arXiv subjects

Xun Lin

Publications and source records attributed to Xun Lin.

At least 37 records · Page 2Linked to original sources

arXiv2025

SVC 2025: the First Multimodal Deception Detection Challenge

Deception detection is a critical task in real-world applications such as security screening, fraud prevention, and credibility assessment. While deep learning methods have shown promise in surpassing human-level performance, their effectiveness often depends on the availability of high-quality and diverse deception samples. Existing research predominantly focuses on single-domain scenarios, overlooking the significant performance degradation caused by domain shifts. To address this gap, we present the SVC 2025 Multimodal Deception Detection Challenge, a new benchmark designed to evaluate cross-domain generalization in audio-visual deception detection. Participants are required to develop models that not only perform well within individual domains but also generalize across multiple heterogeneous datasets. By leveraging multimodal data, including audio, video, and text, this challenge encourages the design of models capable of capturing subtle and implicit deceptive cues. Through this benchmark, we aim to foster the development of more adaptable, explainable, and practically deployable deception detection systems, advancing the broader field of multimodal learning. By the conclusion of the workshop competition, a total of 21 teams had submitted their final results. https://sites.google.com/view/svc-mm25 for more information.

cs.CV↗

arXiv2025

TopoTTA: Topology-Enhanced Test-Time Adaptation for Tubular Structure Segmentation

Tubular structure segmentation (TSS) is important for various applications, such as hemodynamic analysis and route navigation. Despite significant progress in TSS, domain shifts remain a major challenge, leading to performance degradation in unseen target domains. Unlike other segmentation tasks, TSS is more sensitive to domain shifts, as changes in topological structures can compromise segmentation integrity, and variations in local features distinguishing foreground from background (e.g., texture and contrast) may further disrupt topological continuity. To address these challenges, we propose Topology-enhanced Test-Time Adaptation (TopoTTA), the first test-time adaptation framework designed specifically for TSS. TopoTTA consists of two stages: Stage 1 adapts models to cross-domain topological discrepancies using the proposed Topological Meta Difference Convolutions (TopoMDCs), which enhance topological representation without altering pre-trained parameters; Stage 2 improves topological continuity by a novel Topology Hard sample Generation (TopoHG) strategy and prediction alignment on hard samples with pseudo-labels in the generated pseudo-break regions. Extensive experiments across four scenarios and ten datasets demonstrate TopoTTA's effectiveness in handling topological distribution shifts, achieving an average improvement of 31.81% in clDice. TopoTTA also serves as a plug-and-play TTA solution for CNN-based TSS models.

cs.CV↗

arXiv2025

Infinitesimal Torelli problems for special Gushel-Mukai and related Fano threefolds: Hodge theoretical and categorical perspectives

We investigate infinitesimal Torelli problems for some of the Fano threefolds of the following two types: (a) those which can be described as zero loci of sections of vector bundles on Grassmannians (for instance, ordinary Gushel-Mukai threefolds), and (b) double covers of rigid Fano threefolds branched along a $K3$ surface (such as, special Gushel-Mukai threefolds). The differential of the period map for ordinary Gushel-Mukai threefolds has been studied by Debarre, Iliev and Manivel; in particular, it has a $2$-dimensional kernel. The main result of this paper is that the invariant part of the infinitesimal period map for a special Gushel-Mukai threefold is injective. We prove this result using a Hodge theoretical argument as well as a categorical method. Through similar approaches, we also study infinitesimal Torelli problems for prime Fano threefolds with genus $7$, $8$, $9$, $10$, $12$ (type (a)) and for special Verra threefolds (type (b)). Furthermore, a geometric description of the kernel of the differential of the period maps for Gushel-Mukai threefolds (and for prime Fano threefolds of genus $8$) is given via a Bridgeland moduli space in the Kuznetsov components.

