arXiv subjects

Huimin Li

Publications and source records attributed to Huimin Li.

At least 19 recordsLinked to original sources

arXiv2026

AttackonCTF: Defending Hardware Security Competition Benchmarks in the Age of LLMs

Hardware security competitions such as HackTheSilicon serve as benchmarking platforms for evaluating vulnerability detection methods and for training humans and AI. However, our study reveals that LLMs threaten their validity. Instead of genuine security reasoning, detectors exploit a diff-style syntactic comparison, achieving an 83% detection rate, undermining fair evaluation. To mitigate this, we propose the first LLM-oriented, semantics-preserving obfuscation framework for these benchmarks. Unlike IP-protection approaches, it applies human-readable transformations and controlled diff-noise while preserving functionality. On HackTheSilicon, the framework reduces LLM-based detection accuracy by 50% with only 10% obfuscation and by 78.6% under complete obfuscation, restoring benchmark reliability.

cs.CR↗

arXiv2026

Patch-MoE Mamba: A Patch-Ordered Mixture-of-Experts State Space Architecture for Medical Image Segmentation

CNN- and Transformer-based architectures have achieved strong performance in medical image segmentation, but CNNs are limited in modeling long-range dependencies, while Transformers often suffer from quadratic computational and memory complexity. State space models, especially Mamba-based networks, offer an efficient alternative with linear sequence complexity. However, existing Mamba segmentation models still face two limitations: pixel-wise directional scanning can disrupt local 2D spatial structure, and simple summation-based fusion of scan directions cannot adapt well to diverse object sizes, shapes, and boundaries. To address these issues, we propose \textit{Patch-MoE Mamba}, a patch-ordered mixture-of-experts state space architecture for medical image segmentation. It introduces a hierarchical patch-ordered scanning mechanism that preserves local spatial neighborhoods while capturing multi-scale context, and an MoE-based directional fusion module that adaptively combines multiple Mamba scanner outputs using four directional experts, a learnable concatenation expert, and residual directional aggregation. Experiments on five public polyp segmentation benchmarks and the ISIC 2017/2018 skin lesion segmentation datasets demonstrate the effectiveness and generality of Patch-MoE Mamba.

cs.CV↗

arXiv2026

An uncertainty model for positive-valued parameters with application to robust optimization

Many practical optimization problems involve uncertain parameters that are strictly positive. However, the most common uncertainty sets used in robust optimization are the box and the ellipsoidal sets, which may include non-positive values when the level of uncertainty is large. This can lead to overly conservative solutions or make the corresponding robust counterpart infeasible. To overcome this, in this paper, we propose a new uncertainty-set model that not only preserves positivity but is also computationally tractable. The proposed set uses a particular convex function that measures the variation of uncertain parameters from their nominal values. We can also write the dual reformulation of the associated robust problem. For the theoretical results, we show several properties of the proposed model, including analytical bounds that guide the choice of the uncertainty level, as well as a probabilistic guarantee result. To check the validity of our proposal, we consider photovoltaic-battery operation planning problems and support vector machines in the numerical experiments. For these problems, standard uncertainty models may lead to infeasibility of the robust counterpart, while the proposed uncertainty set gives a tractable dual reformulation.

math.OC↗

arXiv2026

AegisSat: Securing AI-Enabled SoC FPGA Satellite Platforms

The increasing adoption of System-on-Chip Field-Programmable Gate Arrays (SoC FPGAs) in AI-enabled satellite systems, valued for their reconfigurability and in-orbit update capabilities, introduces significant security challenges. Compromised updates can lead to performance degradation, service disruptions, or adversarial manipulation of mission outcomes. To address these risks, this paper proposes a comprehensive security framework, AegisSat. It ensures the integrity and resilience of satellite platforms by (i) integrating cryptographically-based secure boot mechanisms to establish a trusted computing base; (ii) enforcing strict runtime resource isolation; (iii) employing authenticated procedures for in-orbit reconfiguration and AI model updates to prevent unauthorized modifications; and (iv) providing robust rollback capabilities to recover from boot and update failures and maintain system stability. To further support our claims, we conducted experiments demonstrating the integration of these mechanisms on contemporary SoC FPGA devices. This defense-in-depth framework is crucial for space applications, where physical access is impossible and systems must operate reliably over extended periods, thereby enhancing the trustworthiness of SoC FPGA-based satellite systems and enabling secure and resilient AI operations in orbit.

