Deep learning models represent valuable intellectual property due to their high development costs. To protect model ownership, existing fingerprinting techniques have been proposed to use adversarial examples to fingerprint a model's decision boundaries. However, these fingerprints are inherently fragile, as model decision boundaries are highly sensitive to common model modifications such as fine-tuning, pruning, and adversarial training. In this paper, we propose MFUE (Model Fingerprinting via Unlearnable Examples), a novel fingerprinting methodology that leverages the stable unlearnability of unlearnable examples to fingerprint arbitrary modified models in parameter space, fundamentally circumventing the inherent vulnerability of decision boundaries. To achieve robust model fingerprinting in parameter space, we are the first to identify that unlearnable examples, owing to their persistent training resistance, can serve as stable fingerprints beyond the model's decision boundaries. To endow unlearnable examples with robustness against arbitrary model modifications, we introduce adversarial training that simulates the randomness of model modifications by jointly optimizing the unlearnable examples over models at different training stages. We evaluate the performance of MFUE against six different attack types, including both model and input tampering. Through extensive experiments, we demonstrate that MFUE outperforms four existing methods in terms of robustness and uniqueness.

Abstract Creating ultra‐high‐resolution spatially varying bidirectional reflectance functions (SVBRDFs) is critical for photorealistic 3D content creation, to faithfully represent fine‐scale surface details required for close‐up rendering. However, achieving 4K generation faces two key challenges: (1) the need to synthesize multiple reflectance maps at full resolution, which multiplies the pixel budget and imposes prohibitive memory and computational cost, and (2) the requirement to maintain strong pixellevel alignment across maps at 4K, which is particularly difficult when adapting pretrained models designed for the RGB image domain. We introduce HiMat, a diffusion‐based framework tailored for efficient and diverse 4K SVBRDF generation. To address the first challenge, HiMat generates in a high‐compression latent space via a DC‐AE and employs a pretrained diffusion transformer with linear attention to improve per‐map efficiency. To address the second challenge, we propose CrossStitch, a lightweight convolutional module that enforces cross‐map consistency without incurring the cost of global attention. Our experiments show that HiMat achieves high‐fidelity 4K SVBRDF generation with superior efficiency, structural consistency, and diversity compared to prior methods. Beyond materials, our framework also generalizes to related applications such as intrinsic decomposition.

The rapid advancements and widespread application of deep neural networks (DNNs), coupled with their reliance on sensitive and private data, have sparked growing concerns regarding data privacy and the ''right to be forgotten''. To address these concerns, machine unlearning has been proposed to efficiently eliminate the influence of specific training data from trained DNNs. However, existing machine unlearning methods struggle with the large number of parameters in trained DNNs, which lead to slow execution and high memory consumption, making them impractical for large-scale models. In this paper, we shift our focus to the small set of weights in the final classification layer of DNNs, which are defined as as ''prototypes'' for different classes. Our key observation is that the prototype associated with the unlearned training data undergoes a significant shift, whereas prototypes of unrelated classes exhibit only minor changes when comparing the prototypes of original and retrained models. Based on this observation, we propose a novel machine unlearning approach that efficiently achieves machine unlearning by directly adjusting the prototypes of DNNs. We first introduce Naive Prototype Surgery (Naive PS), a fast and simplified method that uses a closed-form solution to approximate unlearning effect by directly adjusting the prototype associated with the unlearned data. Next, we propose Prototype Surgery (PS), which incorporates soft label information to fine-tune the prototypes of all classes, to achieve a more effective unlearning. Both methods achieve data unlearning by only modifying the prototypes in the DNNs, thus avoiding the challenges posed by the large number of model parameters. Extensive experiments on four datasets demonstrate that our methods significantly accelerate the unlearning process while achieving comparable results to five existing methods in terms of both unlearning performance and privacy guarantee.

