检索结果-内蒙古大学图书馆

Verification of Bit-Flip Attacks against Quantized Neural Networks

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Yedi Huang, Lei Gao, Pengfei Song, Fu Sun, Jun Dong, Jin Song National University of Singapore Singapore ShanghaiTech University China ByteDance Inc China Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China Singapore Management University Singapore University of Chinese Academy of Sciences China Nanjing Institute of Software Technology China National University of Singapore Singapore Singapore ShanghaiTech University Shanghai China ByteDance Inc Beijing China Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China Singapore Management University Singapore Singapore

In the rapidly evolving landscape of neural network security, the resilience of neural networks against bit-flip attacks (i.e., an attacker maliciously flips an extremely small amount of bits within its parameter storage memory system to induce harmful behavior), has emerged as a relevant area of research. Existing studies suggest that quantization may serve as a viable defense against such attacks. Recognizing the documented susceptibility of real-valued neural networks to such attacks and the comparative robustness of quantized neural networks (QNNs), in this work, we introduce BFAVerifier, the first verification framework designed to formally verify the absence of bit-flip attacks or to identify all vulnerable parameters in a sound and rigorous manner. BFAVerifier comprises two integral components: an abstraction-based method and an MILP-based method. Specifically, we first conduct a reachability analysis with respect to symbolic parameters that represent the potential bit-flip attacks, based on a novel abstract domain with a sound guarantee. If the reachability analysis fails to prove the resilience of such attacks, then we encode this verification problem into an equivalent MILP problem which can be solved by off-the-shelf solvers. Therefore, BFAVerifier is sound, complete, and reasonably efficient. We conduct extensive experiments, which demonstrate its effectiveness and efficiency across various network architectures, quantization bit-widths, and adversary capabilities. © 2025, CC BY.

关键词： Neural networks

HYBRID VALUE ESTIMATION FOR OFF-POLICY EVALUATION AND OFFLINE REINFORCEMENT LEARNING

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jin, Xue-Kun Liu, Xu-Hui Jiang, Shengyi Yu, Yang National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science The University of Hong Kong Hong Kong Polixir.ai

Value function estimation is an indispensable subroutine in reinforcement learning, which becomes more challenging in the offline setting. In this paper, we propose Hybrid Value Estimation (HVE) to reduce value estimation error, which trades off bias and variance by balancing between the value estimation from offline data and the learned model. Theoretical analysis discloses that HVE enjoys a better error bound than the direct methods. HVE can be leveraged in both off-policy evaluation and offline reinforcement learning settings. We, therefore, provide two concrete algorithms Off-policy HVE (OPHVE) and Model-based Offline HVE (MOHVE), respectively. Empirical evaluations on MuJoCo tasks corroborate the theoretical claim. OPHVE outperforms other off-policy evaluation methods in all three metrics measuring the estimation effectiveness, while MOHVE achieves better or comparable performance with state-of-the-art offline reinforcement learning algorithms. We hope that HVE could shed some light on further research on reinforcement learning from fixed data. © 2022, CC BY.

关键词： Reinforcement learning

On the Generalization and Causal Explanation in Self-Supervised Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Qiang, Wenwen Song, Zeen Gu, Ziyin Li, Jiangmeng Zheng, Changwen Sun, Fuchun Xiong, Hui The National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China The National Key Laboratory of Space Integrated Information System Department of Computer Science and Technology Tsinghua University Beijing China The Hong Kong University of Science and Technology China

Self-supervised learning (SSL) methods learn from unlabeled data and achieve high generalization performance on downstream tasks. However, they may also suffer from overfitting to their training data and lose the ability to adapt to new tasks. To investigate this phenomenon, we conduct experiments on various SSL methods and datasets and make two observations: (1) Overfitting occurs abruptly in later layers and epochs, while generalizing features are learned in early layers for all epochs;(2) Coding rate reduction can be used as an indicator to measure the degree of overfitting in SSL models. Based on these observations, we propose Undoing Memorization Mechanism (UMM), a plug-and-play method that mitigates overfitting of the pre-trained feature extractor by aligning the feature distributions of the early and the last layers to maximize the coding rate reduction of the last layer output. The learning process of UMM is a bi-level optimization process. We provide a causal analysis of UMM to explain how UMM can help the pre-trained feature extractor overcome overfitting and recover generalization. We also demonstrate that UMM significantly improves the generalization performance of SSL methods on various downstream tasks. The source code is to be released at https://***/ZeenSong/UMM. © 2024, CC BY.