cs.CR↗

arXiv2026

Learning with Geometric Priors in U-Net Variants for Polyp Segmentation

Accurate and robust polyp segmentation is essential for early colorectal cancer detection and for computer-aided diagnosis. While convolutional neural network-, Transformer-, and Mamba-based U-Net variants have achieved strong performance, they still struggle to capture geometric and structural cues, especially in low-contrast or cluttered colonoscopy scenes. To address this challenge, we propose a novel Geometric Prior-guided Module (GPM) that injects explicit geometric priors into U-Net-based architectures for polyp segmentation. Specifically, we fine-tune the Visual Geometry Grounded Transformer (VGGT) on a simulated ColonDepth dataset to estimate depth maps of polyp images tailored to the endoscopic domain. These depth maps are then processed by GPM to encode geometric priors into the encoder's feature maps, where they are further refined using spatial and channel attention mechanisms that emphasize both local spatial and global channel information. GPM is plug-and-play and can be seamlessly integrated into diverse U-Net variants. Extensive experiments on five public polyp segmentation datasets demonstrate consistent gains over three strong baselines. Code and the generated depth maps are available at: https://github.com/fvazqu/GPM-PolypSeg

cs.CV↗

arXiv2025

GoldenFuzz: Generative Golden Reference Hardware Fuzzing

Modern hardware systems, driven by demands for high performance and application-specific functionality, have grown increasingly complex, introducing large surfaces for bugs and security-critical vulnerabilities. Fuzzing has emerged as a scalable solution for discovering such flaws. Yet, existing hardware fuzzers suffer from limited semantic awareness, inefficient test refinement, and high computational overhead due to reliance on slow device simulation. In this paper, we present GoldenFuzz, a novel two-stage hardware fuzzing framework that partially decouples test case refinement from coverage and vulnerability exploration. GoldenFuzz leverages a fast, ISA-compliant Golden Reference Model (GRM) as a ``digital twin'' of the Device Under Test (DUT). It fuzzes the GRM first, enabling rapid, low-cost test case refinement, accelerating deep architectural exploration and vulnerability discovery on DUT. During the fuzzing pipeline, GoldenFuzz iteratively constructs test cases by concatenating carefully chosen instruction blocks that balance the subtle inter- and intra-instructions quality. A feedback-driven mechanism leveraging insights from both high- and low-coverage samples further enhances GoldenFuzz's capability in hardware state exploration. Our evaluation of three RISC-V processors, RocketChip, BOOM, and CVA6, demonstrates that GoldenFuzz significantly outperforms existing fuzzers in achieving the highest coverage with minimal test case length and computational overhead. GoldenFuzz uncovers all known vulnerabilities and discovers five new ones, four of which are classified as highly severe with CVSS v3 severity scores exceeding seven out of ten. It also identifies two previously unknown vulnerabilities in the commercial BA51-H core extension.

cs.CR↗

arXiv2025

Integrating Multi-scale and Multi-filtration Topological Features for Medical Image Classification

Modern deep neural networks have shown remarkable performance in medical image classification. However, such networks either emphasize pixel-intensity features instead of fundamental anatomical structures (e.g., those encoded by topological invariants), or they capture only simple topological features via single-parameter persistence. In this paper, we propose a new topology-guided classification framework that extracts multi-scale and multi-filtration persistent topological features and integrates them into vision classification backbones. For an input image, we first compute cubical persistence diagrams (PDs) across multiple image resolutions/scales. We then develop a ``vineyard'' algorithm that consolidates these PDs into a single, stable diagram capturing signatures at varying granularities, from global anatomy to subtle local irregularities that may indicate early-stage disease. To further exploit richer topological representations produced by multiple filtrations, we design a cross-attention-based neural network that directly processes the consolidated final PDs. The resulting topological embeddings are fused with feature maps from CNNs or Transformers. By integrating multi-scale and multi-filtration topologies into an end-to-end architecture, our approach enhances the model's capacity to recognize complex anatomical structures. Evaluations on three public datasets show consistent, considerable improvements over strong baselines and state-of-the-art methods, demonstrating the value of our comprehensive topological perspective for robust and interpretable medical image classification.

