Searcharxiv⌕ Search

arXiv subjects

Bin Chen

Publications and source records attributed to Bin Chen.

At least 325 records · Page 18Linked to original sources
arXiv2024

CLIP-Guided Generative Networks for Transferable Targeted Adversarial Attacks

Transferable targeted adversarial attacks aim to mislead models into outputting adversary-specified predictions in black-box scenarios. Recent studies have introduced \textit{single-target} generative attacks that train a generator for each target class to generate highly transferable perturbations, resulting in substantial computational overhead when handling multiple classes. \textit{Multi-target} attacks address this by training only one class-conditional generator for multiple classes. However, the generator simply uses class labels as conditions, failing to leverage the rich semantic information of the target class. To this end, we design a \textbf{C}LIP-guided \textbf{G}enerative \textbf{N}etwork with \textbf{C}ross-attention modules (CGNC) to enhance multi-target attacks by incorporating textual knowledge of CLIP into the generator. Extensive experiments demonstrate that CGNC yields significant improvements over previous multi-target generative attacks, e.g., a 21.46\% improvement in success rate from ResNet-152 to DenseNet-121. Moreover, we propose a masked fine-tuning mechanism to further strengthen our method in attacking a single class, which surpasses existing single-target methods.

cs.CV↗
arXiv2024

A Closer Look at GAN Priors: Exploiting Intermediate Features for Enhanced Model Inversion Attacks

Model Inversion (MI) attacks aim to reconstruct privacy-sensitive training data from released models by utilizing output information, raising extensive concerns about the security of Deep Neural Networks (DNNs). Recent advances in generative adversarial networks (GANs) have contributed significantly to the improved performance of MI attacks due to their powerful ability to generate realistic images with high fidelity and appropriate semantics. However, previous MI attacks have solely disclosed private information in the latent space of GAN priors, limiting their semantic extraction and transferability across multiple target models and datasets. To address this challenge, we propose a novel method, Intermediate Features enhanced Generative Model Inversion (IF-GMI), which disassembles the GAN structure and exploits features between intermediate blocks. This allows us to extend the optimization space from latent code to intermediate features with enhanced expressive capabilities. To prevent GAN priors from generating unrealistic images, we apply a L1 ball constraint to the optimization process. Experiments on multiple benchmarks demonstrate that our method significantly outperforms previous approaches and achieves state-of-the-art results under various settings, especially in the out-of-distribution (OOD) scenario. Our code is available at: https://github.com/final-solution/IF-GMI

cs.CV↗
arXiv2024

OV-DQUO: Open-Vocabulary DETR with Denoising Text Query Training and Open-World Unknown Objects Supervision

Open-vocabulary detection aims to detect objects from novel categories beyond the base categories on which the detector is trained. However, existing open-vocabulary detectors trained on base category data tend to assign higher confidence to trained categories and confuse novel categories with the background. To resolve this, we propose OV-DQUO, an \textbf{O}pen-\textbf{V}ocabulary DETR with \textbf{D}enoising text \textbf{Q}uery training and open-world \textbf{U}nknown \textbf{O}bjects supervision. Specifically, we introduce a wildcard matching method. This method enables the detector to learn from pairs of unknown objects recognized by the open-world detector and text embeddings with general semantics, mitigating the confidence bias between base and novel categories. Additionally, we propose a denoising text query training strategy. It synthesizes foreground and background query-box pairs from open-world unknown objects to train the detector through contrastive learning, enhancing its ability to distinguish novel objects from the background. We conducted extensive experiments on the challenging OV-COCO and OV-LVIS benchmarks, achieving new state-of-the-art results of 45.6 AP50 and 39.3 mAP on novel categories respectively, without the need for additional training data. Models and code are released at \url{https://github.com/xiaomoguhz/OV-DQUO}

cs.CV↗
arXiv2024

Photon emissions from Kerr equatorial geodesic orbits

We consider the light emitters moving freely along the geodesics on the equatorial plane near a Kerr black hole and study the observability of these emitters. To do so, we assume these emitters emit the photons isotropically and monochromatically, and we compute the photon escaping probability (PEP) and the maximum observable blueshift (MOB) of the photons that reach infinity. We obtain numerical results of PEP and MOB for the emitters along various geodesic orbits, which exhibit distinct features for the trajectories of different classes. We exhaustively investigate the effects of the emitters' motion on the PEP and MOB. In particular, we find that the plunging emitters approaching the unstable circular orbits could have very good observability, before fading away suddenly. This interesting observational feature becomes more significant for the high-energy emitters near a high-spin black hole. As the radiatively-inefficient accretion flow may consist of such plunging emitters, the present work could be of great relevance to the astrophysical observations.