math.AG↗

arXiv2025

DADM: Dual Alignment of Domain and Modality for Face Anti-spoofing

With the availability of diverse sensor modalities (i.e., RGB, Depth, Infrared) and the success of multi-modal learning, multi-modal face anti-spoofing (FAS) has emerged as a prominent research focus. The intuition behind it is that leveraging multiple modalities can uncover more intrinsic spoofing traces. However, this approach presents more risk of misalignment. We identify two main types of misalignment: (1) \textbf{Intra-domain modality misalignment}, where the importance of each modality varies across different attacks. For instance, certain modalities (e.g., Depth) may be non-defensive against specific attacks (e.g., 3D mask), indicating that each modality has unique strengths and weaknesses in countering particular attacks. Consequently, simple fusion strategies may fall short. (2) \textbf{Inter-domain modality misalignment}, where the introduction of additional modalities exacerbates domain shifts, potentially overshadowing the benefits of complementary fusion. To tackle (1), we propose a alignment module between modalities based on mutual information, which adaptively enhances favorable modalities while suppressing unfavorable ones. To address (2), we employ a dual alignment optimization method that aligns both sub-domain hyperplanes and modality angle margins, thereby mitigating domain gaps. Our method, dubbed \textbf{D}ual \textbf{A}lignment of \textbf{D}omain and \textbf{M}odality (DADM), achieves state-of-the-art performance in extensive experiments across four challenging protocols demonstrating its robustness in multi-modal domain generalization scenarios. The codes will be released soon.

cs.CV↗

arXiv2025

Transferable Adversarial Attacks on SAM and Its Downstream Models

The utilization of large foundational models has a dilemma: while fine-tuning downstream tasks from them holds promise for making use of the well-generalized knowledge in practical applications, their open accessibility also poses threats of adverse usage. This paper, for the first time, explores the feasibility of adversarial attacking various downstream models fine-tuned from the segment anything model (SAM), by solely utilizing the information from the open-sourced SAM. In contrast to prevailing transfer-based adversarial attacks, we demonstrate the existence of adversarial dangers even without accessing the downstream task and dataset to train a similar surrogate model. To enhance the effectiveness of the adversarial attack towards models fine-tuned on unknown datasets, we propose a universal meta-initialization (UMI) algorithm to extract the intrinsic vulnerability inherent in the foundation model, which is then utilized as the prior knowledge to guide the generation of adversarial perturbations. Moreover, by formulating the gradient difference in the attacking process between the open-sourced SAM and its fine-tuned downstream models, we theoretically demonstrate that a deviation occurs in the adversarial update direction by directly maximizing the distance of encoded feature embeddings in the open-sourced SAM. Consequently, we propose a gradient robust loss that simulates the associated uncertainty with gradient-based noise augmentation to enhance the robustness of generated adversarial examples (AEs) towards this deviation, thus improving the transferability. Extensive experiments demonstrate the effectiveness of the proposed universal meta-initialized and gradient robust adversarial attack (UMI-GRAT) toward SAMs and their downstream models. Code is available at https://github.com/xiasong0501/GRAT.

cs.LG↗

arXiv2025

Towards Model Resistant to Transferable Adversarial Examples via Trigger Activation

Adversarial examples, characterized by imperceptible perturbations, pose significant threats to deep neural networks by misleading their predictions. A critical aspect of these examples is their transferability, allowing them to deceive {unseen} models in black-box scenarios. Despite the widespread exploration of defense methods, including those on transferability, they show limitations: inefficient deployment, ineffective defense, and degraded performance on clean images. In this work, we introduce a novel training paradigm aimed at enhancing robustness against transferable adversarial examples (TAEs) in a more efficient and effective way. We propose a model that exhibits random guessing behavior when presented with clean data $\boldsymbol{x}$ as input, and generates accurate predictions when with triggered data $\boldsymbol{x}+\boldsymbolτ$. Importantly, the trigger $\boldsymbolτ$ remains constant for all data instances. We refer to these models as \textbf{models with trigger activation}. We are surprised to find that these models exhibit certain robustness against TAEs. Through the consideration of first-order gradients, we provide a theoretical analysis of this robustness. Moreover, through the joint optimization of the learnable trigger and the model, we achieve improved robustness to transferable attacks. Extensive experiments conducted across diverse datasets, evaluating a variety of attacking methods, underscore the effectiveness and superiority of our approach.