cs.CV↗

arXiv2025

TopoImages: Incorporating Local Topology Encoding into Deep Learning Models for Medical Image Classification

Topological structures in image data, such as connected components and loops, play a crucial role in understanding image content (e.g., biomedical objects). % Despite remarkable successes of numerous image processing methods that rely on appearance information, these methods often lack sensitivity to topological structures when used in general deep learning (DL) frameworks. % In this paper, we introduce a new general approach, called TopoImages (for Topology Images), which computes a new representation of input images by encoding local topology of patches. % In TopoImages, we leverage persistent homology (PH) to encode geometric and topological features inherent in image patches. % Our main objective is to capture topological information in local patches of an input image into a vectorized form. % Specifically, we first compute persistence diagrams (PDs) of the patches, % and then vectorize and arrange these PDs into long vectors for pixels of the patches. % The resulting multi-channel image-form representation is called a TopoImage. % TopoImages offers a new perspective for data analysis. % To garner diverse and significant topological features in image data and ensure a more comprehensive and enriched representation, we further generate multiple TopoImages of the input image using various filtration functions, which we call multi-view TopoImages. % The multi-view TopoImages are fused with the input image for DL-based classification, with considerable improvement. % Our TopoImages approach is highly versatile and can be seamlessly integrated into common DL frameworks. Experiments on three public medical image classification datasets demonstrate noticeably improved accuracy over state-of-the-art methods.

cs.CV↗

arXiv2025

Second-order sequential optimality conditions for nonlinear semidefinite optimization problems

Sequential optimality conditions play an important role in constrained optimization since they provide necessary conditions without requiring constraint qualifications (CQs). This paper introduces a second-order extension of the Approximate Karush-Kuhn-Tucker (AKKT) conditions, referred to as AKKT2, for nonlinear semidefinite optimization problems (NSDP). In particular, we provide a formal definition of AKKT2, as well as its stronger variant, called Complementary AKKT2 (CAKKT2), and prove that these conditions are necessary for local minima without any assumption. Moreover, under Robinson's CQ and the weak constant rank property, we show that AKKT2 implies the so-called weak second-order necessary condition. Finally, we propose a penalty-based algorithm that generates sequences whose accumulation points satisfy the AKKT2 and the CAKKT2 conditions.

math.OC↗

arXiv2025

Topo-VM-UNetV2: Encoding Topology into Vision Mamba UNet for Polyp Segmentation

Convolutional neural network (CNN) and Transformer-based architectures are two dominant deep learning models for polyp segmentation. However, CNNs have limited capability for modeling long-range dependencies, while Transformers incur quadratic computational complexity. Recently, State Space Models such as Mamba have been recognized as a promising approach for polyp segmentation because they not only model long-range interactions effectively but also maintain linear computational complexity. However, Mamba-based architectures still struggle to capture topological features (e.g., connected components, loops, voids), leading to inaccurate boundary delineation and polyp segmentation. To address these limitations, we propose a new approach called Topo-VM-UNetV2, which encodes topological features into the Mamba-based state-of-the-art polyp segmentation model, VM-UNetV2. Our method consists of two stages: Stage 1: VM-UNetV2 is used to generate probability maps (PMs) for the training and test images, which are then used to compute topology attention maps. Specifically, we first compute persistence diagrams of the PMs, then we generate persistence score maps by assigning persistence values (i.e., the difference between death and birth times) of each topological feature to its birth location, finally we transform persistence scores into attention weights using the sigmoid function. Stage 2: These topology attention maps are integrated into the semantics and detail infusion (SDI) module of VM-UNetV2 to form a topology-guided semantics and detail infusion (Topo-SDI) module for enhancing the segmentation results. Extensive experiments on five public polyp segmentation datasets demonstrate the effectiveness of our proposed method. The code will be made publicly available.