gr-qc↗
arXiv2024

Self-Supervised Scalable Deep Compressed Sensing

Compressed sensing (CS) is a promising tool for reducing sampling costs. Current deep neural network (NN)-based CS methods face the challenges of collecting labeled measurement-ground truth (GT) data and generalizing to real applications. This paper proposes a novel $\mathbf{S}$elf-supervised s$\mathbf{C}$alable deep CS method, comprising a deep $\mathbf{L}$earning scheme called $\mathbf{SCL}$ and a family of $\mathbf{Net}$works named $\mathbf{SCNet}$, which does not require GT and can handle arbitrary sampling ratios and matrices once trained on a partial measurement set. Our SCL contains a dual-domain loss and a four-stage recovery strategy. The former encourages a cross-consistency on two measurement parts and a sampling-reconstruction cycle-consistency regarding arbitrary ratios and matrices to maximize data/information utilization. The latter can progressively leverage common signal prior in external measurements and internal characteristics of test samples and learned NNs to improve accuracy. SCNet combines both the explicit guidance from optimization algorithms with implicit regularization from advanced NN blocks to learn a collaborative signal representation. Our theoretical analyses and experiments on simulated and real captured data, covering 1-/2-/3-D natural and scientific signals, demonstrate the effectiveness, superior performance, flexibility, and generalization ability of our method over existing self-supervised methods and its significant potential in competing against state-of-the-art supervised methods. Code is available at https://github.com/Guaishou74851/SCNet.

eess.SP↗
arXiv2024

On self-dual Carrollian conformal nonlinear electrodynamics

In this work, we study the duality symmetry group of Carrollian (nonlinear) electrodynamics and propose a family of Carrollian ModMax theories, which are invariant under Carrollian $\text{SO}(2)$ electromagnetic (EM) duality transformations and conformal transformation. We define the Carrollian $\text{SO}(2)$ EM transformations, with the help of Hodge duality in Carrollian geometry, then we rederive the Gaillard-Zumino consistency condition for EM duality of Carrollian nonlinear electrodynamics. Together with the traceless condition for the energy-momentum tensor, we are able to determine the Lagrangian of the Carrollian ModMax theories among pure electrodynamics. We furthermore study their behaviors under the $\sqrt{T\bar{T}}$ deformation flow, and show that these theories deform to each other and may reach two endpoints under the flow, with one of the endpoint being the Carrollian Maxwell theory. As a byproduct, we construct a family of two-dimensional Carrollian ModMax-like multiple scalar theories, which are closed under the $\sqrt{T\bar{T}}$ flow and may flow to a BMS free multi-scalar model.

hep-th↗
arXiv2024

Correlation Function Of Thin-Shell Operators

In this study, we explore the correlation functions of thin-shell operators, represented semiclassically by a homogeneous, thin interface of dust particles. Employing the monodromy method, we successfully compute the contribution from the Virasoro vacuum block and present the monodromy equation in a closed form without assuming the probe limit. Although an analytical solution to the monodromy equation remains difficult, we demonstrate that it is perturbatively solvable within specific limits, including the probe, the heavy-shell, and the early-time limits. Moreover, we compare our results with gravitational calculations and find precise agreement. We strengthen our findings by proving that the thermal correlation functions in gravity, after an inverse Laplace transformation, satisfy the field theory's monodromy equation. Additionally, we identify an infinite series of unphysical solutions to the monodromy equation and discuss their potential geometrical duals.

hep-th↗
arXiv2024

GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolution

Implicit neural representations (INRs) have significantly advanced the field of arbitrary-scale super-resolution (ASSR) of images. Most existing INR-based ASSR networks first extract features from the given low-resolution image using an encoder, and then render the super-resolved result via a multi-layer perceptron decoder. Although these approaches have shown promising results, their performance is constrained by the limited representation ability of discrete latent codes in the encoded features. In this paper, we propose a novel ASSR method named GaussianSR that overcomes this limitation through 2D Gaussian Splatting (2DGS). Unlike traditional methods that treat pixels as discrete points, GaussianSR represents each pixel as a continuous Gaussian field. The encoded features are simultaneously refined and upsampled by rendering the mutually stacked Gaussian fields. As a result, long-range dependencies are established to enhance representation ability. In addition, a classifier is developed to dynamically assign Gaussian kernels to all pixels to further improve flexibility. All components of GaussianSR (i.e., encoder, classifier, Gaussian kernels, and decoder) are jointly learned end-to-end. Experiments demonstrate that GaussianSR achieves superior ASSR performance with fewer parameters than existing methods while enjoying interpretable and content-aware feature aggregations.

cs.CV↗
arXiv2024

Energetic Electrons Accelerated and Trapped in a Magnetic Bottle above a Solar Flare Arcade