cs.CR↗

arXiv2025

AdaMHF: Adaptive Multimodal Hierarchical Fusion for Survival Prediction

The integration of pathologic images and genomic data for survival analysis has gained increasing attention with advances in multimodal learning. However, current methods often ignore biological characteristics, such as heterogeneity and sparsity, both within and across modalities, ultimately limiting their adaptability to clinical practice. To address these challenges, we propose AdaMHF: Adaptive Multimodal Hierarchical Fusion, a framework designed for efficient, comprehensive, and tailored feature extraction and fusion. AdaMHF is specifically adapted to the uniqueness of medical data, enabling accurate predictions with minimal resource consumption, even under challenging scenarios with missing modalities. Initially, AdaMHF employs an experts expansion and residual structure to activate specialized experts for extracting heterogeneous and sparse features. Extracted tokens undergo refinement via selection and aggregation, reducing the weight of non-dominant features while preserving comprehensive information. Subsequently, the encoded features are hierarchically fused, allowing multi-grained interactions across modalities to be captured. Furthermore, we introduce a survival prediction benchmark designed to resolve scenarios with missing modalities, mirroring real-world clinical conditions. Extensive experiments on TCGA datasets demonstrate that AdaMHF surpasses current state-of-the-art (SOTA) methods, showcasing exceptional performance in both complete and incomplete modality settings.

cs.CV↗

arXiv2025

Dynamic Analysis and Adaptive Discriminator for Fake News Detection

In current web environment, fake news spreads rapidly across online social networks, posing serious threats to society. Existing multimodal fake news detection methods can generally be classified into knowledge-based and semantic-based approaches. However, these methods are heavily rely on human expertise and feedback, lacking flexibility. To address this challenge, we propose a Dynamic Analysis and Adaptive Discriminator (DAAD) approach for fake news detection. For knowledge-based methods, we introduce the Monte Carlo Tree Search algorithm to leverage the self-reflective capabilities of large language models (LLMs) for prompt optimization, providing richer, domain-specific details and guidance to the LLMs, while enabling more flexible integration of LLM comment on news content. For semantic-based methods, we define four typical deceit patterns: emotional exaggeration, logical inconsistency, image manipulation, and semantic inconsistency, to reveal the mechanisms behind fake news creation. To detect these patterns, we carefully design four discriminators and expand them in depth and breadth, using the soft-routing mechanism to explore optimal detection models. Experimental results on three real-world datasets demonstrate the superiority of our approach. The code will be available at: https://github.com/SuXinqi/DAAD.

cs.AI↗

arXiv2025

Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable Trigger

No-Reference Image Quality Assessment (NR-IQA), responsible for assessing the quality of a single input image without using any reference, plays a critical role in evaluating and optimizing computer vision systems, e.g., low-light enhancement. Recent research indicates that NR-IQA models are susceptible to adversarial attacks, which can significantly alter predicted scores with visually imperceptible perturbations. Despite revealing vulnerabilities, these attack methods have limitations, including high computational demands, untargeted manipulation, limited practical utility in white-box scenarios, and reduced effectiveness in black-box scenarios. To address these challenges, we shift our focus to another significant threat and present a novel poisoning-based backdoor attack against NR-IQA (BAIQA), allowing the attacker to manipulate the IQA model's output to any desired target value by simply adjusting a scaling coefficient $α$ for the trigger. We propose to inject the trigger in the discrete cosine transform (DCT) domain to improve the local invariance of the trigger for countering trigger diminishment in NR-IQA models due to widely adopted data augmentations. Furthermore, the universal adversarial perturbations (UAP) in the DCT space are designed as the trigger, to increase IQA model susceptibility to manipulation and improve attack effectiveness. In addition to the heuristic method for poison-label BAIQA (P-BAIQA), we explore the design of clean-label BAIQA (C-BAIQA), focusing on $α$ sampling and image data refinement, driven by theoretical insights we reveal. Extensive experiments on diverse datasets and various NR-IQA models demonstrate the effectiveness of our attacks. Code can be found at https://github.com/yuyi-sd/BAIQA.

