arXiv subjects

Haoyu Jiang

Publications and source records attributed to Haoyu Jiang.

27 records · Page 2Linked to original sources

arXiv2024

Building Intelligence Identification System via Large Language Model Watermarking: A Survey and Beyond

Large Language Models (LLMs) are increasingly integrated into diverse industries, posing substantial security risks due to unauthorized replication and misuse. To mitigate these concerns, robust identification mechanisms are widely acknowledged as an effective strategy. Identification systems for LLMs now rely heavily on watermarking technology to manage and protect intellectual property and ensure data security. However, previous studies have primarily concentrated on the basic principles of algorithms and lacked a comprehensive analysis of watermarking theory and practice from the perspective of intelligent identification. To bridge this gap, firstly, we explore how a robust identity recognition system can be effectively implemented and managed within LLMs by various participants using watermarking technology. Secondly, we propose a mathematical framework based on mutual information theory, which systematizes the identification process to achieve more precise and customized watermarking. Additionally, we present a comprehensive evaluation of performance metrics for LLM watermarking, reflecting participant preferences and advancing discussions on its identification applications. Lastly, we outline the existing challenges in current watermarking technologies and theoretical frameworks, and provide directional guidance to address these challenges. Our systematic classification and detailed exposition aim to enhance the comparison and evaluation of various methods, fostering further research and development toward a transparent, secure, and equitable LLM ecosystem.

cs.CR↗

arXiv2024

Magnitude-based Neuron Pruning for Backdoor Defens

Deep Neural Networks (DNNs) are known to be vulnerable to backdoor attacks, posing concerning threats to their reliable deployment. Recent research reveals that backdoors can be erased from infected DNNs by pruning a specific group of neurons, while how to effectively identify and remove these backdoor-associated neurons remains an open challenge. In this paper, we investigate the correlation between backdoor behavior and neuron magnitude, and find that backdoor neurons deviate from the magnitude-saliency correlation of the model. The deviation inspires us to propose a Magnitude-based Neuron Pruning (MNP) method to detect and prune backdoor neurons. Specifically, MNP uses three magnitude-guided objective functions to manipulate the magnitude-saliency correlation of backdoor neurons, thus achieving the purpose of exposing backdoor behavior, eliminating backdoor neurons and preserving clean neurons, respectively. Experiments show our pruning strategy achieves state-of-the-art backdoor defense performance against a variety of backdoor attacks with a limited amount of clean data, demonstrating the crucial role of magnitude for guiding backdoor defenses.

cs.LG↗

arXiv2024

OCGEC: One-class Graph Embedding Classification for DNN Backdoor Detection

Deep neural networks (DNNs) have been found vulnerable to backdoor attacks, raising security concerns about their deployment in mission-critical applications. There are various approaches to detect backdoor attacks, however they all make certain assumptions about the target attack to be detected and require equal and huge numbers of clean and backdoor samples for training, which renders these detection methods quite limiting in real-world circumstances. This study proposes a novel one-class classification framework called One-class Graph Embedding Classification (OCGEC) that uses GNNs for model-level backdoor detection with only a little amount of clean data. First, we train thousands of tiny models as raw datasets from a small number of clean datasets. Following that, we design a ingenious model-to-graph method for converting the model's structural details and weight features into graph data. We then pre-train a generative self-supervised graph autoencoder (GAE) to better learn the features of benign models in order to detect backdoor models without knowing the attack strategy. After that, we dynamically combine the GAE and one-class classifier optimization goals to form classification boundaries that distinguish backdoor models from benign models. Our OCGEC combines the powerful representation capabilities of graph neural networks with the utility of one-class classification techniques in the field of anomaly detection. In comparison to other baselines, it achieves AUC scores of more than 98% on a number of tasks, which far exceeds existing methods for detection even when they rely on a huge number of positive and negative samples. Our pioneering application of graphic scenarios for generic backdoor detection can provide new insights that can be used to improve other backdoor defense tasks. Code is available at https://github.com/jhy549/OCGEC.

cs.LG↗

arXiv2023

CN-Celeb-AV: A Multi-Genre Audio-Visual Dataset for Person Recognition

Audio-visual person recognition (AVPR) has received extensive attention. However, most datasets used for AVPR research so far are collected in constrained environments, and thus cannot reflect the true performance of AVPR systems in real-world scenarios. To meet the request for research on AVPR in unconstrained conditions, this paper presents a multi-genre AVPR dataset collected `in the wild', named CN-Celeb-AV. This dataset contains more than 419k video segments from 1,136 persons from public media. In particular, we put more emphasis on two real-world complexities: (1) data in multiple genres; (2) segments with partial information. A comprehensive study was conducted to compare CN-Celeb-AV with two popular public AVPR benchmark datasets, and the results demonstrated that CN-Celeb-AV is more in line with real-world scenarios and can be regarded as a new benchmark dataset for AVPR research. The dataset also involves a development set that can be used to boost the performance of AVPR systems in real-life situations. The dataset is free for researchers and can be downloaded from http://cnceleb.org/.

cs.CV↗

arXiv2023

Swin Transformer coupling CNNs Makes Strong Contextual Encoders for VHR Image Road Extraction