Where and how flares efficiently accelerate charged particles remains an unresolved question. Recent studies revealed that a "magnetic bottle" structure, which forms near the bottom of a large-scale reconnection current sheet above the flare arcade, is an excellent candidate for confining and accelerating charged particles. However, further understanding its role requires linking the various observational signatures to the underlying coupled plasma and particle processes. Here we present the first study combining multiwavelength observations with data-informed macroscopic magnetohydrodynamics and particle modeling in a realistic eruptive flare geometry. The presence of an above-the-loop-top magnetic bottle structure is strongly supported by the observations, which feature not only a local minimum of magnetic field strength but also abruptly slowing down plasma downflows. It also coincides with a compact hard X-ray source and an extended microwave source that bestrides above the flare arcade. Spatially resolved spectral analysis suggests that nonthermal electrons are highly concentrated in this region. Our model returns synthetic emission signatures that are well matched to the observations. The results suggest that the energetic electrons are strongly trapped in the magnetic bottle region due to turbulence, with only a small fraction managing to escape. The electrons are primarily accelerated by plasma compression and facilitated by a fast-mode termination shock via the Fermi mechanism. Our results provide concrete support for the magnetic bottle as the primary electron acceleration site in eruptive solar flares. They also offer new insights into understanding the previously reported small population of flare-accelerated electrons entering interplanetary space.

astro-ph.SR↗
arXiv2024

A Joint Approach to Local Updating and Gradient Compression for Efficient Asynchronous Federated Learning

Asynchronous Federated Learning (AFL) confronts inherent challenges arising from the heterogeneity of devices (e.g., their computation capacities) and low-bandwidth environments, both potentially causing stale model updates (e.g., local gradients) for global aggregation. Traditional approaches mitigating the staleness of updates typically focus on either adjusting the local updating or gradient compression, but not both. Recognizing this gap, we introduce a novel approach that synergizes local updating with gradient compression. Our research begins by examining the interplay between local updating frequency and gradient compression rate, and their collective impact on convergence speed. The theoretical upper bound shows that the local updating frequency and gradient compression rate of each device are jointly determined by its computing power, communication capabilities and other factors. Building on this foundation, we propose an AFL framework called FedLuck that adaptively optimizes both local update frequency and gradient compression rates. Experiments on image classification and speech recognization show that FedLuck reduces communication consumption by 56% and training time by 55% on average, achieving competitive performance in heterogeneous and low-bandwidth scenarios compared to the baselines.

cs.DC↗
arXiv2024

An expanding curvature flow and the (p,q)-Christoffel-Minkowski problems

The present paper introduces a new class of geometric measures, the k-th (p,q)-mixed curvature measures, and a natural correspondence-(p,q)-Christoffel-Minkowski problem is proposed. The (p,q)-Christoffel-Minkowski problem posed here can be regarded as a natural generalization of the L_p Christoffel-Minkowski problem and Lp dual Minkowski problem. We investigate and arrive at the existence of smooth solution to the (p,q)-Christoffel-Minkowski problem by a type of expanding curvature flow. Furthermore, the uniqueness result of solutions to the (p,q)-Christoffel-Minkowski problem shall be discussed.

math.DG↗
arXiv2024

Micropores can enhance intrinsic fracture energy of hydrogels

It is widely known that hydrogels, a class of soft materials made of a polymer chain network, are prone to fatigue failure. To understand the underlying mechanism, here we simulate polymer scission and fatigue initiation in the vicinity of a crack tip in a two-dimensional chain network. For a network without pores, our findings reveal that polymer scission can take place across multiple layers of chains, rather than just a single layer as assumed in the classical Lake-Thomas theory, in consistency with previus studies. For a network with a high density of micropores, our results demonstrate that the pores can substantially enhance the intrinsic fracture energy of the network in direct proportion to the pore size. The underlying mechanism is attributed to pore-pore interactions which lead to a relatively uniform distribution of cohesive energy ahead of the crack tip. Our model suggests that micropores could be a promising strategy for improving the intrinsic fracture energy of hydrogels and that natural porous tissues may have evolved for enhanced fatigue resistance.

cond-mat.soft↗
arXiv2024

MEAT: Median-Ensemble Adversarial Training for Improving Robustness and Generalization