Given the rapid advancements in geometric deep-learning techniques, there has been a dedicated effort to create mesh-based convolutional operators that act as a link between irregular mesh structures and widely adopted backbone networks . Despite the numerous advantages of Convolutional Neural Networks (CNNs) over Multi-Layer Perceptrons (MLPs), mesh-oriented CNNs often require intricate network architectures to tackle irregularities of a triangular mesh. These architectures not only demand that the mesh be manifold and watertight but also impose constraints on the abundance of training samples . In this paper, we note that for specific tasks such as mesh classification and semantic part segmentation, large-scale shape features play a pivotal role . This is in contrast to the realm of shape correspondence, where a comprehensive understanding of 3D shapes necessitates considering both local and global characteristics. Inspired by this key observation, we introduce a task-driven neural network architecture that seamlessly operates in an end-to-end fashion. Our method takes as input mesh vertices equipped with the heat kernel signature (HKS) and dihedral angles between adjacent faces . Notably, we replace the conventional convolutional module, commonly found in ResNet architectures, with MLPs and incorporate Layer Normalization (LN) to facilitate layer-wise normalization. Our approach, with a seemingly straightforward network architecture, demonstrates an accuracy advantage. It exhibits a marginal 0.1% improvement in the mesh classification task and a substantial 1.8% enhancement in the mesh part segmentation task compared to state-of-the-art methodologies. Moreover, as the number of training samples decreases to 1/50 or even 1/100, the accuracy advantage of our approach becomes more pronounced. In summary, our convolution-free network is tailored for specific tasks relying on large-scale shape features and excels in the situation with a limited number of training samples, setting itself apart from state-of-the-art methodologies.

Machine Learning (ML) techniques have been applied to many real-world applications to perform a wide range of tasks. In practice, ML models are typically deployed as the black-box APIs to protect the model owner’s benefits and/or defend against various privacy attacks. In this paper, we present Gradient-Leaks as the first evidence showcasing the possibility of performing membership inference attacks (MIAs), with mere black-box access, which aim to determine whether a data record was utilized to train a given target ML model or not. The key idea of Gradient-Leaks is to construct a local ML model around the given record which locally approximates the target model’s prediction behavior. By extracting the membership information of the given record from the gradient of the substituted local model using an intentionally modified autoencoder, Gradient-Leaks can thus breach the membership privacy of the target model’s training data in an unsupervised manner, without any priori knowledge about the target model’s internals or its training data. Extensive experiments on different types of ML models with real-world datasets have shown that Gradient-Leaks can achieve a better performance compared with state-of-the-art attacks.

Geometric deep learning has sparked a rising interest in computer graphics to perform shape understanding tasks, such as shape classification and semantic segmentation. When the input is a polygonal surface, one has to suffer from the irregular mesh structure. Motivated by the geometric spectral theory, we introduce Laplacian2Mesh, a novel and flexible convolutional neural network (CNN) framework for coping with irregular triangle meshes (vertices may have any valence). By mapping the input mesh surface to the multi-dimensional Laplacian-Beltrami space, Laplacian2Mesh enables one to perform shape analysis tasks directly using the mature CNNs, without the need to deal with the irregular connectivity of the mesh structure. We further define a mesh pooling operation such that the receptive field of the network can be expanded while retaining the original vertex set as well as the connections between them. Besides, we introduce a channel-wise self-attention block to learn the individual importance of feature ingredients. Laplacian2Mesh not only decouples the geometry from the irregular connectivity of the mesh structure but also better captures the global features that are central to shape classification and segmentation. Extensive tests on various datasets demonstrate the effectiveness and efficiency of Laplacian2Mesh, particularly in terms of the capability of being vulnerable to noise to fulfill various learning tasks.

