arXiv subjects

Haobo Zhang

Publications and source records attributed to Haobo Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2026

ForgetMark: Stealthy Fingerprint Embedding via Targeted Unlearning in Language Models

Existing invasive (backdoor) fingerprints suffer from high-perplexity triggers that are easily filtered, fixed response patterns exposed by heuristic detectors, and spurious activations on benign inputs. We introduce \textsc{ForgetMark}, a stealthy fingerprinting framework that encodes provenance via targeted unlearning. It builds a compact, human-readable key--value set with an assistant model and predictive-entropy ranking, then trains lightweight LoRA adapters to suppress the original values on their keys while preserving general capabilities. Ownership is verified under black/gray-box access by aggregating likelihood and semantic evidence into a fingerprint success rate. By relying on probabilistic forgetting traces rather than fixed trigger--response patterns, \textsc{ForgetMark} avoids high-perplexity triggers, reduces detectability, and lowers false triggers. Across diverse architectures and settings, it achieves 100\% ownership verification on fingerprinted models while maintaining standard performance, surpasses backdoor baselines in stealthiness and robustness to model merging, and remains effective under moderate incremental fine-tuning. Our code and data are available at \href{https://github.com/Xuzhenhua55/ForgetMark}{https://github.com/Xuzhenhua55/ForgetMark}.

cs.CR↗

arXiv2025

Chain-of-Generation: Progressive Latent Diffusion for Text-Guided Molecular Design

Text-conditioned molecular generation aims to translate natural-language descriptions into chemical structures, enabling scientists to specify functional groups, scaffolds, and physicochemical constraints without handcrafted rules. Diffusion-based models, particularly latent diffusion models (LDMs), have recently shown promise by performing stochastic search in a continuous latent space that compactly captures molecular semantics. Yet existing methods rely on one-shot conditioning, where the entire prompt is encoded once and applied throughout diffusion, making it hard to satisfy all the requirements in the prompt. We discuss three outstanding challenges of one-shot conditioning generation, including the poor interpretability of the generated components, the failure to generate all substructures, and the overambition in considering all requirements simultaneously. We then propose three principles to address those challenges, motivated by which we propose Chain-of-Generation (CoG), a training-free multi-stage latent diffusion framework. CoG decomposes each prompt into curriculum-ordered semantic segments and progressively incorporates them as intermediate goals, guiding the denoising trajectory toward molecules that satisfy increasingly rich linguistic constraints. To reinforce semantic guidance, we further introduce a post-alignment learning phase that strengthens the correspondence between textual and molecular latent spaces. Extensive experiments on benchmark and real-world tasks demonstrate that CoG yields higher semantic alignment, diversity, and controllability than one-shot baselines, producing molecules that more faithfully reflect complex, compositional prompts while offering transparent insight into the generation process.

cs.LG↗

arXiv2025

Holographic Beamforming for Integrated Sensing and Communication with Mutual Coupling Effects

Integrated sensing and communication (ISAC) is envisioned as a key technology in 6G networks, owing to its potential for high spectral and cost efficiency. As a promising solution for extremely large-scale arrays, reconfigurable holographic surfaces (RHS) can be integrated with ISAC to form the holographic ISAC paradigm, where enlarged radiation apertures of RHS can achieve significant beamforming gains, thereby improving both communication and sensing performance. In this paper, we investigate holographic beamforming designs for ISAC systems, which, unlike existing holographic beamforming schemes developed for RHS-aided communications, requires explicit consideration of mutual coupling effects within RHS. This is because, different from prior works only considering communication performance, ISAC systems incorporate sensing functionality, which is sensitive to sidelobe levels. Ignoring mutual coupling in holographic beamforming can lead to notable undesired sidelobes, thus degrading sensing performance. The consideration of mutual coupling introduces new challenges, i.e., it induces non-linearity in beamforming problems, rendering them inherently non-convex. To address this issue, we propose a tractable electromagnetic-compliant holographic ISAC model that characterizes mutual coupling in a closed form using coupled dipole approximations. We then develop an efficient mutual coupling aware holographic beamforming algorithm to suppress sidelobes and enhance ISAC performance. Numerical results validate effectiveness of the proposed algorithm.