eess.IV↗

arXiv2025

Adapting a Segmentation Foundation Model for Medical Image Classification

Recent advancements in foundation models, such as the Segment Anything Model (SAM), have shown strong performance in various vision tasks, particularly image segmentation, due to their impressive zero-shot segmentation capabilities. However, effectively adapting such models for medical image classification is still a less explored topic. In this paper, we introduce a new framework to adapt SAM for medical image classification. First, we utilize the SAM image encoder as a feature extractor to capture segmentation-based features that convey important spatial and contextual details of the image, while freezing its weights to avoid unnecessary overhead during training. Next, we propose a novel Spatially Localized Channel Attention (SLCA) mechanism to compute spatially localized attention weights for the feature maps. The features extracted from SAM's image encoder are processed through SLCA to compute attention weights, which are then integrated into deep learning classification models to enhance their focus on spatially relevant or meaningful regions of the image, thus improving classification performance. Experimental results on three public medical image classification datasets demonstrate the effectiveness and data-efficiency of our approach.

cs.CV↗

arXiv2025

A strong second-order sequential optimality condition for nonlinear programming problems

Most numerical methods developed for solving nonlinear programming problems are designed to find points that satisfy certain optimality conditions. While the Karush-Kuhn-Tucker conditions are well-known, they become invalid when constraint qualifications (CQ) are not met. Recent advances in sequential optimality conditions address this limitation in both first- and second-order cases, providing genuine optimality guarantees at local optima, even when CQs do not hold. However, some second-order sequential optimality conditions still require some restrictive conditions on constraints in the recent literature. In this paper, we propose a new strong second-order sequential optimality condition without CQs. We also show that a penalty-type method and an augmented Lagrangian method generate points satisfying these new optimality conditions.

math.OC↗

arXiv2024

Two-molecule theory of polyethylene liquids

Two-molecule theory refers to a class of microscopic, self-consistent field theories for the radial distribution function in classical molecular liquids. The version examined here can be considered as one of the very few formally derived closures to the reference interaction site model (RISM) equation. The theory is applied to polyethylene liquids, computing their equilibrium structural and thermodynamic properties at melt densities. The equation for the radial distribution function, which is represented as an average over the accessible states of two molecules in an external field that mimics the effects of the other molecules in the liquid, is computed by Monte Carlo simulation along with the intramolecular structure function. An improved direct sampling algorithm is utilized to speed the equilibration. Polyethylene chains of 24 and 66 united atom CH2 units are studied. Results are compared with full, many-chain molecular dynamics (MD) simulations and self-consistent polymer-RISM (PRISM) theory with the atomic Percus-Yevick (PY) closure under the same conditions. It is shown that the two-molecule theory produces results that are close to those of MD, and is thus able to overcome defects of PRISM-PY theory and predict more accurate liquid structure at both short and long range. Predictions for the equation of state are also discussed.

cond-mat.soft↗

arXiv2024

Fuzzerfly Effect: Hardware Fuzzing for Memory Safety

Hardware-level memory vulnerabilities severely threaten computing systems. However, hardware patching is inefficient or difficult postfabrication. We investigate the effectiveness of hardware fuzzing in detecting hardware memory vulnerabilities and highlight challenges and potential future research directions to enhance hardware fuzzing for memory safety.

cs.CR↗

arXiv2024

Self Pre-training with Topology- and Spatiality-aware Masked Autoencoders for 3D Medical Image Segmentation

