检索结果-内蒙古大学图书馆

Code is not natural language: unlock the power of semantics-oriented graph representation for binary code similarity detection 24

学校读者我要写书评

暂无评论

Code is not natural language: unlock the power of semantics-...

Proceedings of the 33rd USENIX Conference on Security Symposium

作者： Haojie He Xingwei Lin Ziang Weng Ruijie Zhao Shuitao Gan Libo Chen Yuede Ji Jiashui Wang Zhi Xue School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Ant Group Laboratory for Advanced Computing and Intelligence Engineering University of North Texas

ISBN: (纸本)9781939133441

Binary code similarity detection (BCSD) has garnered significant attention in recent years due to its crucial role in various binary code-related tasks, such as vulnerability search and software plagiarism detection. Currently, BCSD systems are typically based on either instruction streams or control flow graphs (CFGs). However, these approaches have limitations. Instruction stream-based approaches treat binary code as natural languages, overlooking well-defined semantic structures. CFG-based approaches exploit only the control flow structures, neglecting other essential aspects of code. Our key insight is that unlike natural languages, binary code has well-defined semantic structures, including intra-instruction structures, inter-instruction relations (e.g., def-use, branches), and implicit conventions (e.g. calling conventions). Motivated by that, we carefully examine the necessary relations and structures required to express the full semantics and expose them directly to the deep neural network through a novel semantics-oriented graph representation. Furthermore, we propose a lightweight multi-head softmax aggregator to effectively and efficiently fuse multiple aspects of the binary code. Extensive experiments show that our method significantly outperforms the state-of-the-art (e.g., in the x64-XC retrieval experiment with a pool size of 10000, our method achieves a recall score of 184%, 220%, and 153% over Trex, GMN, and jTrans, respectively).

关键词：

Quantum Direct Steganography Scheme Based on Modified Generator Projection Directions of Steane Code over a Single-Type Pauli Channel

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Hao, Chaolong Ma, Quangong Qu, Dan Shi, Dawei School of Information Systems Engineering Information Engineering University 62 Science Avenue Zhengzhou450001 China Laboratory for Advanced Computing and Intelligence Engineering Jiangsu Wuxi214000 China

In quantum mechanics, measurements of a quantum state in various directions yield distinct outcomes, a principle that forms the foundation of quantum communication theory. This paper expands upon this concept by introducing a method to modify generator projection directions (MGPD) within quantum stabilizer codes. Employing the Steane code ((7, 1, 3) code), as a fundamental carrier, we develop a novel scheme for direct quantum steganography across a single-type Pauli channel. The infeasibility of eavesdropping decoding under MGPD is proven. We detail the steganographic encoding and decoding schemes, corresponding quantum circuits, and eavesdropping detection principles. We also use a’Sudoku’-style strategy to balance steganographic error probabilities and provide the complete steganography protocol. Relative to existing studies, the MGPD method achieves embedding rates approaching and attaining the upper limit of the information capacity for the (n, k, d) = (7, 1, 3) code within a noise probability range of approximately 1/(n + 1) = 12.5%. It also reduces the consumption of auxiliary keys from O(log (N)) to O(1), while enabling eavesdropping detection and steganography of arbitrary quantum states. We investigate its potential applications in quantum communication and assess its benefits in the context of secret information transmission and eavesdropping detection in noisy channels. Although the MGPD method incorporates certain idealized assumptions and limitations, it provides novel perspectives on the concealment of quantum information. Copyright © 2025, The Authors. All rights reserved.

关键词： Decoding

Task-Oriented 6-DoF Grasp Pose Detection in Clutters

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, An-Lan Chen, Nuo Lin, Kun-Yu Li, Yuan-Ming Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

In general, humans would grasp an object differently for different tasks, e.g., "grasping the handle of a knife to cut" vs. "grasping the blade to hand over". In the field of robotic grasp pose detection research, some existing works consider this task-oriented grasping and made some progress, but they are generally constrained by low-DoF gripper type or non-cluttered setting, which is not applicable for human assistance in real life. With an aim to get more general and practical grasp models, in this paper, we investigate the problem named Task-Oriented 6-DoF Grasp Pose Detection in Clutters (TO6DGC), which extends the task-oriented problem to a more general 6-DOF Grasp Pose Detection in Cluttered (multi-object) scenario. To this end, we construct a large-scale 6-DoF task-oriented grasping dataset, 6-DoF Task Grasp (6DTG), which features 4391 cluttered scenes with over 2 million 6-DoF grasp poses. Each grasp is annotated with a specific task, involving 6 tasks and 198 objects in total. Moreover, we propose One-Stage TaskGrasp (OSTG), a strong baseline to address the TO6DGC problem. Our OSTG adopts a task-oriented point selection strategy to detect where to grasp, and a task-oriented grasp generation module to decide how to grasp given a specific task. To evaluate the effectiveness of OSTG, extensive experiments are conducted on 6DTG. The results show that our method outperforms various baselines on multiple metrics. Real robot experiments also verify that our OSTG has a better perception of the task-oriented grasp points and 6-DoF grasp poses. © 2025, CC BY.