cs.CV↗

arXiv2024

BIG-MoE: Bypass Isolated Gating MoE for Generalized Multimodal Face Anti-Spoofing

In the domain of facial recognition security, multimodal Face Anti-Spoofing (FAS) is essential for countering presentation attacks. However, existing technologies encounter challenges due to modality biases and imbalances, as well as domain shifts. Our research introduces a Mixture of Experts (MoE) model to address these issues effectively. We identified three limitations in traditional MoE approaches to multimodal FAS: (1) Coarse-grained experts' inability to capture nuanced spoofing indicators; (2) Gated networks' susceptibility to input noise affecting decision-making; (3) MoE's sensitivity to prompt tokens leading to overfitting with conventional learning methods. To mitigate these, we propose the Bypass Isolated Gating MoE (BIG-MoE) framework, featuring: (1) Fine-grained experts for enhanced detection of subtle spoofing cues; (2) An isolation gating mechanism to counteract input noise; (3) A novel differential convolutional prompt bypass enriching the gating network with critical local features, thereby improving perceptual capabilities. Extensive experiments on four benchmark datasets demonstrate significant generalization performance improvement in multimodal FAS task. The code is released at https://github.com/murInJ/BIG-MoE.

cs.CV↗

arXiv2024

EPE-P: Evidence-based Parameter-efficient Prompting for Multimodal Learning with Missing Modalities

Missing modalities are a common challenge in real-world multimodal learning scenarios, occurring during both training and testing. Existing methods for managing missing modalities often require the design of separate prompts for each modality or missing case, leading to complex designs and a substantial increase in the number of parameters to be learned. As the number of modalities grows, these methods become increasingly inefficient due to parameter redundancy. To address these issues, we propose Evidence-based Parameter-Efficient Prompting (EPE-P), a novel and parameter-efficient method for pretrained multimodal networks. Our approach introduces a streamlined design that integrates prompting information across different modalities, reducing complexity and mitigating redundant parameters. Furthermore, we propose an Evidence-based Loss function to better handle the uncertainty associated with missing modalities, improving the model's decision-making. Our experiments demonstrate that EPE-P outperforms existing prompting-based methods in terms of both effectiveness and efficiency. The code is released at https://github.com/Boris-Jobs/EPE-P_MLLMs-Robustness.

cs.CV↗

arXiv2024

Three approaches to a categorical Torelli theorem for cubic threefolds of non-Eckardt type via the equivariant Kuznetsov components

Let $Y$ be a cubic threefold with a non-Eckardt type involution $τ$. Our first main result is that the $τ$-equivariant category of the Kuznetsov component $\mathcal{K}u_{\mathbb{Z}_2}(Y)$ determines the isomorphism class of $Y$ for general $(Y,τ)$. We shall prove this categorical Torelli theorem via three approaches: a noncommutative Hodge theoretical one (using a generalization of the intermediate Jacobian construction due to Alexander Perry), a Bridgeland moduli theoretical one (using equivariant stability conditions), and a Chow theoretical one (using some techniques in [kuznetsovnonclodedfield2021]).The remaining part of the paper is devoted to proving an equivariant infinitesimal categorical Torelli for non-Eckardt cubic threefolds $(Y,τ)$. To accomplish it, we prove a compatibility theorem on the algebra structures of the Hochschild cohomology of the bounded derived category $D^b(X)$ of a smooth projective variety $X$ and on the Hochschild cohomology of a semi-orthogonal component of $D^b(X)$. Another key ingredient is a generalization of a result in [macri2009infinitesima] which shows that the twisted Hochschild-Kostant-Rosenberg isomorphism is compatible with the actions on the Hochschild cohomology and on the singular cohomology induced by an automorphism of $X$. In appendix, we prove an equivariant categorical Torelli theorem for arbitrary cubic threefold with a geometric involution under a natural assumption.