Masked Autoencoders (MAEs) have been shown to be effective in pre-training Vision Transformers (ViTs) for natural and medical image analysis problems. By reconstructing missing pixel/voxel information in visible patches, a ViT encoder can aggregate contextual information for downstream tasks. But, existing MAE pre-training methods, which were specifically developed with the ViT architecture, lack the ability to capture geometric shape and spatial information, which is critical for medical image segmentation tasks. In this paper, we propose a novel extension of known MAEs for self pre-training (i.e., models pre-trained on the same target dataset) for 3D medical image segmentation. (1) We propose a new topological loss to preserve geometric shape information by computing topological signatures of both the input and reconstructed volumes, learning geometric shape information. (2) We introduce a pre-text task that predicts the positions of the centers and eight corners of 3D crops, enabling the MAE to aggregate spatial information. (3) We extend the MAE pre-training strategy to a hybrid state-of-the-art (SOTA) medical image segmentation architecture and co-pretrain it alongside the ViT. (4) We develop a fine-tuned model for downstream segmentation tasks by complementing the pre-trained ViT encoder with our pre-trained SOTA model. Extensive experiments on five public 3D segmentation datasets show the effectiveness of our new approach.

cs.CV↗

arXiv2023

FLAIRS: FPGA-Accelerated Inference-Resistant & Secure Federated Learning

Federated Learning (FL) has become very popular since it enables clients to train a joint model collaboratively without sharing their private data. However, FL has been shown to be susceptible to backdoor and inference attacks. While in the former, the adversary injects manipulated updates into the aggregation process; the latter leverages clients' local models to deduce their private data. Contemporary solutions to address the security concerns of FL are either impractical for real-world deployment due to high-performance overheads or are tailored towards addressing specific threats, for instance, privacy-preserving aggregation or backdoor defenses. Given these limitations, our research delves into the advantages of harnessing the FPGA-based computing paradigm to overcome performance bottlenecks of software-only solutions while mitigating backdoor and inference attacks. We utilize FPGA-based enclaves to address inference attacks during the aggregation process of FL. We adopt an advanced backdoor-aware aggregation algorithm on the FPGA to counter backdoor attacks. We implemented and evaluated our method on Xilinx VMK-180, yielding a significant speed-up of around 300 times on the IoT-Traffic dataset and more than 506 times on the CIFAR-10 dataset.

cs.CR↗

arXiv2020

Learning Enhanced Resolution-wise features for Human Pose Estimation

Recently, multi-resolution networks (such as Hourglass, CPN, HRNet, etc.) have achieved significant performance on pose estimation by combining feature maps of various resolutions. In this paper, we propose a Resolution-wise Attention Module (RAM) and Gradual Pyramid Refinement (GPR), to learn enhanced resolution-wise feature maps for precise pose estimation. Specifically, RAM learns a group of weights to represent the different importance of feature maps across resolutions, and the GPR gradually merges every two feature maps from low to high resolutions to regress final human keypoint heatmaps. With the enhanced resolution-wise features learnt by CNN, we obtain more accurate human keypoint locations. The efficacies of our proposed methods are demonstrated on MS-COCO dataset, achieving state-of-the-art performance with average precision of 77.7 on COCO val2017 set and 77.0 on test-dev2017 set without using extra human keypoint training dataset.

cs.CV↗

arXiv2020

Comparing Wiener complexity with eccentric complexity

The transmission of a vertex $v$ of a graph $G$ is the sum of distances from $v$ to all the other vertices in $G$. The Wiener complexity of $G$ is the number of different transmissions of its vertices. Similarly, the eccentric complexity of $G$ is defined as the number of different eccentricities of its vertices. In this paper these two complexities are compared. The complexities are first studied on Cartesian product graphs. Transmission indivisible graphs and arithmetic transmission graphs are introduced to demonstrate sharpness of upper and lower bounds on the Wiener complexity, respectively. It is shown that for almost all graphs the Wiener complexity is not smaller than the eccentric complexity. This property is proved for trees, the equality holding precisely for center-regular trees. Several families of graphs in which the complexities are equal are constructed. Using the Cartesian product, it is proved that the eccentric complexity can be arbitrarily larger than the Wiener complexity. Additional infinite families of graphs with this property are constructed by amalgamating universally diametrical graphs with center-regular trees.

math.CO↗