检索结果-内蒙古大学图书馆

An Efficient Watermarking Method for Latent Diffusion Models via Low-Rank Adaptation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lin, Dongdong Li, Yue Tondi, Benedetta Li, Bin Barni, Mauro Guangdong Provincial Key Laboratory of Intelligent Information Processing The Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen518060 China Huaqiao University China Xiamen Key Laboratory of Data Security and Blockchain Technology Xiamen361021 China Department of Information Engineering and Mathematics The University of Siena Italy

The rapid proliferation of deep neural networks (DNNs) is driving a surge in model watermarking technologies, as the trained deep models themselves serve as intellectual properties. The core of existing model watermarking techniques involves modifying or tuning the models’ weights. However, with the emergence of increasingly complex models, ensuring the efficiency of watermarking process is essential to manage the growing computational demands. Prioritizing efficiency not only optimizes resource utilization, making the watermarking process more applicable, but also minimizes potential impacts on model performance. In this letter, we propose an efficient watermarking method for latent diffusion models (LDMs) which is based on Low-Rank Adaptation (LoRA). We specifically choose to add trainable low-rank matrices to the existing weight matrices of the models to embed watermark, while keeping the original weights frozen. Moreover, we also propose a dynamic loss weight tuning algorithm to balance the generative task with the watermark embedding task, ensuring that the model can be watermarked with a limited impact on the quality of the generated images. Experimental results show that the proposed method ensures fast watermark embedding and maintains a very low bit error rate of the watermark, a high-quality of the generated image, and a zero false negative rate (FNR) for verification. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

What's the Real: A Novel Design Philosophy for Robust AI-Synthesized Voice Detection 24

学校读者我要写书评

暂无评论

What's the Real: A Novel Design Philosophy for Robust AI-Syn...

32nd ACM International Conference on Multimedia, MM 2024

作者： Hai, Xuan Liu, Xin Tan, Yuan Liu, Gang Li, Song Niu, Weina Zhou, Rui Zhou, Xiaokang School of Information Science and Engineering Lanzhou University Lanzhou China The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Faculty of Business Data Science Kansai University Osaka Japan

ISBN: (纸本)9798400706868

Voice is one of the most widely used media for information transmission in human society. While high-quality synthetic voices are extensively utilized in various applications, they pose significant risks to content security and trust building. Numerous studies have concentrated on AI-synthesized voice detection to mitigate these risks, with many claiming to achieve promising performance. However, recent research has demonstrated that fake voice detectors suffer from serious overfitting to speaker-irrelative features (SiFs) and cannot be used in real-world scenarios. In this paper, we analyze the limitations of existing fake voice detectors and propose a new design philosophy, guiding the detection model to prioritize learning human voice features rather than the difference between the human voice and the synthetic voice. Based on this philosophy, we propose a novel AI-synthesized voice detection framework named SiFSafer, which uses pre-trained speech representation models to enhance the learning of feature distribution in human voices and the adapter fine-tuning to optimize the performance. The evaluation shows that the average EERs of existing fake voice detectors in the ASVspoof datasets can exceed 20% if the SiFs like silence segments are removed, while SiFSafer achieves an EER of less than 8%, indicating that SiFSafer is robust to SiFs and strongly resistant to existing attacks. © 2024 ACM.

关键词： Fake detection

MSHyper: Multi-Scale Hypergraph Transformer for Long-Range Time Series Forecasting

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Shang, Zongjiang Chen, Ling Wu, Binqing Cui, Dongliang State Key Laboratory of Blockchain and Data Security College of Computer Science and Technology Zhejiang University Hangzhou310027 China

Demystifying the interactions between temporal patterns of different scales is fundamental to precise long-range time series forecasting. However, previous works lack the ability to model high-order interactions. To promote more comprehensive pattern interaction modeling for long-range time series forecasting, we propose a Multi-Scale Hypergraph Transformer (MSHyper) framework. Specifically, a multi-scale feature extraction (MFE) modlue is introduced to map the input sequence into multi-scale embeddings. Then, a multi-scale hypergraph is designed to provide foundations for modeling high-order pattern interactions and a hyperedge graph is built to enhance hypergraph modeling. In addition, a tri-stage message passing (TMP) mechanism is introduced to aggregate pattern information and learn the interaction strength between temporal patterns of different scales. Extensive experimental results on eight real-world datasets demonstrate that MSHyper achieves the state-of-the-art (SOTA) performance across various settings. Copyright © 2024, The Authors. All rights reserved.

关键词： Time series

A Multipath Source Location Privacy Protection Scheme in Wireless Sensor Networks via Proxy Node 15

学校读者我要写书评

暂无评论

A Multipath Source Location Privacy Protection Scheme in Wir...