math.AG↗

arXiv2024

Kuznetsov's Fano threefold conjecture via Hochschild-Serre algebra

Let $Y$ be a smooth quartic double solid regarded as a degree 4 hypersurface of the weighted projective space $\mathbb{P}(1,1,1,1,2)$. We study the multiplication of Hochschild-Serre algebra of its Kuznetsov component $\mathcal{K}u(Y)$, via matrix factorization. As an application, we give a new disproof of Kuznetsov's Fano threefold conjecture.

math.AG↗

arXiv2024

IVHS via Kuznetsov components and categorical Torelli theorems for weighted hypersurfaces

We study the categorical Torelli theorem for smooth (weighted) hypersurfaces in (weighted) projective spaces via the Hochschild--Serre algebra of its Kuznetsov component. In the first part of the paper, we show that a natural graded subalgebra of the Hochschild--Serre algebra of the Kuznetsov component of a degree $d$ weighted hypersurface in $\mathbb{P}(a_0,\ldots,a_n)$ reconstructs the graded subalgebra of the Jacobian ring generated by the degree $t:=\mathrm{gcd}(d,Σ_{i=0}^na_i)$ piece under mild assumptions. Using results of Donagi and Cox--Green, this gives a categorical Torelli theorem for most smooth hypersurfaces $Y$ of degree $d \le n$ in $\mathbb{P}^n$ such that $d$ does not divide $n+1$ (the exception being the cases of the form $(d,n) = (4, 4k + 2)$, for which a result of Voisin lets us deduce a generic categorical Torelli theorem when $k \ge 150$). Next, we show that the Jacobian ring of the Veronese double cone can be reconstructed from its graded subalgebra of even degree, thus proving a categorical Torelli theorem for the Veronese double cone. In the second part, we rebuild the infinitesimal Variation of Hodge structures of a series of (weighted) hypersurfaces from their Kuznetsov components via the Hochschild--Serre algebra. As a result, we prove categorical Torelli theorems for two classes of (weighted) hypersurfaces: $(1):$ Generalized Veronese double cone; $(2):$ Certain $k$-sheeted covering of $\mathbb{P}^n$, when they are generic. Then, we prove a refined categorical Torelli theorem for a Fano variety whose Kuznetsov component is a Calabi--Yau category of dimension $2m+1$. Finally, we prove the actual categorical Torelli theorem for generalized Veronese double cone and $k$-sheeted covering of $\mathbb{P}^n$.

math.AG↗

arXiv2024

DDAP: Dual-Domain Anti-Personalization against Text-to-Image Diffusion Models

Diffusion-based personalized visual content generation technologies have achieved significant breakthroughs, allowing for the creation of specific objects by just learning from a few reference photos. However, when misused to fabricate fake news or unsettling content targeting individuals, these technologies could cause considerable societal harm. To address this problem, current methods generate adversarial samples by adversarially maximizing the training loss, thereby disrupting the output of any personalized generation model trained with these samples. However, the existing methods fail to achieve effective defense and maintain stealthiness, as they overlook the intrinsic properties of diffusion models. In this paper, we introduce a novel Dual-Domain Anti-Personalization framework (DDAP). Specifically, we have developed Spatial Perturbation Learning (SPL) by exploiting the fixed and perturbation-sensitive nature of the image encoder in personalized generation. Subsequently, we have designed a Frequency Perturbation Learning (FPL) method that utilizes the characteristics of diffusion models in the frequency domain. The SPL disrupts the overall texture of the generated images, while the FPL focuses on image details. By alternating between these two methods, we construct the DDAP framework, effectively harnessing the strengths of both domains. To further enhance the visual quality of the adversarial samples, we design a localization module to accurately capture attentive areas while ensuring the effectiveness of the attack and avoiding unnecessary disturbances in the background. Extensive experiments on facial benchmarks have shown that the proposed DDAP enhances the disruption of personalized generation models while also maintaining high quality in adversarial samples, making it more effective in protecting privacy in practical applications.

