arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 973 records · Page 54Linked to original sources

arXiv2024

Seamless Website Fingerprinting in Multiple Environments

Website fingerprinting (WF) attacks identify the websites visited over anonymized connections by analyzing patterns in network traffic flows, such as packet sizes, directions, or interval times using a machine learning classifier. Previous studies showed WF attacks achieve high classification accuracy. However, several issues call into question whether existing WF approaches are realizable in practice and thus motivate a re-exploration. Due to Tor's performance issues and resulting poor browsing experience, the vast majority of users opt for Virtual Private Networking (VPN) despite VPNs weaker privacy protections. Many other past assumptions are increasingly unrealistic as web technology advances. Our work addresses several key limitations of prior art. First, we introduce a new approach that classifies entire websites rather than individual web pages. Site-level classification uses traffic from all site components, including advertisements, multimedia, and single-page applications. Second, our Convolutional Neural Network (CNN) uses only the jitter and size of 500 contiguous packets from any point in a TCP stream, in contrast to prior work requiring heuristics to find page boundaries. Our seamless approach makes eavesdropper attack models realistic. Using traces from a controlled browser, we show our CNN matches observed traffic to a website with over 90% accuracy. We found the training traffic quality is critical as classification accuracy is significantly reduced when the training data lacks variability in network location, performance, and clients' computational capability. We enhanced the base CNN's efficacy using domain adaptation, allowing it to discount irrelevant features, such as network location. Lastly, we evaluate several defensive strategies against seamless WF attacks.

cs.CR↗

arXiv2024

Overview of AI-Debater 2023: The Challenges of Argument Generation Tasks

In this paper we present the results of the AI-Debater 2023 Challenge held by the Chinese Conference on Affect Computing (CCAC 2023), and introduce the related datasets. We organize two tracks to handle the argumentative generation tasks in different scenarios, namely, Counter-Argument Generation (Track 1) and Claim-based Argument Generation (Track 2). Each track is equipped with its distinct dataset and baseline model respectively. In total, 32 competing teams register for the challenge, from which we received 11 successful submissions. In this paper, we will present the results of the challenge and a summary of the systems, highlighting commonalities and innovations among participating systems. Datasets and baseline models of the AI-Debater 2023 Challenge have been already released and can be accessed through the official website of the challenge.

cs.CL↗

arXiv2024

OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion

Open-vocabulary detection is a challenging task due to the requirement of detecting objects based on class names, including those not encountered during training. Existing methods have shown strong zero-shot detection capabilities through pre-training and pseudo-labeling on diverse large-scale datasets. However, these approaches encounter two main challenges: (i) how to effectively eliminate data noise from pseudo-labeling, and (ii) how to efficiently leverage the language-aware capability for region-level cross-modality fusion and alignment. To address these challenges, we propose a novel unified open-vocabulary detection method called OV-DINO, which is pre-trained on diverse large-scale datasets with language-aware selective fusion in a unified framework. Specifically, we introduce a Unified Data Integration (UniDI) pipeline to enable end-to-end training and eliminate noise from pseudo-label generation by unifying different data sources into detection-centric data format. In addition, we propose a Language-Aware Selective Fusion (LASF) module to enhance the cross-modality alignment through a language-aware query selection and fusion process. We evaluate the performance of the proposed OV-DINO on popular open-vocabulary detection benchmarks, achieving state-of-the-art results with an AP of 50.6% on the COCO benchmark and 40.1% on the LVIS benchmark in a zero-shot manner, demonstrating its strong generalization ability. Furthermore, the fine-tuned OV-DINO on COCO achieves 58.4% AP, outperforming many existing methods with the same backbone. The code for OV-DINO is available at https://github.com/wanghao9610/OV-DINO.

cs.CV↗

arXiv2024

Theoretical Study on the Structural and Thermodynamic Properties of U-He compounds under High Pressure

