods in terms of comprehensive evaluation.