Recent generative unlearning models synthesize high quality samples while protecting private information by unlearning the identity. However, existing generative identity unlearning methods face two challenges in multi-identity unlearning: 1) identity conflicts, which cause conflicts of model parameters in the continuous erasure of multiple identities; 2) fragile unlearning, where the model's unlearning ability deteriorates or fails under malicious attacks. In this paper, we introduce a critical yet under-explored task called robust multi-identity unlearning, with the goals of resolving identity conflicts to achieve interference-free unlearning and protecting against malicious attacks to achieve robust unlearning. To satisfy these goals, we propose a novel framework, RObust generatiVE continual identity unlearning against Relearning attacks (ROVER). By filtering unlearning requests with latent similarity, our method effectively isolates benign unlearning from malicious attacks to preserve identity removal integrity. Meanwhile, residual orthogonal resonator resolves identity conflicts in the continuous erasure of multiple identities, preserving stability in benign continual unlearning. Moreover, we introduce the phantom guard network to block malicious attacks by absorbing adversarial gradients, ensuring irreversible identity unlearning. The extensive experiments demonstrate that our proposed method achieves state-of-the-art performance on the task of robust multi-identity unlearning against relearning attacks.

Dynamic novel view synthesis (NVS) aims to render time-varying scenes from arbitrary viewpoints, balancing rendering quality and computational efficiency. While recent 4D Gaussian Splatting approaches offer promising real-time performance, they fundamentally overlook critical interdependence between Gaussians by modeling deformations independently. Our information-theoretic analysis reveals substantial mutual information across the Gaussian field, manifesting as appearance-preserving radiance coherence and motion-consistent deformation propagation. This finding establishes that rendering quality emerges from coordinated transformation rather than independent processing. We propose Correlation-aware Dynamic Gaussian Splatting (CaDGS) with our novel Gaussian Correlation Tensor Projection (GCTP) method, which efficiently transforms the complex O(n3) mutual information tensor into a dual-channel O(n2) spatial matrix, preserving the critical topological structure of Gaussian interactions. Combined with our Spatio-Temporal Deformation Consistency (STDC) learning, which enforces volumetric coherence through tensor-guided regularization across multiple scales, CaDGS prevents geometric distortions and texture inconsistencies common in previous approaches. Experimental results demonstrate state-of-the-art performance, achieving 32.4 PSNR on the Neu3D dataset with fewer Gaussians while maintaining rendering speeds of 323 FPS at 1353 × 1014 resolution.

With the ever-growing attention on communication security, machine learning-based network intrusion detection system (NIDS) is widely utilized to meet different security requirements. However, most of the existing methods manually extract or learn features from raw traffic, which is usually expensive, complicated, and time-consuming. Moreover, this also brings unprecedented challenges for preserving users’ privacy in the communication process, making it difficult for existing solutions to be deployed in practice due to the privacy requirements from legal policies. This paper proposes a privacy-preserving graph neural network (named NIGNN) for NIDS, which can encode the local structure and traffic features. To address the privacy issues pertaining to the application of graph representation learning, we design a privacy message-passing mechanism with formal privacy guarantees, in which sensitive information potentially contained in graph vertices will be kept private. Specifically, we design a privacy-enhancement graph representation that introduces a degree-sensitive item in vertex-based aggregation to reduce noise. Our theoretical analysis shows that NIGNN can provide a provable privacy guarantee. Extensive experiments demonstrate NIGNN's performance in maintaining a sound privacy-accuracy trade-off.

Model stealing (MS) involves querying and observing the output of a machine learning model to steal its capabilities. The quality of queried data is crucial, yet obtaining a large amount of real data for MS is often challenging. Recent works have reduced reliance on real data by using generative models. However, when high-dimensional query data is required, these methods are impractical due to the high costs of querying and the risk of model collapse. In this work, we propose using sample gradients (SG) to enhance the utility of each real sample, as SG provides crucial guidance on the decision boundaries of the victim model. However, utilizing SG in the model stealing scenario faces two challenges: 1. Pixel-level gradient estimation requires ex-tensive query volume and is susceptible to defenses. 2. The estimation of sample gradients has a significant variance. This paper proposes Superpixel Sample Gradient stealing (SPSG) for model stealing under the constraint of limited real samples. With the basic idea of imitating the victim model's low-variance patch-level gradients instead ofpixel-level gradients, SPSG achieves efficient sample gradient es-timation through two steps. First, we perform patch-wise perturbations on query images to estimate the average gradient in different regions of the image. Then, we filter the gradients through a threshold strategy to reduce variance. Exhaustive experiments demonstrate that, with the same number of real samples, SPSG achieves accuracy, agreements, and adversarial success rate significantly surpassing the current state-of-the-art MS methods. Codes are available at https://github.com/zyI123456aBISPSG_attack.

Neural Networks’ performance on a sequence of incremental class tasks drops over time for Class Incremental Learning (IL). The gradient-based IL methods can simultaneously adapt to both new and previous tasks by promoting the update of model in the correct direction. However, existing methods simply consider the previous/new task gradients separately. In this paper, we propose Parallel Gradient Blend (PGB) paradigm. On the one hand, PGB uses the gradients generated by mixing previous and new samples in equal proportions with Batch-Normal layers to adjust a reasonable model update direction. By comparing gradient similarities, the model selects either the previous task gradient or mixed gradient to update. On the other hand, PGB uses the sample feature gradient distribution difference to construct a regularized gradient. Finally, we experimentally demonstrate that PGB outperforms state-of-the-art methods on class-IL benchmarks.