关键词： Self-supervised learning

JobFormer: Skill-Aware Job Recommendation with Semantic-Enhanced Transformer

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Guan, ZhiHao Yang, Jia-Qi Yang, Yang Zhu, Hengshu Li, Wenjie Xiong, Hui the Nanjing University of Science and Technology Nanjing210094 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China Career Science Lab BOSS Zhipin Beijing100028 China the Hong Kong Polytechnic University Hong Kong the Artificial Intelligence Thrust The Hong Kong University of Science and Technology Guangzhou China PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China

Job recommendation aims to provide potential talents with suitable job descriptions (JDs) consistent with their career trajectory, which plays an essential role in proactive talent recruitment. In real-world management scenarios, the available JD-user records always consist of JDs, user profiles, and click data, in which the user profiles are typically summarized as the user’s skill distribution for privacy reasons. Although existing sophisticated recommendation methods can be directly employed, effective recommendation still has challenges considering the information deficit of JD itself and the natural heterogeneous gap between JD and user profile. To address these challenges, we proposed a novel skill-aware recommendation model based on the designed semantic-enhanced transformer to parse JDs and complete personalized job recommendation. Specifically, we first model the relative items of each JD and then adopt an encoder with the local-global attention mechanism to better mine the intra-job and inter-job dependencies from JD tuples. Moreover, we adopt a two-stage learning strategy for skill-aware recommendation, in which we utilize the skill distribution to guide JD representation learning in the recall stage, and then combine the user profiles for final prediction in the ranking stage. Consequently, we can embed rich contextual semantic representations for learning JDs, while skill-aware recommendation provides effective JD-user joint representation for click-through rate (CTR) prediction. To validate the superior performance of our method for job recommendation, we present a thorough empirical analysis of large-scale real-world and public datasets to demonstrate its effectiveness and interpretability. Copyright © 2024, The Authors. All rights reserved.

关键词： User profile

Federated Deep Recommendation System Based on Multi-View Feature Embedding

学校读者我要写书评

暂无评论

Federated Deep Recommendation System Based on Multi-View Fea...

International Conference on Data science and Advanced Analytics (DSAA)

作者： Xinna Wang Shunmei Meng Yanran Chen Qiyan Liu Rui Yuan Qianmu Li Department of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Business School University of Auckland Auckland New Zealand Computer Engineering University of Toronto Toronto Canada

ISBN: (纸本)9781665473316

The application of recommendation systems online services is becoming more and more extensive. However, most existing recommendation algorithms centralize multi-party information into a central processor, which may lead to the risk of privacy leakage. And many enterprises or institutions still have the problem that data cannot be shared. Federated learning has been introduced into recommendation algorithms for privacy- aware distributed learning. A typical federated learning is that each client uses local data to train a shared model, the server uses their gradient information to form a global model, and then each client updates. In this paper, we propose a federated deep recommendation algorithm called FedHe-mlp that applies a federated deep learning for data privacy protection, and combines heterogeneous information network (HIN) and matrix factorization technique for better prediction performance. First, each client obtains heterogeneous information through meta- paths, then we combine matrix factorization and heterogeneous information to mine the latent features and heterogeneous features of each client. Finally, We propose a deep neural network that considers features from multiple views. Extensive experiments on three public datasets demonstrate that FedHe- mlp can provide excellent convergence speed, recommendation accuracy, and communication efficiency while preserving data privacy.