Uranium is considered as a very important nuclear energy material because of the huge amount of energy released. As the main products of spontaneous decay of uranium, helium is difficult to react with uranium for its chemical inertness. Therefore, bubbles will be formed inside uranium, which could greatly reduce the performance of uranium or cause the safety problems. Additionally, nuclear materials are usually operated in an environment of high-temperature and high-pressure, so it is necessary to figure out the exact state of helium inside uranium at extreme conditions. Here, we explored the structural stability of U-He system under high-pressure and high-temperature by using density functional theory calculations. Two metastable phases are found between 50 and 400 GPa: U4He with space group Fmmm and U6He with space group P-1. Both are metallic and adopt layered structures. Electron localization function calculation combined with charge density difference analysis indicate that there are covalent bonds between U and U atoms in both Fmmm-U4He and P-1-U6He. Compared with the elastic modulus of $α$-U, the addition of helium has certain influence on the mechanical properties of uranium. Besides, first-principles molecular dynamics simulations were carried out to study the dynamical behavior of Fmmm-U4He and P-1-U6He at high-temperature. It is found that Fmmm-U4He and P-1-U6He undergo one-dimensional superionic phase transitions at 150 GPa. Our study revealed exotic structure of U-He compounds beyond the form of bubble under high-pressure and high-temperature, that might be relevant to the performance and safety issue of nuclear materials at extreme conditions.

cond-mat.mtrl-sci↗

arXiv2024

First-principles study of structural and electronic properties of multiferroic oxide Mn3TeO6 under high pressure

Mn3TeO6 (MTO) has been experimentally found to adopt a P21/n structure under high pressure, which exhibits a significantly smaller band gap compared to the atmospheric R-3 phase. In this study, we systematically investigate the magnetism, structural phase transition and electronic properties of MTO under high pressure through first-principles calculations. Both R-3 and P21/n phases of MTO are antiferromagnetic at zero temperature. The R-3 phase transforms to the P21/n phase at 7.58 GPa, accompanied by a considerable volume collapse of about 6.47%. Employing the accurate method that combines DFT+U and G0W0, the calculated band gap of R-3 phase at zero pressure is very close to the experimental values, while that of the P21/n phase is significantly overestimated. The main reason for this difference is that the experimental study incorrectly used the Kubelka-Munk plot for the indirect band gap to obtain the band gap of the P21/n phase instead of the Kubelka-Munk plot for the direct band gap. Furthermore, our study reveals that the transition from the R-3 phase to the P21/n phase is accompanied by a slight reduction in the band gap.

cond-mat.mtrl-sci↗

arXiv2024

SkyMask: Attack-agnostic Robust Federated Learning with Fine-grained Learnable Masks

Federated Learning (FL) is becoming a popular paradigm for leveraging distributed data and preserving data privacy. However, due to the distributed characteristic, FL systems are vulnerable to Byzantine attacks that compromised clients attack the global model by uploading malicious model updates. With the development of layer-level and parameter-level fine-grained attacks, the attacks' stealthiness and effectiveness have been significantly improved. The existing defense mechanisms solely analyze the model-level statistics of individual model updates uploaded by clients to mitigate Byzantine attacks, which are ineffective against fine-grained attacks due to unawareness or overreaction. To address this problem, we propose SkyMask, a new attack-agnostic robust FL system that firstly leverages fine-grained learnable masks to identify malicious model updates at the parameter level. Specifically, the FL server freezes and multiplies the model updates uploaded by clients with the parameter-level masks, and trains the masks over a small clean dataset (i.e., root dataset) to learn the subtle difference between benign and malicious model updates in a high-dimension space. Our extensive experiments involve different models on three public datasets under state-of-the-art (SOTA) attacks, where the results show that SkyMask achieves up to 14% higher testing accuracy compared with SOTA defense strategies under the same attacks and successfully defends against attacks with malicious clients of a high fraction up to 80%. Code is available at https://github.com/KoalaYan/SkyMask.

cs.CR↗

arXiv2024

IPA-NeRF: Illusory Poisoning Attack Against Neural Radiance Fields

Neural Radiance Field (NeRF) represents a significant advancement in computer vision, offering implicit neural network-based scene representation and novel view synthesis capabilities. Its applications span diverse fields including robotics, urban mapping, autonomous navigation, virtual reality/augmented reality, etc., some of which are considered high-risk AI applications. However, despite its widespread adoption, the robustness and security of NeRF remain largely unexplored. In this study, we contribute to this area by introducing the Illusory Poisoning Attack against Neural Radiance Fields (IPA-NeRF). This attack involves embedding a hidden backdoor view into NeRF, allowing it to produce predetermined outputs, i.e. illusory, when presented with the specified backdoor view while maintaining normal performance with standard inputs. Our attack is specifically designed to deceive users or downstream models at a particular position while ensuring that any abnormalities in NeRF remain undetectable from other viewpoints. Experimental results demonstrate the effectiveness of our Illusory Poisoning Attack, successfully presenting the desired illusory on the specified viewpoint without impacting other views. Notably, we achieve this attack by introducing small perturbations solely to the training set. The code can be found at https://github.com/jiang-wenxiang/IPA-NeRF.