cs.IT↗

arXiv2025

Hybrid Near-field and Far-field Localization with Holographic MIMO

Due to its ability to precisely control wireless beams, holographic multiple-input multiple-output (HMIMO) is expected to be a promising solution to achieve high-accuracy localization. However, as the scale of HMIMO increases to improve beam control capability, the corresponding near-field (NF) region expands, indicating that users may exist in both NF and far-field (FF) regions with different electromagnetic transmission characteristics. As a result, existing methods for pure NF or FF localization are no longer applicable. We consider a hybrid NF and FF localization scenario in this paper, where a base station (BS) locates multiple users in both NF and FF regions with the aid of a reconfigurable intelligent surface (RIS), which is a low-cost implementation of HMIMO. In such a scenario, it is difficult to locate the users and optimize the RIS phase shifts because whether the location of the user is in the NF or FF region is unknown, and the channels of different users are coupled. To tackle this challenge, we propose a RIS-enabled localization method that searches the users in both NF and FF regions and tackles the coupling issue by jointly estimating all user locations. We derive the localization error bound by considering the channel coupling and propose an RIS phase shift optimization algorithm that minimizes the derived bound. Simulations show the effectiveness of the proposed method and demonstrate the performance gain compared to pure NF and FF techniques.

eess.SP↗

arXiv2025

Hybrid Near-Field and Far-Field Localization with Multiple Holographic MIMO Surfaces

Localization using multiple base stations (BSs) has gained much attention for its advantage in localization accuracy. However, the performance of the multi-BS system suffers from its limited number of antennas. To solve the above issue, we propose to use reconfigurable intelligent surfaces (RIS) serving as antennas. Existing localization methods enabled by multiple RISs mainly focus on the far-field (FF) region of each RIS. As the scale of RIS increases, the near-field (NF) region of each RIS expands, where FF methods struggle to achieve high localization accuracy. In this letter, a hybrid NF and FF localization method aided by multiple RISs is proposed. In such scenarios, achieving user localization and RIS optimization becomes challenging due to the high complexity caused by the exhaustive search through all candidate locations to match the signals. Moreover, the interference from multiple RISs degrades the localization accuracy. To address this challenge, we propose a two-phase localization method that first estimates the relative locations of the user to each RIS and fuses the results to obtain the estimation. This approach reduces the complexity by decreasing the number of candidate locations considered in each step. Also, we introduce a constraint in the RIS optimization problem that limits the sidelobe levels directed towards other RISs, effectively minimizing inter-RIS interference. The effectiveness of the proposed method is verified through simulations.

eess.SP↗

arXiv2025

On the Pinsker bound of inner product kernel regression in large dimensions

Building on recent studies of large-dimensional kernel regression, particularly those involving inner product kernels on the sphere $\mathbb{S}^{d}$, we investigate the Pinsker bound for inner product kernel regression in such settings. Specifically, we address the scenario where the sample size $n$ is given by $αd^γ(1+o_{d}(1))$ for some $α, γ>0$. We have determined the exact minimax risk for kernel regression in this setting, not only identifying the minimax rate but also the exact constant, known as the Pinsker constant, associated with the excess risk.

math.ST↗

arXiv2025

On the Saturation Effects of Spectral Algorithms in Large Dimensions

The saturation effects, which originally refer to the fact that kernel ridge regression (KRR) fails to achieve the information-theoretical lower bound when the regression function is over-smooth, have been observed for almost 20 years and were rigorously proved recently for kernel ridge regression and some other spectral algorithms over a fixed dimensional domain. The main focus of this paper is to explore the saturation effects for a large class of spectral algorithms (including the KRR, gradient descent, etc.) in large dimensional settings where $n \asymp d^γ$. More precisely, we first propose an improved minimax lower bound for the kernel regression problem in large dimensional settings and show that the gradient flow with early stopping strategy will result in an estimator achieving this lower bound (up to a logarithmic factor). Similar to the results in KRR, we can further determine the exact convergence rates (both upper and lower bounds) of a large class of (optimal tuned) spectral algorithms with different qualification $τ$'s. In particular, we find that these exact rate curves (varying along $γ$) exhibit the periodic plateau behavior and the polynomial approximation barrier. Consequently, we can fully depict the saturation effects of the spectral algorithms and reveal a new phenomenon in large dimensional settings (i.e., the saturation effect occurs in large dimensional setting as long as the source condition $s>τ$ while it occurs in fixed dimensional setting as long as $s>2τ$).