Surface reconstruction is a challenging task when input point clouds, especially real scans, are noisy and lack normals. Observing that the Multilayer Perceptron (MLP) and the implicit moving least-square function (IMLS) provide a dual representation of the underlying surface, we introduce Neural-IMLS, a novel approach that directly learns a noise-resistant signed distance function (SDF) from unoriented raw point clouds in a self-supervised manner. In particular, IMLS regularizes MLP by providing estimated SDFs near the surface and helps enhance its ability to represent geometric details and sharp features, while MLP regularizes IMLS by providing estimated normals. We prove that at convergence, our neural network produces a faithful SDF whose zero-level set approximates the underlying surface due to the mutual learning mechanism between the MLP and the IMLS. Extensive experiments on various benchmarks, including synthetic and real scans, show that Neural-IMLS can reconstruct faithful shapes even with noise and missing parts. The source code can be found at https://github.com/bearprin/Neural-IMLS.

We derive approximate bit error probability (BEP) expressions for binary differential phase shift keying (BDPSK) and quadrature differential phase shift keying (QDPSK) signals in free-space optical communication system over exponentiated Weibull (EW) fading channel. By using the cumulative distribution function of EW channel and integration by parts, the conventional BEP expressions with the integral over an infinite interval are transformed to the integral over a finite interval. Based on the novel BEP expressions, we derive new, closed-form, approximate BEP expressions that involve only a gamma function, which reduce the computational complexity. The approximate BEP expressions are compared with theoretical BEP expressions under weak, moderate, and strong turbulence regimes, where the maximum gaps between the approximate and theoretical BEP expressions are 0.33 dB and 1.36 dB for BDPSK and QDPSK signals, respectively. The approximate BEP expressions are also used to analyze the loss of signal-to-noise ratio in EW fading channel.

The Signed Distance Function (SDF), as an implicit surface representation, provides a crucial method for reconstructing a watertight surface from unorganized point clouds. The SDF has a fundamental relationship with the principles of surface vector calculus. Given a smooth surface, there exists a thin-shell space in which the SDF is differentiable everywhere such that the gradient of the SDF is an eigenvector of its Hessian matrix, with a corresponding eigenvalue of zero. In this paper, we introduce a method to directly learn the SDF from point clouds in the absence of normals. Our motivation is grounded in a fundamental observation: aligning the gradient and the Hessian of the SDF provides a more efficient mechanism to govern gradient directions. This, in turn, ensures that gradient changes more accurately reflect the true underlying variations in shape. Extensive experimental results demonstrate its ability to accurately recover the underlying shape while effectively suppressing the presence of ghost geometry.

Shape manipulation is a central research topic in computer graphics. Topology editing, such as breaking apart connections, joining disconnected ends, and filling/opening a topological hole, is generally more challenging than geometry editing. In this paper, we observe that the saddle points of the signed distance function (SDF) provide useful hints for altering surface topology deliberately. Based on this key observation, we parameterize the SDF into a cubic trivariate tensor-product B-spline function F whose saddle points {si} can be quickly exhausted based on a subdivision-based root-finding technique coupled with Newton’s method. Users can select one of the candidate points, say si, to edit the topology in real time. In implementation, we add a compactly supported B-spline function rooted at si, which we call a deformer in this paper, to F, with its local coordinate system aligning with the three eigenvectors of the Hessian. Combined with ray marching technique, our interactive system operates at 30 FPS. Additionally, our system empowers users to create desired bulges or concavities on the surface. An extensive user study indicates that our system is user-friendly and intuitive to operate. We demonstrate the effectiveness and usefulness of our system in a range of applications, including fixing surface reconstruction errors, artistic work design, 3D medical imaging and simulation, and antiquity restoration. Please refer to the attached video for a demonstration.