cs.CV↗

arXiv2024

RBAD: A Dataset and Benchmark for Retinal Vessels Branching Angle Detection

Detecting retinal image analysis, particularly the geometrical features of branching points, plays an essential role in diagnosing eye diseases. However, existing methods used for this purpose often are coarse-level and lack fine-grained analysis for efficient annotation. To mitigate these issues, this paper proposes a novel method for detecting retinal branching angles using a self-configured image processing technique. Additionally, we offer an open-source annotation tool and a benchmark dataset comprising 40 images annotated with retinal branching angles. Our methodology for retinal branching angle detection and calculation is detailed, followed by a benchmark analysis comparing our method with previous approaches. The results indicate that our method is robust under various conditions with high accuracy and efficiency, which offers a valuable instrument for ophthalmic research and clinical applications.

cs.CV↗

arXiv2024

Impact of evolving dark energy on the search for primordial gravitational waves

Recent data seem to suggest a preference for the evolving dark energy (DE). However, if the case is actually so, and not caused by unknown systematics in data, it might impact our understanding about our Universe in an anomalous way due to the shifts of some primary parameters. As an example, we present the search for the primordial gravitational waves, based on the evolving DE. The joint analysis of recent BICEP/Keck cosmic microwave background (CMB) B-mode polarization data with Planck18 CMB, DESI baryon acoustic oscillations and PantheonPlus data shows that the bestfit tensor-to-scalar ratio is $r_{0.05}\sim 0.01$, and the lower bound of $r_{0.05}$ is $\sim 2σ$ non-zero.

astro-ph.CO↗

arXiv2024

Parallel Ising Annealer via Gradient-based Hamiltonian Monte Carlo

Ising annealer is a promising quantum-inspired computing architecture for combinatorial optimization problems. In this paper, we introduce an Ising annealer based on the Hamiltonian Monte Carlo, which updates the variables of all dimensions in parallel. The main innovation is the fusion of an approximate gradient-based approach into the Ising annealer which introduces significant acceleration and allows a portable and scalable implementation on the commercial FPGA. Comprehensive simulation and hardware experiments show that the proposed Ising annealer has promising performance and scalability on all types of benchmark problems when compared to other Ising annealers including the state-of-the-art hardware. In particular, we have built a prototype annealer which solves Ising problems of both integer and fraction coefficients with up to 200 spins on a single low-cost FPGA board, whose performance is demonstrated to be better than the state-of-the-art quantum hardware D-Wave 2000Q and similar to the expensive coherent Ising machine. The sub-linear scalability of the annealer signifies its potential in solving challenging combinatorial optimization problems and evaluating the advantage of quantum hardware.

quant-ph↗

arXiv2024

Stochastic generalized Kolmogorov systems with small diffusion: II. Explicit approximations for periodic solutions in distribution

This paper is Part II of a two-part series on coexistence states study in stochastic generalized Kolmogorov systems under small diffusion. Part I provided a complete characterization for approximating invariant probability measures and density functions, while here, we focus on explicit approximations for periodic solutions in distribution. Two easily implementable methods are introduced: periodic normal approximation (PNOA) and periodic log-normal approximation (PLNA). These methods offer unified algorithms to calculate the mean and covariance matrix, and verify positive definiteness, without additional constraints like non-degenerate diffusion. Furthermore, we explore essential properties of the covariance matrix, particularly its connection under periodic and non-periodic drift coefficients. Our new approximation methods significantly relax the minimal criteria for positive definiteness of the solution of the discrete-type Lyapunov equation. Some numerical experiments are provided to support our theoretical results.