stat.ML↗

arXiv2024

On the Optimality of Misspecified Spectral Algorithms

In the misspecified spectral algorithms problem, researchers usually assume the underground true function $f_ρ^{*} \in [\mathcal{H}]^{s}$, a less-smooth interpolation space of a reproducing kernel Hilbert space (RKHS) $\mathcal{H}$ for some $s\in (0,1)$. The existing minimax optimal results require $\|f_ρ^{*}\|_{L^{\infty}}<\infty$ which implicitly requires $s > α_{0}$ where $α_{0}\in (0,1)$ is the embedding index, a constant depending on $\mathcal{H}$. Whether the spectral algorithms are optimal for all $s\in (0,1)$ is an outstanding problem lasting for years. In this paper, we show that spectral algorithms are minimax optimal for any $α_{0}-\frac{1}β < s < 1$, where $β$ is the eigenvalue decay rate of $\mathcal{H}$. We also give several classes of RKHSs whose embedding index satisfies $ α_0 = \frac{1}β $. Thus, the spectral algorithms are minimax optimal for all $s\in (0,1)$ on these RKHSs.

math.ST↗

arXiv2024

Optimal Rate of Kernel Regression in Large Dimensions

We perform a study on kernel regression for large-dimensional data (where the sample size $n$ is polynomially depending on the dimension $d$ of the samples, i.e., $n\asymp d^γ$ for some $γ>0$ ). We first build a general tool to characterize the upper bound and the minimax lower bound of kernel regression for large dimensional data through the Mendelson complexity $\varepsilon_{n}^{2}$ and the metric entropy $\bar{\varepsilon}_{n}^{2}$ respectively. When the target function falls into the RKHS associated with a (general) inner product model defined on $\mathbb{S}^{d}$, we utilize the new tool to show that the minimax rate of the excess risk of kernel regression is $n^{-1/2}$ when $n\asymp d^γ$ for $γ=2, 4, 6, 8, \cdots$. We then further determine the optimal rate of the excess risk of kernel regression for all the $γ>0$ and find that the curve of optimal rate varying along $γ$ exhibits several new phenomena including the multiple descent behavior and the periodic plateau behavior. As an application, For the neural tangent kernel (NTK), we also provide a similar explicit description of the curve of optimal rate. As a direct corollary, we know these claims hold for wide neural networks as well.

stat.ML↗

arXiv2024

On the Saturation Effect of Kernel Ridge Regression

The saturation effect refers to the phenomenon that the kernel ridge regression (KRR) fails to achieve the information theoretical lower bound when the smoothness of the underground truth function exceeds certain level. The saturation effect has been widely observed in practices and a saturation lower bound of KRR has been conjectured for decades. In this paper, we provide a proof of this long-standing conjecture.

stat.ML↗

arXiv2024

The phase diagram of kernel interpolation in large dimensions

The generalization ability of kernel interpolation in large dimensions (i.e., $n \asymp d^γ$ for some $γ>0$) might be one of the most interesting problems in the recent renaissance of kernel regression, since it may help us understand the 'benign overfitting phenomenon' reported in the neural networks literature. Focusing on the inner product kernel on the sphere, we fully characterized the exact order of both the variance and bias of large-dimensional kernel interpolation under various source conditions $s\geq 0$. Consequently, we obtained the $(s,γ)$-phase diagram of large-dimensional kernel interpolation, i.e., we determined the regions in $(s,γ)$-plane where the kernel interpolation is minimax optimal, sub-optimal and inconsistent.