In conventional approach, the bit error probability (BEP) expressions of$M$-ary phase-shift keying (MPSK) signals over additive white Gaussian noise (AWGN) channel are derived by averaging error probabilities for all bits of MPSK symbol. The closed-form BEP expressions of MPSK signals over AWGN channel can also be derived by using the weighted conditional symbol error probability (SEP) expressions, which has not been reported. In this paper, we derive the conditional SEP expressions of MPSK signals in terms of Gaussian$Q$and Owen's$T$functions by changing the domain of integration from a plane bounded by two rays into a quadrant. By weighting the conditional SEP expressions according to average distance spectrum, the closed-form BEP expressions of MPSK signals over AWGN channel are obtained. Only two summations involving two parameters are required. The closed-form BEP expressions of MPSK signals over Nakagami-$m$fading channel are derived by using the BEP expressions over AWGN channel and the moment generating function-based approach. The approximate BEP expressions of MPSK signals over Nakagami-$m$fading channel are obtained by using elementary functions-based approximations of Gaussian$Q$and Owen’s$T$functions. The conciseness and computational complexity of our BEP expressions are verified by the comparison with existing results.

Deep learning (DL) has achieved tremendous success in recent years in many fields. The success of DL typically relies on a considerable amount of training data and the expensive model optimization process. Therefore, a trained DL model and its corresponding training data have become valuable assets whose intellectual property (IP) needs to be protected. Once a DL model or its training dataset is released, there is currently no mechanism for the entity that owns one part to establish a clear relationship with the other. In this paper, we aim to reveal the integrated relationship between a given DL model and the corresponding training dataset, by framing the problem of knowledge representation of a dataset with respect to DL models trained on it:how to effectively represent the knowledge transferred from a training dataset to a DL model?Our basic idea is that the knowledge transferred from a training dataset to a DL model can be uniquely represented by the model’s decision boundary. Therefore, we design a novel generation method that utilizes geometric consistency to find the samples supporting the decision boundary, which can serve as the proxy for the knowledge representation. We evaluate our method in three different cases: IP audit of training data, IP audit of DL models, and adversarial knowledge distillation. The experimental results show that our method can improve the performance of existing works in all cases, which confirm that our method can effectively represent the knowledge transferred from a training dataset to a DL model.

Neural implicit representation is a promising approach for reconstructing surfaces from point clouds. Existing methods combine various regularization terms, such as the Eikonal and Laplacian energy terms, to enforce the learned neural function to possess the properties of a Signed Distance Function (SDF). However, inferring the actual topology and geometry of the underlying surface from poor-quality unoriented point clouds remains challenging. In accordance with Differential Geometry, the Hessian of the SDF is singular for points within the differential thin-shell space surrounding the surface. Our approach enforces the Hessian of the neural implicit function to have a zero determinant for points near the surface. This technique aligns the gradients for a near-surface point and its on-surface projection point, producing a rough but faithful shape within just a few iterations. By annealing the weight of the singular-Hessian term, our approach ultimately produces a high-fidelity reconstruction result. Extensive experimental results demonstrate that our approach effectively suppresses ghost geometry and recovers details from unoriented point clouds with better expressiveness than existing fitting-based methods.

The task of explicit surface reconstruction is to generate a surface mesh by interpolating a given point cloud. Explicit surface reconstruction is necessary when the point cloud is required to appear exactly on the surface. However, for a non-perfect input, such as lack of normals, low density, irregular distribution, thin and tiny parts, and high genus, a robust explicit reconstruction method that can generate a high-quality manifold triangulation is missing. We propose a robust explicit surface reconstruction method that starts from an initial simple surface mesh, alternately performs a Filmsticking step and a Sculpting step of the initial mesh, and converges when the surface mesh interpolates all input points (except outliers) and remains stable. The Filmsticking is to minimize the geometric distance between the surface mesh and the point cloud through iteratively performing a restricted Voronoi diagram technique on the surface mesh, whereas the Sculpting is to bootstrap the Filmsticking iteration from local minima by applying appropriate geometric and topological changes of the surface mesh. Our algorithm is fully automatic and produces high-quality surface meshes for non-perfect inputs that are typically considered to be challenging for prior state of the art. We conducted extensive experiments on simulated scans and real scans to validate the effectiveness of our approach.