math.DS↗

arXiv2024

FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs

This report introduces FunAudioLLM, a model family designed to enhance natural voice interactions between humans and large language models (LLMs). At its core are two innovative models: SenseVoice, which handles multilingual speech recognition, emotion recognition, and audio event detection; and CosyVoice, which facilitates natural speech generation with control over multiple languages, timbre, speaking style, and speaker identity. SenseVoice-Small delivers exceptionally low-latency ASR for 5 languages, and SenseVoice-Large supports high-precision ASR for over 50 languages, while CosyVoice excels in multi-lingual voice generation, zero-shot in-context learning, cross-lingual voice cloning, and instruction-following capabilities. The models related to SenseVoice and CosyVoice have been open-sourced on Modelscope and Huggingface, along with the corresponding training, inference, and fine-tuning codes released on GitHub. By integrating these models with LLMs, FunAudioLLM enables applications such as speech-to-speech translation, emotional voice chat, interactive podcasts, and expressive audiobook narration, thereby pushing the boundaries of voice interaction technology. Demos are available at https://fun-audio-llm.github.io, and the code can be accessed at https://github.com/FunAudioLLM.

cs.SD↗

arXiv2024

Entropy Law: The Story Behind Data Compression and LLM Performance

Data is the cornerstone of large language models (LLMs), but not all data is useful for model learning. Carefully selected data can better elicit the capabilities of LLMs with much less computational overhead. Most methods concentrate on evaluating the quality of individual samples in data selection, while the combinatorial effects among samples are neglected. Even if each sample is of perfect quality, their combinations may be suboptimal in teaching LLMs due to their intrinsic homogeneity or contradiction. In this paper, we aim to uncover the underlying relationships between LLM performance and data selection. Inspired by the information compression nature of LLMs, we uncover an ``entropy law'' that connects LLM performance with data compression ratio and first-epoch training loss, which reflect the information redundancy of a dataset and the mastery of inherent knowledge encoded in this dataset, respectively. Through both theoretical deduction and empirical evaluation, we find that model performance is negatively correlated to the compression ratio of training data, which usually yields a lower training loss. Based on the findings of the entropy law, we propose a quite efficient and universal data selection method named \textbf{ZIP} for training LLMs, which aim to prioritize data subsets exhibiting a low compression ratio. Based on a multi-stage algorithm that selects diverse data in a greedy manner, we can obtain a good data subset with satisfactory diversity. Extensive experiments have been conducted to validate the entropy law and the superiority of ZIP across different LLM backbones and alignment stages. We also present an interesting application of entropy law that can detect potential performance risks at the beginning of model training.

cs.LG↗

arXiv2024

jetsimpy: A Highly Efficient Hydrodynamic Code for Gamma-ray Burst Afterglow

Gamma-ray burst (GRB) afterglows are emissions from ultrarelativistic blast waves produced by a narrow jet interacting with surrounding matter. Since the first multimessenger observation of a neutron star merger, hydrodynamic modeling of GRB afterglows for structured jets with smoothly varying angular energy distributions has gained increased interest. While the evolution of a jet is well described by self-similar solutions in both ultrarelativistic and Newtonian limits, modeling the transitional phase remains challenging. This is due to the nonlinear spreading of a narrow jet to a spherical configuration and the breakdown of self-similar solutions. Analytical models are limited in capturing these nonlinear effects, while relativistic hydrodynamic simulations are computationally expensive, which restricts the exploration of various initial conditions. In this work, we introduce a reduced hydrodynamic model that approximates the blast wave as an infinitely thin two-dimensional surface. Further assuming axial symmetry, this model simplifies the simulation to one dimension and drastically reduces the computational costs. We have compared our modeling to relativistic hydrodynamic simulations and semianalytic methods, and applied it to fit the light curve and flux centroid motion of GRB 170817A. These comparisons demonstrate good agreement and validate our approach. We have developed this method into a numerical tool, \texttt{jetsimpy}, which models the synchrotron GRB afterglow emission from a blast wave with arbitrary angular energy and Lorentz factor distribution. Although the code is built with GRB afterglow in mind, it applies to any relativistic jet. This tool is particularly useful in Markov Chain Monte Carlo studies and is provided to the community.