2022 IEEE Congress on Cybermatics: 15th IEEE International Conferences on Internet of Things, iThings 2022, 18th IEEE International Conferences on Green Computing and Communications, GreenCom 2022, 2022 IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2022 and 8th IEEE International Conference on Smart data, Smartdata 2022

作者： Sun, Jing Chen, Yuling Lv, Xiao Qian, Xiaobin Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang China Guilin University of Electronic Technology Guangxi Key Laboratory of Cryptography and Information Security Guilin China Weifang University of Science and Technology Blockchain Laboratory of Agricultural Vegetables Weifang China Guizhou Shuanhui Big Data Industry Development Co.Ltd Guiyang China Guizhou CoVision Science &technology Co.Ltd Guiyang China

ISBN: (数字)9781665454179

ISBN: (纸本)9781665454179

Wireless sensor networks (WSNs) are widely devoted to monitoring target. Attackers can detect the source node by hop-by-hop backtracking strategy. Therefore, it is necessary to protect the location privacy of data source nodes. Source location privacy (SLP) plays a crucial role in WSNs security. To ensure the security of source location in WSNs, a multi-path source location privacy protection scheme via proxy node is proposed. Source node initiates restricted flooding and directed routing algorithm keep packets away from the source location, effectively increasing the number of random directed paths. Greedy quantitative routing is the basis of generating vast quantities of relay nodes with diverse geographical locations. The receiving node randomly generates angles to complete equal-hop routing. The sending node continuously selects any near-neighbor node as a participant until the data packet is sent to the spin node. The spin node chooses the adjacent quadrant to complete the variable length equal-hop routing through proxy nodes and forwards the packet to the sink node. Theoretical analysis and simulation experiments show that this scheme provides excellent privacy for the source location. © 2022 IEEE.

关键词： data privacy

Ppt4j: Patch Presence Test for Java Binaries 24

学校读者我要写书评

暂无评论

Ppt4j: Patch Presence Test for Java Binaries

44th ACM/IEEE International Conference on Software Engineering, ICSE 2024

作者： Pan, Zhiyuan Hu, Xing Xia, Xin Zhan, Xian Lo, David Yang, Xiaohu Zhejiang University The State Key Laboratory of Blockchain and Data Security Hangzhou China Huawei Software Engineering Application Technology Lab Hangzhou China The Hong Kong Polytechnic University Hong Kong School of Computing and Information Systems Singapore Management University Singapore

ISBN: (纸本)9798400702174

The number of vulnerabilities reported in open source software has increased substantially in recent years. security patches provide the necessary measures to protect software from attacks and vulnerabilities. In practice, it is difficult to identify whether patches have been integrated into software, especially if we only have binary files. Therefore, the ability to test whether a patch is applied to the target binary, a.k.a. patch presence test, is crucial for practitioners. However, it is challenging to obtain accurate semantic information from patches, which could lead to incorrect results. In this paper, we propose a new patch presence test framework named Ppt4j (Patch Presence Test forJava Binaries). Ppt4j is designed for open-source Java libraries. It takes Java binaries (i.e. bytecode files) as input, extracts semantic information from patches, and uses feature-based techniques to identify patch lines in the binaries. To evaluate the effectiveness of our proposed approach Ppt4j, we construct a dataset with binaries that include 110 vulnerabilities. The results show that Ppt4j achieves an F1 score of 98.5% with reasonable efficiency, improving the baseline by 14.2%. Furthermore, we conduct an in-the-wild evaluation of Ppt4j on JetBrains IntelliJ IDEA. The results suggest that a third-party library included in the software is not patched for two CVEs, and we have reported this potential security problem to the vendor. © 2024 ACM.

关键词： Open source software

GLOW: Global Layout Aware Attacks on Object Detection

学校读者我要写书评

暂无评论

GLOW: Global Layout Aware Attacks on Object Detection

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Jun Bao Buyu Liu Kui Ren Jun Yu The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou Dianzi University Harbin Institute of Technology (Shenzhen)

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Adversarial attacks aim to perturb images such that a predictor outputs incorrect results. Due to the limited research in structured attacks, imposing consistency checks on natural multi-object scenes is a practical defense against conventional adversarial attacks. More desired attacks should be able to fool defenses with such consistency checks. Therefore, we present the first approach GLOW that copes with various attack requests by generating global layout-aware adversar-ial attacks, in which both categorical and geometric layout constraints are explicitly established. Specifically, we focus on object detection tasks and given a victim image, GLOW first localizes victim objects according to target labels. And then it generates multiple attack plans, together with their context-consistency scores. GLOW, on the one hand, is ca-pable of handling various types of requests, including single or multiple victim objects, with or without specified victim objects. On the other hand, it produces a consistency score for each attack plan, reflecting the overall contextual consistency that both semantic category and global scene layout are considered. We conduct our experiments on MS COCO and Pascal. Extensive experimental results demonstrate that we can achieve about 30% average relative improvement compared to state-of-the-art methods in conventional single object attack request; Moreover, such superiority is also valid across more generic attack requests, under both white-box and zero-query black-box settings. Finally, we conduct comprehensive human analysis, which not only validates our claim further but also provides strong evidence that our evaluation metrics reflect human reviews well.