关键词： Deep learning Training Data privacy Privacy Analytical models Federated learning Neural networks

MACRO: Incentivizing Multi-Leader Game-Based Pareto-Efficient Crowdsourcing for Video Analytics

学校读者我要写书评

暂无评论

MACRO: Incentivizing Multi-Leader Game-Based Pareto-Efficien...

International Conference on Data Engineering

作者： Yu Chen Sheng Zhang Ziying Zhou Xiaokun Wang Yu Liang Ning Chen Yuting Yan Mingjun Xiao Jie Wu Zhuzhong Qian Harry Xu State Key Lab. for Novel Software Technology Nanjing University P.R. China School of Systems Science Beijing Normal University China School of Computer and Electronic Information / School of Artificial Intelligence Nanjing Normal University China School of Computer Science and Technology University of Science and Technology of China P.R. China Center for Networked Computing Temple University USA Computer Science Department Samueli School of Engineering University of California Los Angeles USA

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

In recent years, many crowdsourcing platforms have emerged, using the resources of recruited workers to perform diverse outsourcing tasks, where the video analytics attracts much attention due to its practical implications. For maximum profits, platforms carefully choose the workers and determine the video analytics configurations to ensure accuracy; meanwhile, workers possess the flexibility to tailor the configurations for their indivi-dual gains, which makes it hard for platforms to optimize their profits considering the platform-worker conflicts. In this paper, we design an incentive mechanism for Multi-leader game-based video Analytics upon CROwdsourcing, named MACRO, to over-come the above situation. Under that mechanism, we first formu-late the utility optimization problems for platforms and workers, respectively. We then propose a dual ascent-based method to op-timally determine the video analytics configurations for a multi-platform game, ensuring Pareto efficiency. Moreover, in the context of a multi-leader game involving platform-worker conflicts, we design an incentive function with its incentive factor update strategy and propose an ADMM-based approach for maximizing incentives that motivate workers to contribute to the platforms' profits. Rigorous proofs demonstrate the linear convergence of the MACRO to the multi-leader Stackelberg equilibrium. Trace-driven experiments show that MACRO improves the Pareto efficiency by 26.3%, outperforming other approaches.

关键词： Crowdsourcing Accuracy Visual analytics Games Data engineering Outsourcing Task analysis

UltraEdit: Instruction-based Fine-Grained Image Editing at Scale

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhao, Haozhe Ma, Xiaojian Chen, Liang Si, Shuzheng Wu, Rujie An, Kaikai Yu, Peiyu Zhang, Minjia Li, Qing Chang, Baobao National Key Laboratory for Multimedia Information Processing Peking University China State Key Laboratory of General Artificial Intelligence BIGAI China School of Software and Microelectronics Peking University China Department of Computer Science and Technology Tsinghua University China School of Computer Science Peking University China UCLA United States UIUC United States

This paper presents ULTRAEDIT, a large-scale (~4M editing samples), automatically generated dataset for instruction-based image editing. Our key idea is to address the drawbacks in existing image editing datasets like InstructPix2Pix [10] and MagicBrush [71], and provide a systematic approach to producing massive and high-quality image editing samples. ULTRAEDIT offers several distinct advantages: 1) It features a broader range of editing instructions by leveraging the creativity of large language models (LLMs) alongside in-context editing examples from human raters;2) Its data sources are based on real images, including photographs and artworks, which provide greater diversity and reduced bias compared to datasets solely generated by text-to-image models;3) It also supports region-based editing, enhanced by high-quality, automatically produced region annotations. Our experiments show that canonical diffusion-based editing baselines trained on ULTRAEDIT set new records on MagicBrush and Emu-Edit benchmarks. Our analysis further confirms the crucial role of real image anchors and region-based editing data. The dataset, code, and models are available in ***/pkunlp-icler/UltraEdit. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

Deep Learning-based software Engineering: Progress, Challenges, and Opportunities