astro-ph.HE↗

arXiv2024

Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition

Modern automatic speech recognition (ASR) model is required to accurately transcribe diverse speech signals (from different domains, languages, accents, etc) given the specific contextual information in various application scenarios. Classic end-to-end models fused with extra language models perform well, but mainly in data matching scenarios and are gradually approaching a bottleneck. In this work, we introduce Seed-ASR, a large language model (LLM) based speech recognition model. Seed-ASR is developed based on the framework of audio conditioned LLM (AcLLM), leveraging the capabilities of LLMs by inputting continuous speech representations together with contextual information into the LLM. Through stage-wise large-scale training and the elicitation of context-aware capabilities in LLM, Seed-ASR demonstrates significant improvement over end-to-end models on comprehensive evaluation sets, including multiple domains, accents/dialects and languages. Additionally, Seed-ASR can be further deployed to support specific needs in various scenarios without requiring extra language models. Compared to recently released large ASR models, Seed-ASR achieves 10%-40% reduction in word (or character, for Chinese) error rates on Chinese and English public test sets, further demonstrating its powerful performance.

eess.AS↗

arXiv2024

DOZE: A Dataset for Open-Vocabulary Zero-Shot Object Navigation in Dynamic Environments

Zero-Shot Object Navigation (ZSON) requires agents to autonomously locate and approach unseen objects in unfamiliar environments and has emerged as a particularly challenging task within the domain of Embodied AI. Existing datasets for developing ZSON algorithms lack consideration of dynamic obstacles, object attribute diversity, and scene texts, thus exhibiting noticeable discrepancies from real-world situations. To address these issues, we propose a Dataset for Open-Vocabulary Zero-Shot Object Navigation in Dynamic Environments (DOZE) that comprises ten high-fidelity 3D scenes with over 18k tasks, aiming to mimic complex, dynamic real-world scenarios. Specifically, DOZE scenes feature multiple moving humanoid obstacles, a wide array of open-vocabulary objects, diverse distinct-attribute objects, and valuable textual hints. Besides, different from existing datasets that only provide collision checking between the agent and static obstacles, we enhance DOZE by integrating capabilities for detecting collisions between the agent and moving obstacles. This novel functionality enables the evaluation of the agents' collision avoidance abilities in dynamic environments. We test four representative ZSON methods on DOZE, revealing substantial room for improvement in existing approaches concerning navigation efficiency, safety, and object recognition accuracy. Our dataset can be found at https://DOZE-Dataset.github.io/.

cs.CV↗

arXiv2024

Foundations and Frontiers of Graph Learning Theory

Recent advancements in graph learning have revolutionized the way to understand and analyze data with complex structures. Notably, Graph Neural Networks (GNNs), i.e. neural network architectures designed for learning graph representations, have become a popular paradigm. With these models being usually characterized by intuition-driven design or highly intricate components, placing them within the theoretical analysis framework to distill the core concepts, helps understand the key principles that drive the functionality better and guide further development. Given this surge in interest, this article provides a comprehensive summary of the theoretical foundations and breakthroughs concerning the approximation and learning behaviors intrinsic to prevalent graph learning models. Encompassing discussions on fundamental aspects such as expressiveness power, generalization, optimization, and unique phenomena such as over-smoothing and over-squashing, this piece delves into the theoretical foundations and frontier driving the evolution of graph learning. In addition, this article also presents several challenges and further initiates discussions on possible solutions.

cs.LG↗

arXiv2024

Kanbun-LM: Reading and Translating Classical Chinese in Japanese Methods by Language Models

Recent studies in natural language processing (NLP) have focused on modern languages and achieved state-of-the-art results in many tasks. Meanwhile, little attention has been paid to ancient texts and related tasks. Classical Chinese first came to Japan approximately 2,000 years ago. It was gradually adapted to a Japanese form called Kanbun-Kundoku (Kanbun) in Japanese reading and translating methods, which has significantly impacted Japanese literature. However, compared to the rich resources for ancient texts in mainland China, Kanbun resources remain scarce in Japan. To solve this problem, we construct the first Classical-Chinese-to-Kanbun dataset in the world. Furthermore, we introduce two tasks, character reordering and machine translation, both of which play a significant role in Kanbun comprehension. We also test the current language models on these tasks and discuss the best evaluation method by comparing the results with human scores. We release our code and dataset on GitHub.

cs.CL↗