cs.CV↗

arXiv2024

Serre algebra, matrix factorization and categorical Torelli theorem for hypersurfaces

Let $X$ be a smooth Fano variety. We attach a bi-graded associative algebra $\mathrm{HS}(\mathcal{K}u(X))=\bigoplus_{i,j\in \mathbb{Z}} \mathrm{Hom}(\mathrm{Id},S_{\mathcal{K}u(X)}^{i}[j])$ to the Kuznetsov component $\mathcal{K}u(X)$ whenever it is defined. Then we construct a natural sub-algebra of $\mathrm{HS}(\mathcal{K}u(X))$ when $X$ is a Fano hypersurface and establish its relation with Jacobian ring $\mathrm{Jac}(X)$. As an application, we prove a categorical Torelli theorem for Fano hypersurface $X\subset\mathbb{P}^n(n\geq 2)$ of degree $d$ if $\mathrm{gcd}(n+1,d)=1.$ In addition, we give a new proof of the $[Pir22, Theorem 1.2]$ using a similar idea.

math.AG↗

arXiv2024

Exposing Image Splicing Traces in Scientific Publications via Uncertainty-guided Refinement

Recently, a surge in scientific publications suspected of image manipulation has led to numerous retractions, bringing the issue of image integrity into sharp focus. Although research on forensic detectors for image plagiarism and image synthesis exists, the detection of image splicing traces in scientific publications remains unexplored. Compared to image duplication and synthesis, image splicing detection is more challenging due to the lack of reference images and the typically small tampered areas. Furthermore, disruptive factors in scientific images, such as artifacts from digital compression, abnormal patterns, and noise from physical operations, present misleading features like splicing traces, significantly increasing the difficulty of this task. Moreover, the scarcity of high-quality datasets of spliced scientific images limits potential advancements. In this work, we propose an Uncertainty-guided Refinement Network (URN) to mitigate the impact of these disruptive factors. Our URN can explicitly suppress the propagation of unreliable information flow caused by disruptive factors between regions, thus obtaining robust splicing features. Additionally, the URN is designed to concentrate improvements in uncertain prediction areas during the decoding phase. We also construct a dataset for image splicing detection (SciSp) containing 1,290 spliced images. Compared to existing datasets, SciSp includes the largest number of spliced images and the most diverse sources. Comprehensive experiments conducted on three benchmark datasets demonstrate the superiority of our approach. We also validate the URN's generalisability in resisting cross-dataset domain shifts and its robustness against various post-processing techniques, including advanced deep-learning-based inpainting.

cs.CV↗

arXiv2024

Safeguarding Medical Image Segmentation Datasets against Unauthorized Training via Contour- and Texture-Aware Perturbations

The widespread availability of publicly accessible medical images has significantly propelled advancements in various research and clinical fields. Nonetheless, concerns regarding unauthorized training of AI systems for commercial purposes and the duties of patient privacy protection have led numerous institutions to hesitate to share their images. This is particularly true for medical image segmentation (MIS) datasets, where the processes of collection and fine-grained annotation are time-intensive and laborious. Recently, Unlearnable Examples (UEs) methods have shown the potential to protect images by adding invisible shortcuts. These shortcuts can prevent unauthorized deep neural networks from generalizing. However, existing UEs are designed for natural image classification and fail to protect MIS datasets imperceptibly as their protective perturbations are less learnable than important prior knowledge in MIS, e.g., contour and texture features. To this end, we propose an Unlearnable Medical image generation method, termed UMed. UMed integrates the prior knowledge of MIS by injecting contour- and texture-aware perturbations to protect images. Given that our target is to only poison features critical to MIS, UMed requires only minimal perturbations within the ROI and its contour to achieve greater imperceptibility (average PSNR is 50.03) and protective performance (clean average DSC degrades from 82.18% to 6.80%).

eess.IV↗