检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Qing, Yunpeng Liu, Shunyu Cong, Jingyuan Chen, Kaixuan Zhou, Yihe Song, Mingli College of Computer Science and Technology Zhejiang University China State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China

Offline reinforcement learning endeavors to leverage offline datasets to craft effective agent policy without online interaction, which imposes proper conservative constraints with the support of behavior policies to tackle the out-of-distribution problem. However, existing works often suffer from the constraint conflict issue when offline datasets are collected from multiple behavior policies, i.e., different behavior policies may exhibit inconsistent actions with distinct returns across the state space. To remedy this issue, recent advantage-weighted methods prioritize samples with high advantage values for agent training while inevitably ignoring the diversity of behavior policy. In this paper, we introduce a novel Advantage-Aware Policy Optimization (A2PO) method to explicitly construct advantage-aware policy constraints for offline learning under mixed-quality datasets. Specifically, A2PO employs a conditional variational auto-encoder to disentangle the action distributions of intertwined behavior policies by modeling the advantage values of all training data as conditional variables. Then the agent can follow such disentangled action distribution constraints to optimize the advantage-aware policy towards high advantage values. Extensive experiments conducted on both the single-quality and mixed-quality datasets of the D4RL benchmark demonstrate that A2PO yields results superior to the counterparts. Our code is available at https://***/Plankson/A2PO. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Automating Zero-Shot Patch Porting for Hard Forks

arXiv

引用

arXiv 2024年

作者： Pan, Shengyi Hu, Xing Wang, You Xia, Xin Liu, Zhongxin Li, Shanping The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China The State Key Laboratory of Blockchain and Data Security Zhejiang University Ningbo China Zhejiang University Hangzhou China Huawei Hangzhou China

Forking is a typical way of code reuse, which provides a simple way for developers to create a variant software (denoted as hard fork) by copying and modifying an existing codebase. Despite of the benefits, forking also leads to duplicate efforts in software maintenance. Developers need to port patches across the hard forks to address similar bugs or implement similar features. Due to the divergence between the source project and the hard fork, patch porting is complicated, which requires an adaption regarding different implementations of the same functionality. In this work, we take the first step to automate patch porting for hard forks under a zero-shot setting. We first conduct an empirical study of the patches ported from Vim to Neovim over the last ten years to investigate the necessities of patch porting and the potential flaws in the current practice. We then propose a large language model (LLM) based approach (namely PPatHF) to automatically port patches for hard forks on a function-wise basis. Specifically, PPatHF is composed of a reduction module and a porting module. Given the pre- and post-patch versions of a function from the reference project and the corresponding function from the target project, the reduction module first slims the input functions by removing code snippets less relevant to the patch. Then, the porting module leverages a LLM to apply the patch to the function from the target project. To better elicit the power of the LLM on patch porting, we design a prompt template to enable efficient in-context learning. We further propose an instruction-tuning based training task to better guide the LLM to port the patch and inject task-specific knowledge. We evaluate PPatHF on 310 Neovim patches ported from Vim. The experimental results show that PPatHF outperforms the baselines significantly. Specifically, PPatHF can correctly port 131 (42.3%) patches and automate 57% of the manual edits required for the developer to port the patch. Copyright ©

关键词： Computer software reusability

来源：评论

学校读者我要写书评

暂无评论

Local Differentially Private Heavy Hitter Detection in data Streams with Bounded Memory

引用

Proceedings of the ACM on Management of data 2024年第1期2卷 1-27页

作者： Xiaochen Li Weiran Liu Jian Lou Yuan Hong Lei Zhang Zhan Qin Kui Ren The State Key Laboratory of Blockchain and Data Security Zhejiang university Hangzhou China Alibaba Group Beijing China Zhejiang University Hangzhou China University of Connecticut Mansfield USA Alibaba Group Hangzhou China The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China