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Xiangping Hu, Xing Huang, Yuan Jiang, He Ji, Weixing Jiang, Yanjie Jiang, Yanyan Liu, Bo Liu, Hui Li, Xiaochen Lian, Xiaoli Meng, Guozhu Peng, Xin Sun, Hailong Shi, Lin Wang, Bo Wang, Chong Wang, Jiayi Wang, Tiantian Xuan, Jifeng Xia, Xin Yang, Yibiao Yang, Yixin Zhang, Li Zhou, Yuming Zhang, Lu Ministry of Education School of Computer Science Peking University Beijing100871 China School of Journalism and Communication Sun Yat-sen University Guangzhou510275 China School of Software Technology Zhejiang University Hangzhou310058 China School of Software Engineering Sun Yat-sen University Guangzhou510275 China School of Software Dalian University of Technology Dalian116024 China School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China School of Computer Science and Engineering Beihang University Beijing100191 China Institute of Information Engineering Chinese Academy of Sciences Beijing100864 China School of Computer Science Fudan University Shanghai200433 China School of Software Beihang University Beijing100191 China School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China School of Computer Science and Technology Harbin Institute of Technology Harbin150001 China School of Computer Science Wuhan University Wuhan430072 China Huawei Technologies Hangzhou China

Researchers have recently achieved significant advances in deep learning techniques, which in turn has substantially advanced other research disciplines, such as natural language processing, image processing, speech recognition, and software engineering. Various deep learning techniques have been successfully employed to facilitate software engineering tasks, including code generation, software refactoring, and fault localization. Many papers have also been presented in top conferences and journals, demonstrating the applications of deep learning techniques in resolving various software engineering tasks. However, although several surveys have provided overall pictures of the application of deep learning techniques in software engineering, they focus more on learning techniques, that is, what kind of deep learning techniques are employed and how deep models are trained or fine-tuned for software engineering tasks. We still lack surveys explaining the advances of subareas in software engineering driven by deep learning techniques, as well as challenges and opportunities in each subarea. To this end, in this paper, we present the first task-oriented survey on deep learning-based software engineering. It covers twelve major software engineering subareas significantly impacted by deep learning techniques. Such subareas spread out the through the whole lifecycle of software development and maintenance, including requirements engineering, software development, testing, maintenance, and developer collaboration. As we believe that deep learning may provide an opportunity to revolutionize the whole discipline of software engineering, providing one survey covering as many subareas as possible in software engineering can help future research push forward the frontier of deep learning-based software engineering more systematically. For each of the selected subareas, we highlight the major advances achieved by applying deep learning techniques with pointers to the available data

关键词： Life cycle

Deep Learning-Driven Simultaneous Layout Decomposition and Mask Optimization

学校读者我要写书评

暂无评论

Deep Learning-Driven Simultaneous Layout Decomposition and M...

作者： Zhong, Wei Hu, Shuxiang Ma, Yuzhe Yang, Haoyu Ma, Xiuyuan Yu, Bei DUTRU International School of Information Science and Engineering Dalian University of Technology Dalian China Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province Dalian116024 China

Combining multiple patterning lithography (MPL) and optical proximity correction (OPC) pushes the limit of 193-nm wavelength lithography to go further. Considering that layout decomposition may generate plenty of solutions with diverse printabilities, relying on conventional mask optimization (MO) process to select the best candidate for manufacturing is computationally expensive. Therefore, an accurate and efficient printability estimation is crucial and can significantly accelerate the layout decomposition and MO (LDMO) flow. In this article, we propose a convolutional neural network (CNN)-based prediction and integrate it into our new high-performance LDMO framework. The optimization process can be considerably improved as the decomposition quality has been inferred in the early phase. To facilitate the network training and ensure better estimation accuracy, we develop sampling strategies for both layout and decomposition. Moreover, we enhance the layout sampling approach by adopting autoencoder to distance evaluation that promises superior sampling results. The experimental results demonstrate the effectiveness and the efficiency of the proposed algorithms. © 1982-2012 IEEE.

关键词： Manufacture