Feature lines are important geometric cues in characterizing the structure of a CAD model. Despite great progress in both explicit reconstruction and implicit reconstruction, it remains a challenging task to reconstruct a polygonal surface equipped with feature lines, especially when the input point cloud is noisy and lacks faithful normal vectors. In this paper, we develop a multistage algorithm, named RFEPS , to address this challenge. The key steps include (1) denoising the point cloud based on the assumption of local planarity, (2) identifying the feature-line zone by optimization of discrete optimal transport, (3) augmenting the point set so that sufficiently many additional points are generated on potential geometry edges, and (4) generating a polygonal surface that interpolates the augmented point set based on restricted power diagram. We demonstrate through extensive experiments that RFEPS, benefiting from the edge-point augmentation and the feature preserving explicit reconstruction, outperforms state of the art methods in terms of the reconstruction quality, especially in terms of the ability to reconstruct missing feature lines.

Visible light communication (VLC) system is a great candidate for indoor downlink access. Due to the limitation of light-emitting diode (LED)'s bandwidth, orthogonal frequency division multiplexing (OFDM) is used to enhance the transmission capacity of VLC system. Non-orthogonal multiple access (NOMA) can support multiple users in VLC system by sharing time and spectrum resources. The combination of OFDM and NOMA improves the overall channel capacity and spectral efficiency of a multi-user VLC system. In order to increase the data rate further, high order modulation formats are often applied. However, for the superposition of multiple high order modulation signals such as 16-quadrature amplitude modulation (QAM) and 64-QAM, it is hard to recover each user's signal under traditional successive interference cancellation (SIC) method, which is usually used in NOMA scheme. In this paper, we proposed a novel method to decode the superposed signals. This method is called ergodicity and comparison (EAC). By applying the EAC method, the bit error rate (BER) performance of two- user OFDM-NOMA VLC system is investigated under different power allocation conditions. In this system, the modulation formats for both the two users' signals are 4-QAM, 16-QAM and 64-QAM. Peak clipping effect on the received superposed signals is also considered. Numerical results demonstrate that the EAC method can improve significantly the BER performance of OFDM-NOMA VLC system, when high order M-QAM (M> 4) signals are applied to the two users.

This paper proposes a novel design of an optical wireless communications (OWC) receiver using a solar panel as a photodetector. The proposed system is capable of simultaneous data transmission and energy harvesting. The solar panel can convert a modulated light signal into an electrical signal without any external power requirements. Furthermore, the direct current (DC) component of the modulated light can be harvested in the proposed receiver. The generated energy can potentially be used to power a user terminal or at least to prolong its operation time. The current work discusses the various parameters which need to be considered in the design of a system using a solar panel for simultaneous communication and energy harvesting. The presented theory is supported with an experimental implementation of orthogonal frequency division multiplexing (OFDM), thus, proving the validity of the analysis and demonstrating the feasibility of the proposed receiver. Using the propounded system, a communication link with a data rate of 11.84 Mbps is established for a received optical signal with a peak-to-peak amplitude of 0.7 × 10-3W/cm2.

In this paper, we experimentally demonstrate the feasibility of optical wireless communication (OWC) systems with a solar panel as a photo-detector. The advantage of a solar panel is that it is a passive device, which does not require an additional power supply for converting the received light signal into an electrical signal. The frequency response of a solar panel shows that its 3-dB modulation bandwidth is 350 kHz. The results demonstrate that for a 1-Mbit/s on-off keying signal, a bit error rate of less than 2 × 10-3could be achieved when the average irradiance on the solar panel is 3.5 × 10-4W/cm2. In the current experimental setup, this corresponds to a transmission distance of 39 cm. A data rate of 7.01 Mbit/s is achieved by using orthogonal frequency division multiplexing. In addition, the feasibility of using the solar panel for simultaneous communication and energy harvesting is investigated. A load is connected in parallel to the receiver circuit in order to simulate the conditions of charging a battery by using the received signal's DC component. It is shown that the load does not hamper the communication capabilities. Hence, an OWC system with a solar-panel-based receiver can satisfy the requirements of simultaneous communication and energy harvesting.