Accurately segmenting roads is challenging due to substantial intra-class variations, indistinct inter-class distinctions, and occlusions caused by shadows, trees, and buildings. To address these challenges, attention to important texture details and perception of global geometric contextual information are essential. Recent research has shown that CNN-Transformer hybrid structures outperform using CNN or Transformer alone. While CNN excels at extracting local detail features, the Transformer naturally perceives global contextual information. In this paper, we propose a dual-branch network block named ConSwin that combines ResNet and SwinTransformers for road extraction tasks. This ConSwin block harnesses the strengths of both approaches to better extract detailed and global features. Based on ConSwin, we construct an hourglass-shaped road extraction network and introduce two novel connection structures to better transmit texture and structural detail information to the decoder. Our proposed method outperforms state-of-the-art methods on both the Massachusetts and CHN6-CUG datasets in terms of overall accuracy, IOU, and F1 indicators. Additional experiments validate the effectiveness of our proposed module, while visualization results demonstrate its ability to obtain better road representations.

cs.CV↗

arXiv2020

Measurement of the neutron beam profile of the Back-n white neutron facility at CSNS with a Micromegas detector

The Back-n white neutron beam line, which uses back-streaming white neutrons from the spallation target of the China Spallation Neutron Source, is used for nuclear data measurements. A Micromegas-based neutron detector with two variants was specially developed to measure the beam spot distribution for this beam line. In this article, the design, fabrication, and characterization of the detector are described. The results of the detector performance tests are presented, which include the relative electron transparency, the gain and the gain uniformity, and the neutron beam profile reconstruction capability. The result of the first measurement of the Back-n neutron beam spot distribution is also presented.

physics.ins-det↗

arXiv2019

Measurements of differential and angle-integrated cross sections for the $^{10}$B($n, α$)$^{7}$Li reaction in the neutron energy range from 1.0 eV to 2.5 MeV

Differential and angle-integrated cross sections for the $^{10}$B($n, α$)$^{7}$Li, $^{10}$B($n, α$$_{0}$)$^{7}$Li and $^{10}$B($n, α$$_{1}$)$^{7}$Li$^{*}$ reactions have been measured at CSNS Back-n white neutron source. Two enriched (90%) $^{10}$B samples 5.0 cm in diameter and ~85.0 $μ$g/cm$^{2}$ in thickness each with an aluminum backing were prepared, and back-to-back mounted at the sample holder. The charged particles were detected using the silicon-detector array of the Light-charged Particle Detector Array (LPDA) system. The neutron energy E$_{n}$ was determined by TOF (time-of-flight) method, and the valid $α$ events were extracted from the E$_{n}$-Amplitude two-dimensional spectrum. With 15 silicon detectors, the differential cross sections of $α$-particles were measured from 19.2° to 160.8°. Fitted with the Legendre polynomial series, the ($n, α$) cross sections were obtained through integration. The absolute cross sections were normalized using the standard cross sections of the $^{10}$B($n, α$)$^{7}$Li reaction in the 0.3 - 0.5 MeV neutron energy region. The measurement neutron energy range for the $^{10}$B($n, α$)$^{7}$Li reaction is 1.0 eV $\le$ En < 2.5 MeV (67 energy points), and for the $^{10}$B($n, α$$_{0}$)$^{7}$Li and $^{10}$B($n, α$$_{1}$)$^{7}$Li$^{*}$ reactions is 1.0 eV $\le$ En < 1.0 MeV (59 energy points). The present results have been analyzed by the resonance reaction mechanism and the level structure of the $^{11}$B compound system, and compared with existing measurements and evaluations.

nucl-ex↗

arXiv2018

Spatially Tracking Wave Events in Partitioned Numerical Wave Model Outputs

Numerical wave models can output partitioned wave parameters at each grid point using a spectral partitioning technique. Because these wave partitions are usually organized according to the magnitude of their wave energy without considering the coherence of wave parameters in space, it can be difficult to observe the spatial distributions of wave field features from these outputs. In this study, an approach for spatially tracking coherent wave events (which means a cluster of partitions originated from the same meteorological event) from partitioned numerical wave model outputs is presented to solve this problem. First, an efficient traverse algorithm applicable for different types of grids, termed breadth-first search, is employed to track wave events using the continuity of wave parameters. Second, to reduce the impact of the garden sprinkler effect on tracking, tracked wave events are merged if their boundary outlines and wave parameters on these boundaries are both in good agreement. Partitioned wave information from the Integrated Ocean Waves for Geophysical and other Applications dataset is used to test the performance of this spatial tracking approach. The test results indicate that this approach is able to capture the primary features of partitioned wave fields, demonstrating its potential for wave data analysis, model verification, and data assimilation.

physics.ao-ph↗

arXiv2018

Wave Climate from Spectra and its Connections with Local and Remote Wind Climate

Because wind-generated waves can propagate over large distances, wave spectra from a fixed point can record information about air-sea interactions in distant areas. In this study, the spectral wave climate is computed for a specific location in the tropical Eastern Pacific Ocean. Several well-defined partitions independent of each other, referred to as wave-climate systems, are observed in the annual mean wave spectrum. Significant seasonal cycling, long-term trends, and correlations with climate indices are observed in the local wave spectra, showing the abundant climatic information they contain. The projections of the wind vector on the direction pointing to the target location are used to link the spectral wave climate and basin-scale wind climate. The origins of all the identified wave climate systems are clearly shown in the wind projection maps and some are thousands of kilometers away from the target point, demonstrating the validity of this connection. Comparisons are made between wave spectra and the corresponding local and remote wind fields with respect to seasonal and interannual variability, as well as the long-term trends. The results show that each frequency and direction of ocean wave spectra at a certain location can be linked to the wind field for a geographical area from a climatological point of view, implying that it is feasible to reconstruct a spectral wave climate from global observational wind field data and wind climate monitoring using observations of wave spectrum geographically far away.

physics.ao-ph↗