Self-ensemble adversarial training methods improve model robustness by ensembling models at different training epochs, such as model weight averaging (WA). However, previous research has shown that self-ensemble defense methods in adversarial training (AT) still suffer from robust overfitting, which severely affects the generalization performance. Empirically, in the late phases of training, the AT becomes more overfitting to the extent that the individuals for weight averaging also suffer from overfitting and produce anomalous weight values, which causes the self-ensemble model to continue to undergo robust overfitting due to the failure in removing the weight anomalies. To solve this problem, we aim to tackle the influence of outliers in the weight space in this work and propose an easy-to-operate and effective Median-Ensemble Adversarial Training (MEAT) method to solve the robust overfitting phenomenon existing in self-ensemble defense from the source by searching for the median of the historical model weights. Experimental results show that MEAT achieves the best robustness against the powerful AutoAttack and can effectively allievate the robust overfitting. We further demonstrate that most defense methods can improve robust generalization and robustness by combining with MEAT.

cs.LG↗
arXiv2024

An Efficient Implicit Neural Representation Image Codec Based on Mixed Autoregressive Model for Low-Complexity Decoding

Displaying high-quality images on edge devices, such as augmented reality devices, is essential for enhancing the user experience. However, these devices often face power consumption and computing resource limitations, making it challenging to apply many deep learning-based image compression algorithms in this field. Implicit Neural Representation (INR) for image compression is an emerging technology that offers two key benefits compared to cutting-edge autoencoder models: low computational complexity and parameter-free decoding. It also outperforms many traditional and early neural compression methods in terms of quality. In this study, we introduce a new Mixed AutoRegressive Model (MARM) to significantly reduce the decoding time for the current INR codec, along with a new synthesis network to enhance reconstruction quality. MARM includes our proposed AutoRegressive Upsampler (ARU) blocks, which are highly computationally efficient, and ARM from previous work to balance decoding time and reconstruction quality. We also propose enhancing ARU's performance using a checkerboard two-stage decoding strategy. Moreover, the ratio of different modules can be adjusted to maintain a balance between quality and speed. Comprehensive experiments demonstrate that our method significantly improves computational efficiency while preserving image quality. With different parameter settings, our method can achieve over a magnitude acceleration in decoding time without industrial level optimization, or achieve state-of-the-art reconstruction quality compared with other INR codecs. To the best of our knowledge, our method is the first INR-based codec comparable with Hyperprior in both decoding speed and quality while maintaining low complexity.

eess.IV↗
arXiv2024

MambaVC: Learned Visual Compression with Selective State Spaces

Learned visual compression is an important and active task in multimedia. Existing approaches have explored various CNN- and Transformer-based designs to model content distribution and eliminate redundancy, where balancing efficacy (i.e., rate-distortion trade-off) and efficiency remains a challenge. Recently, state-space models (SSMs) have shown promise due to their long-range modeling capacity and efficiency. Inspired by this, we take the first step to explore SSMs for visual compression. We introduce MambaVC, a simple, strong and efficient compression network based on SSM. MambaVC develops a visual state space (VSS) block with a 2D selective scanning (2DSS) module as the nonlinear activation function after each downsampling, which helps to capture informative global contexts and enhances compression. On compression benchmark datasets, MambaVC achieves superior rate-distortion performance with lower computational and memory overheads. Specifically, it outperforms CNN and Transformer variants by 9.3% and 15.6% on Kodak, respectively, while reducing computation by 42% and 24%, and saving 12% and 71% of memory. MambaVC shows even greater improvements with high-resolution images, highlighting its potential and scalability in real-world applications. We also provide a comprehensive comparison of different network designs, underscoring MambaVC's advantages. Code is available at https://github.com/QinSY123/2024-MambaVC.

eess.IV↗
arXiv2024

Augmented Risk Prediction for the Onset of Alzheimer's Disease from Electronic Health Records with Large Language Models

Alzheimer's disease (AD) is the fifth-leading cause of death among Americans aged 65 and older. Screening and early detection of AD and related dementias (ADRD) are critical for timely intervention and for identifying clinical trial participants. The widespread adoption of electronic health records (EHRs) offers an important resource for developing ADRD screening tools such as machine learning based predictive models. Recent advancements in large language models (LLMs) demonstrate their unprecedented capability of encoding knowledge and performing reasoning, which offers them strong potential for enhancing risk prediction. This paper proposes a novel pipeline that augments risk prediction by leveraging the few-shot inference power of LLMs to make predictions on cases where traditional supervised learning methods (SLs) may not excel. Specifically, we develop a collaborative pipeline that combines SLs and LLMs via a confidence-driven decision-making mechanism, leveraging the strengths of SLs in clear-cut cases and LLMs in more complex scenarios. We evaluate this pipeline using a real-world EHR data warehouse from Oregon Health \& Science University (OHSU) Hospital, encompassing EHRs from over 2.5 million patients and more than 20 million patient encounters. Our results show that our proposed approach effectively combines the power of SLs and LLMs, offering significant improvements in predictive performance. This advancement holds promise for revolutionizing ADRD screening and early detection practices, with potential implications for better strategies of patient management and thus improving healthcare.

cs.AI↗