cs.LG↗

arXiv2024

Safe and Robust Watermark Injection with a Single OoD Image

Training a high-performance deep neural network requires large amounts of data and computational resources. Protecting the intellectual property (IP) and commercial ownership of a deep model is challenging yet increasingly crucial. A major stream of watermarking strategies implants verifiable backdoor triggers by poisoning training samples, but these are often unrealistic due to data privacy and safety concerns and are vulnerable to minor model changes such as fine-tuning. To overcome these challenges, we propose a safe and robust backdoor-based watermark injection technique that leverages the diverse knowledge from a single out-of-distribution (OoD) image, which serves as a secret key for IP verification. The independence of training data makes it agnostic to third-party promises of IP security. We induce robustness via random perturbation of model parameters during watermark injection to defend against common watermark removal attacks, including fine-tuning, pruning, and model extraction. Our experimental results demonstrate that the proposed watermarking approach is not only time- and sample-efficient without training data, but also robust against the watermark removal attacks above.

cs.CV↗

arXiv2024

Multi-target Detection for Reconfigurable Holographic Surfaces Enabled Radar

Multi-target detection is one of the primary tasks in radar-based localization and sensing, typically built on phased array antennas. However, the bulky hardware in the phased array restricts its potential for enhancing detection accuracy, since the cost and power of the phased array can become unaffordable as its physical aperture scales up to pursue higher beam shaping capabilities. To resolve this issue, we propose a radar system enabled by reconfigurable holographic surfaces (RHSs), a novel meta-surface antenna composed of meta-material elements with cost-effective and power-efficient hardware, which performs multi-target detection in an adaptive manner. Different from the phase-control structure in the phased array, the RHS is able to apply beamforming by controlling the radiation amplitudes of its elements. Consequently, traditional beamforming schemes designed for phased arrays cannot be directly applied to RHSs due to this structural difference. To tackle this challenge, a waveform and amplitude optimization algorithm (WAOA) is designed to jointly optimize the radar waveform and RHS amplitudes in order to improve the detection accuracy. Simulation results reveal that the proposed RHS-enabled radar increases the probability of detection by 0.13 compared to phased array radars when six iterations of adaptive detection are performed given the same hardware cost.

eess.SP↗

arXiv2024

Reconfigurable Holographic Surface Aided Wireless Simultaneous Localization and Mapping

As a crucial facilitator of future autonomous driving applications, wireless simultaneous localization and mapping (SLAM) has drawn growing attention recently. However, the accuracy of existing wireless SLAM schemes is limited because the antenna gain is constrained given the cost budget due to the expensive hardware components such as phase arrays. To address this issue, we propose a reconfigurable holographic surface (RHS)-aided SLAM system in this paper. The RHS is a novel type of low-cost antenna that can cut down the hardware cost by replacing phased arrays in conventional SLAM systems. However, compared with a phased array where the phase shifts of parallelfed signals are adjusted, the RHS exhibits a different radiation model because its amplitude-controlled radiation elements are series-fed by surface waves, implying that traditional schemes cannot be applied directly. To address this challenge, we propose an RHS-aided beam steering method for sensing the surrounding environment and design the corresponding SLAM algorithm. Simulation results show that the proposed scheme can achieve more than there times the localization accuracy that traditional wireless SLAM with the same cost achieves.

eess.SP↗

arXiv2024

Unified Near-field and Far-field Localization with Holographic MIMO

Localization which uses holographic multiple input multiple output surface such as reconfigurable intelligent surface (RIS) has gained increasing attention due to its ability to accurately localize users in non-line-of-sight conditions. However, existing RIS-enabled localization methods assume the users at either the near-field (NF) or the far-field (FF) region, which results in high complexity or low localization accuracy, respectively, when they are applied in the whole area. In this paper, a unified NF and FF localization method is proposed for the RIS-enabled localization system to overcome the above issue. Specifically, the NF and FF regions are both divided into grids. The RIS reflects the signals from the user to the base station~(BS), and then the BS uses the received signals to determine the grid where the user is located. Compared with existing NF- or FF-only schemes, the design of the location estimation method and the RIS phase shift optimization algorithm is more challenging because they are based on a hybrid NF and FF model. To tackle these challenges, we formulate the optimization problems for location estimation and RIS phase shifts, and design two algorithms to effectively solve the formulated problems, respectively. The effectiveness of the proposed method is verified through simulations.