Top-k frequent items detection is a fundamental task in data stream mining. Many promising solutions are proposed to improve memory efficiency while still maintaining high accuracy for detecting the Top-k items. Despite the memory efficiency concern, the users could suffer from privacy loss if participating in the task without proper protection, since their contributed local data streams may continually leak sensitive individual information. However, most existing works solely focus on addressing either the memory-efficiency problem or the privacy concerns but seldom jointly, which cannot achieve a satisfactory tradeoff between memory efficiency, privacy protection, and detection *** this paper, we present a novel framework HG-LDP to achieve accurate Top-k item detection at bounded memory expense, while providing rigorous local differential privacy (LDP) protection. Specifically, we identify two key challenges naturally arising in the task, which reveal that directly applying existing LDP techniques will lead to an inferior "accuracy-privacy-memory efficiency" tradeoff. Therefore, we instantiate three advanced schemes under the framework by designing novel LDP randomization methods, which address the hurdles caused by the large size of the item domain and by the limited space of the memory. We conduct comprehensive experiments on both synthetic and real-world datasets to show that the proposed advanced schemes achieve a superior "accuracy-privacy-memory efficiency" tradeoff, saving 2300× memory over baseline methods when the item domain size is 41,270. Our code is anonymously open-sourced via the link.

关键词： data stream processing heavy hitter local differential privacy

来源：评论

学校读者我要写书评

暂无评论

SoK: On the Role and Future of AIGC Watermarking in the Era of Gen-AI

arXiv

引用

arXiv 2024年

作者： Ren, Kui Yang, Ziqi Lu, Li Liu, Jian Li, Yiming Wan, Jie Zhao, Xiaodi Feng, Xianheng Shao, Shuo The State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China College of Computing and Data Science Nanyang Technological University Singapore

The rapid advancement of AI technology, particularly in generating AI-generated content (AIGC), has transformed numerous fields, e.g., art video generation, but also brings new risks, including the misuse of AI for misinformation and intellectual property theft. To address these concerns, AIGC watermarks offer an effective solution to mitigate malicious activities. However, existing watermarking surveys focus more on traditional watermarks, overlooking AIGC-specific challenges. In this work, we propose a systematic investigation into AIGC watermarking and provide the first formal definition of AIGC watermarking. Different from previous surveys, we provide a taxonomy based on the core properties of the watermark which are summarized through comprehensive literature from various AIGC modalities. Derived from the properties, we discuss the functionality and security threats of AIGC watermarking. In the end, we thoroughly investigate the AIGC governance of different countries and practitioners. We believe this taxonomy better aligns with the practical demands for watermarking in the era of GenAI, thus providing a clearer summary of existing work and uncovering potential future research directions for the community. Copyright © 2024, The Authors. All rights reserved.

关键词： Watermarking

来源：评论

学校读者我要写书评

暂无评论

MicGuard: a comprehensive detection system against out-of-band injection attacks for different level microphone-based devices 24

MicGuard: a comprehensive detection system against out-of-ba...

引用

Proceedings of the 33rd USENIX Conference on security Symposium

作者： Tiantian Liu Feng Lin Zhongjie Ba Li Lu Zhan Qin Kui Ren State Key Laboratory of Blockchain and Data Security Zhejiang University School of Cyber Science and Technology Zhejiang University Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security

ISBN: (纸本)9781939133441

The integration of microphones into sensors and systems, serving as input interfaces to intelligent applications and industrial manufacture, has raised public concerns regarding their input perception. Studies have uncovered the potential dangers posed by out-of-band injection attacks on microphones, encompassing ultrasound, laser, and electromagnetic attacks, injecting commands or interferences for malicious purposes. Despite existing efforts on defense against ultrasound injections, there is a critical gap in addressing the risks posed by other out-of-band injections. To bridge this gap, this paper proposes MicGuard, a comprehensive passive detection system against out-of-band attacks. Without relying on prior information from attacking and victim devices, MicGuard leverages carrier traces and spectral chaos observed by injection phenomena across different levels of devices. The carrier traces are used in a prejudgment to fast reject partial injected signals, and the following memory-based detection model to distinguish anomaly based on the quantified chaotic entropy extracted from publicly available audio datasets. MicGuard is evaluated on a wide range of microphone-based devices including sensors, recorders, smartphones, and tablets, achieving an average AUC of 98% with high robustness and universality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