关键词： Measurement Reviews Layout Semantics Closed box Estimation Object detection

PSL: Rethinking and Improving Softmax Loss from Pairwise Perspective for Recommendation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Weiqin Chen, Jiawei Xin, Xin Zhou, Sheng Hu, Binbin Feng, Yan Chen, Chun Wang, Can Shandong University China Ant Group China State Key Laboratory of Blockchain and Data Security Zhejiang University China College of Computer Science and Technology Zhejiang University China Institute of Blockchain and Data Security China

Softmax Loss (SL) is widely applied in recommender systems (RS) and has demonstrated effectiveness. This work analyzes SL from a pairwise perspective, revealing two significant limitations: 1) the relationship between SL and conventional ranking metrics like DCG is not sufficiently tight;2) SL is highly sensitive to false negative instances. Our analysis indicates that these limitations are primarily due to the use of the exponential function. To address these issues, this work extends SL to a new family of loss functions, termed Pairwise Softmax Loss (PSL), which replaces the exponential function in SL with other appropriate activation functions. While the revision is minimal, we highlight three merits of PSL: 1) it serves as a tighter surrogate for DCG with suitable activation functions;2) it better balances data contributions;and 3) it acts as a specific BPR loss enhanced by Distributionally Robust Optimization (DRO). We further validate the effectiveness and robustness of PSL through empirical experiments. The code is available at https://***/Tiny-Snow/IR-Benchmark. © 2024, CC BY.

关键词： Exponential functions

Uncertainty-aware complementary label queries for active learning

学校读者我要写书评

暂无评论

Frontiers of Information technology & Electronic Engineering 2023年第10期24卷 1497-1503页

作者： Shengyuan LIU Ke CHEN Tianlei HU Yunqing MAO Key Lab of Intelligent Computing Based Big Data of Zhejiang Province Zhejiang UniversityHangzhou 310027China State Key Laboratory of Blockchain and Data Security Zhejiang UniversityHangzhou 310027China City Cloud Technology(China)Co. Ltd.Hangzhou 310000China

Many active learning methods assume that a learner can simply ask for the full annotations of some training data from *** methods mainly try to cut the annotation costs by minimizing the number of annotation ***,annotating instances exactly in many realworld classification tasks is still *** reduce the cost of a single annotation action,we try to tackle a novel active learning setting,named active learning with complementary labels(ALCL).ALCL learners ask only yes/no questions in some *** receiving answers from annotators,ALCL learners obtain a few supervised instances and more training instances with complementary labels,which specify only one of the classes to which the pattern does not *** are two challenging issues in ALCL:one is how to sample instances to be queried,and the other is how to learn from these complementary labels and ordinary accurate *** the first issue,we propose an uncertainty-based sampling strategy under this novel setup.

关键词： complementary instance ordinary

TIMEMIXER++: A GENERAL TIME SERIES PATTERN MACHINE FOR UNIVERSAL PREDICTIVE ANALYSIS

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Shiyu Li, Jiawei Shi, Xiaoming Ye, Zhou Mo, Baichuan Lin, Wenze Ju, Shengtong Chu, Zhixuan Jin, Ming The Hong Kong University of Science and Technology Guangzhou China Massachusetts Institute of Technology United States Zhejiang University China The State Key Laboratory of Blockchain and Data Security China Institute of Blockchain and Data Security China Griffith University Australia

Time series analysis plays a critical role in numerous applications, supporting tasks such as forecasting, classification, anomaly detection, and imputation. In this work, we present the time series pattern machine (TSPM), a model designed to excel in a broad range of time series tasks through powerful representation and pattern extraction capabilities. Traditional time series models often struggle to capture universal patterns, limiting their effectiveness across diverse tasks. To address this, we define multiple scales in the time domain and various resolutions in the frequency domain, employing various mixing strategies to extract intricate, task-adaptive time series patterns. Specifically, we introduce TIMEMIXER++, a general-purpose TSPM that processes multi-scale time series using (1) multi-resolution time imaging (MRTI), (2) time image decomposition (TID), (3) multi-scale mixing (MCM), and (4) multi-resolution mixing (MRM) to extract comprehensive temporal patterns. MRTI transforms multi-scale time series into multi-resolution time images, capturing patterns across both temporal and frequency domains. TID leverages dual-axis attention to extract seasonal and trend patterns, while MCM hierarchically aggregates these patterns across scales. MRM adaptively integrates all representations across resolutions. TIMEMIXER++ achieves state-of-the-art performance across 8 time series analytical tasks, consistently surpassing both general-purpose and task-specific models. Our work marks a promising step toward the next generation of TSPMs, paving the way for further advancements in time series analysis. © 2024, CC BY.

关键词： Predictive analytics