eess.SP↗

arXiv2024

Understanding Deep Gradient Leakage via Inversion Influence Functions

Deep Gradient Leakage (DGL) is a highly effective attack that recovers private training images from gradient vectors. This attack casts significant privacy challenges on distributed learning from clients with sensitive data, where clients are required to share gradients. Defending against such attacks requires but lacks an understanding of when and how privacy leakage happens, mostly because of the black-box nature of deep networks. In this paper, we propose a novel Inversion Influence Function (I$^2$F) that establishes a closed-form connection between the recovered images and the private gradients by implicitly solving the DGL problem. Compared to directly solving DGL, I$^2$F is scalable for analyzing deep networks, requiring only oracle access to gradients and Jacobian-vector products. We empirically demonstrate that I$^2$F effectively approximated the DGL generally on different model architectures, datasets, modalities, attack implementations, and perturbation-based defenses. With this novel tool, we provide insights into effective gradient perturbation directions, the unfairness of privacy protection, and privacy-preferred model initialization. Our codes are provided in https://github.com/illidanlab/inversion-influence-function.

cs.LG↗

arXiv2024

Optimal Rates of Kernel Ridge Regression under Source Condition in Large Dimensions

Motivated by the studies of neural networks (e.g.,the neural tangent kernel theory), we perform a study on the large-dimensional behavior of kernel ridge regression (KRR) where the sample size $n \asymp d^γ$ for some $γ> 0$. Given an RKHS $\mathcal{H}$ associated with an inner product kernel defined on the sphere $\mathbb{S}^{d}$, we suppose that the true function $f_ρ^{*} \in [\mathcal{H}]^{s}$, the interpolation space of $\mathcal{H}$ with source condition $s>0$. We first determined the exact order (both upper and lower bound) of the generalization error of kernel ridge regression for the optimally chosen regularization parameter $λ$. We then further showed that when $0 1$, KRR is not minimax optimal (a.k.a. he saturation effect). Our results illustrate that the curves of rate varying along $γ$ exhibit the periodic plateau behavior and the multiple descent behavior and show how the curves evolve with $s>0$. Interestingly, our work provides a unified viewpoint of several recent works on kernel regression in the large-dimensional setting, which correspond to $s=0$ and $s=1$ respectively.

cs.LG↗

arXiv2023

RIS-based IMT-2030 Testbed for MmWave Multi-stream Ultra-massive MIMO Communications

As one enabling technique of the future sixth generation (6G) network, ultra-massive multiple-input-multiple-output (MIMO) can support high-speed data transmissions and cell coverage extension. However, it is hard to realize the ultra-massive MIMO via traditional phased arrays due to unacceptable power consumption. To address this issue, reconfigurable intelligent surface-based (RIS-based) antennas are an energy-efficient enabler of the ultra-massive MIMO, since they are free of energy-hungry phase shifters. In this article, we report the performances of the RIS-enabled ultra-massive MIMO via a project called Verification of MmWave Multi-stream Transmissions Enabled by RIS-based Ultra-massive MIMO for 6G (V4M), which was proposed to promote the evolution towards IMT-2030. In the V4M project, we manufacture RIS-based antennas with 1024 one-bit elements working at 26 GHz, based on which an mmWave dual-stream ultra-massive MIMO prototype is implemented for the first time. To approach practical settings, the Tx and Rx of the prototype are implemented by one commercial new radio base station and one off-the-shelf user equipment, respectively. The measured data rate of the dual-stream prototype approaches the theoretical peak rate. Our contributions to the V4M project are also discussed by presenting technological challenges and corresponding solutions.

cs.IT↗