REFINE: INVERSION-FREE BACKDOOR DEFENSE VIA MODEL REPROGRAMMING

arXiv

引用

arXiv 2025年

作者： Chen, Yukun Shao, Shuo Huang, Enhao Li, Yiming Chen, Pin-Yu Qin, Zhan Ren, Kui State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China Nanyang Technological University Singapore IBM Research United States

Backdoor attacks on deep neural networks (DNNs) have emerged as a significant security threat, allowing adversaries to implant hidden malicious behaviors during the model training phase. Pre-processing-based defense, which is one of the most important defense paradigms, typically focuses on input transformations or backdoor trigger inversion (BTI) to deactivate or eliminate embedded backdoor triggers during the inference process. However, these methods suffer from inherent limitations: transformation-based defenses often fail to balance model utility and defense performance, while BTI-based defenses struggle to accurately reconstruct trigger patterns without prior knowledge. In this paper, we propose REFINE, an inversion-free backdoor defense method based on model reprogramming. REFINE consists of two key components: (1) an input transformation module that disrupts both benign and backdoor patterns, generating new benign features;and (2) an output remapping module that redefines the model’s output domain to guide the input transformations effectively. By further integrating supervised contrastive loss, REFINE enhances the defense capabilities while maintaining model utility. Extensive experiments on various benchmark datasets demonstrate the effectiveness of our REFINE and its resistance to potential adaptive attacks. © 2025, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Non-stationary online convex optimization with arbitrary delays 24

Non-stationary online convex optimization with arbitrary del...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Yuanyu Wan Chang Yao Mingli Song Lijun Zhang The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China and School of Software Technology Zhejiang University Ningbo China and Hangzhou High- Tech Zone (Binjiang) Institute of Blockchain and Data Security Hangzhou China The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China and Hangzhou High- Tech Zone (Binjiang) Institute of Blockchain and Data Security Hangzhou China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China and The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China

Online convex optimization (OCO) with arbitrary delays, in which gradients or other information of functions could be arbitrarily delayed, has received increasing attention recently. Different from previous studies that focus on stationary environments, this paper investigates the delayed OCO in non-stationary environments, and aims to minimize the dynamic regret with respect to any sequence of comparators. To this end, we first propose a simple algorithm, namely DOGD, which performs a gradient descent step for each delayed gradient according to their arrival order. Despite its simplicity, our novel analysis shows that the dynamic regret of DOGD can be automatically bounded by $O(\sqrt{\bar{d}T}(P_T+1))$ under mild assumptions, and $O(\sqrt{dT}(P_T+1))$ in the worst case, where $\bar{d}$ and d denote the average and maximum delay respectively, T is the time horizon, and PT is the path-length of comparators. Furthermore, we develop an improved algorithm, which reduces those dynamic regret bounds achieved by DOGD to $O(\sqrt{\bar{d}T(P_T+1)})$ and $O(\sqrt{dT(P_T+1)})$, respectively. The key idea is to run multiple DOGD with different learning rates, and utilize a metaalgorithm to track the best one based on their delayed performance. Finally, we demonstrate that our improved algorithm is optimal in the worst case by deriving a matching lower bound.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CSCHECKER: Revisiting GDPR and CCPA Compliance of Cookie Banners on the Web 24

CSCHECKER: Revisiting GDPR and CCPA Compliance of Cookie Ban...

引用

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

作者： Zhang, Mingxue Meng, Wei Zhou, You Ren, Kui The State Key Laboratory of Blockchain and Data Security Zhejiang University China ZJU-Hangzhou Global Scientific and Technological Innovation Center Zhejiang University Hangzhou311215 China The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9798400702174

Privacy regulations like GDPR and CCPA have greatly affected online advertising and tracking strategies. To comply with the regulations, websites need to display consent management UIs (i.e., cookie banners) implemented under the corresponding technical frameworks, allowing users to specify consents regarding their personal data processing. Although prior works have investigated the cookie banner compliance problems with GDPR, the technical specification has significantly changed. The compliance status under the latest framework remains unclear. There also lacks a systematic study of CCPA banner compliance. More importantly, most work have focused on detecting the regulation violations, whereas little is known about the possible culprits and causes. In this paper, we develop CSCHECKER, a browser-based tool that monitors and records consent strings on websites. We use CSCHECKER to analyze the GDPR and CCPA cookie banners, and reveal previously unknown compliance problems under both frame-works. We also discover and analyze possible miscreants leading to the violations, e.g., consent management providers that return wrong consent data. The comparison of the two frameworks inspires several suggestions about the design of cookie banners, the implementation of opt-out mechanisms, and the enforcement of user consent choices. © 2024 ACM.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Vision mamba mender 24

Vision mamba mender

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Jiacong Hu Anda Cao Zunlei Feng Shengxuming Zhang Yi Wang Lingxiang Jia Mingli Song College of Computer Science and Technology Zhejiang University and State Key Laboratory of Blockchain and Data Security Zhejiang University College of Computer Science and Technology Zhejiang University School of Software Technology Zhejiang University and State Key Laboratory of Blockchain and Data Security Zhejiang University and Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security School of Software Technology Zhejiang University College of Computer Science and Technology Zhejiang University and State Key Laboratory of Blockchain and Data Security Zhejiang University and Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security

ISBN: (纸本)9798331314385

Mamba, a state-space model with selective mechanisms and hardware-aware architecture, has demonstrated outstanding performance in long sequence modeling tasks, particularly garnering widespread exploration and application in the field of computer vision. While existing works have mixed opinions of its application in visual tasks, the exploration of its internal workings and the optimization of its performance remain urgent and worthy research questions given its status as a novel model. Existing optimizations of the Mamba model, especially when applied in the visual domain, have primarily relied on predefined methods such as improving scanning mechanisms or integrating other architectures, often requiring strong priors and extensive trial and error. In contrast to these approaches, this paper proposes the Vision Mamba Mender, a systematic approach for understanding the workings of Mamba, identifying flaws within, and subsequently optimizing model performance. Specifically, we present methods for predictive correlation analysis of Mamba's hidden states from both internal and external perspectives, along with corresponding definitions of correlation scores, aimed at understanding the workings of Mamba in visual recognition tasks and identifying flaws therein. Additionally, tailored repair methods are proposed for identified external and internal state flaws to eliminate them and optimize model performance. Extensive experiments validate the efficacy of the proposed methods on prevalent Mamba architectures, significantly enhancing Mamba's performance. For more information, please visit https://***/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FESR - Framework to evaluate Software Reliability based on software metrics 24

FESR - Framework to evaluate Software Reliability based on s...

引用

8th International Conference on High Performance Compilation, Computing and Communications, HP3C 2024

作者： Fahad, Hurriya Ahmed, Irfan Mahmood, Jabar Saman Batool, Khadija Ali, Qasim Department of Computer Science University of Sialkot Sialkot Pakistan State Key Laboratory of Blockchain and Data Security School of Cyber Science and Technology College of Computer Science and Technology Zhejiang University Zhejiang Hangzhou310007 China

ISBN: (纸本)9798400716904

Evaluating reliability of software is hot concern for decision makers and software engineers seeing as if we assess, it cannot be mastered. It is common that reliability of system stratum could be employed for evaluating growth of testing of system with help of comparison of failure of currently implemented software with required system. It is also generic that reliability of system echelon assures improved utilization by the user consequently enhanced contentment of customers. In this paper, our goal is to put forward a meticulously analysis of reliability measurement process. As the existing approaches still lack software reliability, quality and its growth, successful generation of test cases, scalability with large software systems, cost and customer satisfaction. we have projected a new framework of software reliability measurement process based on software metrics. Our model is evaluated by comparing it with an existing model and a published case study. The control experiment is used to evaluate FESR Framework. © 2024 ACM.

关键词： Software quality

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：