关键词： Clutter (information theory)

MaintaAvatar: A Maintainable Avatar Based on Neural Radiance Fields by Continual Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Gu, Shengbo Qiu, Yu-Kun Tang, Yu-Ming Wu, Ancong Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Peng Cheng Laboratory Shenzhen China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

The generation of a virtual digital avatar is a crucial research topic in the field of computer vision. Many existing works utilize Neural Radiance Fields (NeRF) to address this issue and have achieved impressive results. However, previous works assume the images of the training person are available and fixed while the appearances and poses of a subject could constantly change and increase in real-world scenarios. How to update the human avatar but also maintain the ability to render the old appearance of the person is a practical challenge. One trivial solution is to combine the existing virtual avatar models based on NeRF with continual learning methods. However, there are some critical issues in this approach: learning new appearances and poses can cause the model to forget past information, which in turn leads to a degradation in the rendering quality of past appearances, especially color bleeding issues, and incorrect human body poses. In this work, we propose a maintainable avatar (MaintaAvatar) based on neural radiance fields by continual learning, which resolves the issues by utilizing a Global-Local Joint Storage Module and a Pose Distillation Module. Overall, our model requires only limited data collection to quickly fine-tune the model while avoiding catastrophic forgetting, thus achieving a maintainable virtual avatar. The experimental results validate the effectiveness of our MaintaAvatar model. © 2025, CC BY.

关键词： Federated learning

Multi-Granular Multimodal Clue Fusion for Meme Understanding

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zheng, Li Fei, Hao Dai, Ting Peng, Zuquan Li, Fei Ma, Huisheng Teng, Chong Ji, Donghong Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Wuhan China National University of Singapore Singapore Singapore Laboratory for Advanced Computing and Intelligence Engineering Wuxi China North China Institute of Computing Technology Beijing China

With the continuous emergence of various social media platforms frequently used in daily life, the multimodal meme understanding (MMU) task has been garnering increasing attention. MMU aims to explore and comprehend the meanings of memes from various perspectives by performing tasks such as metaphor recognition, sentiment analysis, intention detection, and offensiveness detection. Despite making progress, limitations persist due to the loss of fine-grained metaphorical visual clue and the neglect of multimodal text-image weak correlation. To overcome these limitations, we propose a multi-granular multimodal clue fusion model (MGMCF) to advance MMU. Firstly, we design an object-level semantic mining module to extract object-level image feature clues, achieving fine-grained feature clue extraction and enhancing the model’s ability to capture metaphorical details and semantics. Secondly, we propose a brand-new global-local cross-modal interaction model to address the weak correlation between text and images. This model facilitates effective interaction between global multimodal contextual clues and local unimodal feature clues, strengthening their representations through a bidirectional cross-modal attention mechanism. Finally, we devise a dual-semantic guided training strategy to enhance the model’s understanding and alignment of multimodal representations in the semantic space. Experiments conducted on the widely-used MET-MEME bilingual dataset demonstrate significant improvements over state-of-the-art baselines. Specifically, there is an 8.14% increase in precision for offensiveness detection task, and respective accuracy enhancements of 3.53%, 3.89%, and 3.52% for metaphor recognition, sentiment analysis, and intention detection tasks. These results, underpinned by in-depth analyses, underscore the effectiveness and potential of our approach for advancing MMU. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

iManip: Skill-Incremental Learning for Robotic Manipulation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zheng, Zexin Cai, Jia-Feng Wu, Xiao-Ming Wei, Yi-Lin Tang, Yu-Ming Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Pengcheng Lab China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

The development of a generalist agent with adaptive multiple manipulation skills has been a long-standing goal in the robotics community. In this paper, we explore a crucial task, skill-incremental learning, in robotic manipulation, which is to endow the robots with the ability to learn new manipulation skills based on the previous learned knowledge without re-training. First, we build a skill-incremental environment based on the RLBench benchmark, and explore how traditional incremental methods perform in this setting. We find that they suffer from severe catastrophic forgetting due to the previous methods on classification overlooking the characteristics of temporality and action complexity in robotic manipulation tasks. Towards this end, we propose an incremental Manipulation framework, termed iManip, to mitigate the above issues. We firstly design a temporal replay strategy to maintain the integrity of old skills when learning new skill. Moreover, we propose the extendable PerceiverIO, consisting of an action prompt with extendable weight to adapt to new action primitives in new skill. Extensive experiments show that our framework performs well in Skill-Incremental Learning. Codes of the skill-incremental environment with our framework will be open-source. Copyright © 2025, The Authors. All rights reserved.

关键词： Robot learning

Audio-Visual Collaborative Learning for Weakly Supervised Video Anomaly Detection

学校读者我要写书评

暂无评论

IEEE Transactions on Multimedia 2025年

作者： Meng, Jingke Tian, Huilin Lin, Ge Hu, Jian-Fang Zheng, Wei-Shi Sun Yat-sen University School of Computer Science and Engineering Guangzhou China Peng Cheng Laboratory Shenzhen518005 China Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen University Ministry of Education China

Weakly supervised anomaly detection is to identify the time window when an anomaly event happened based on the video-level label indicating whether the video contains anomaly event or not. Recent efforts have focused on leveraging multi-modal data, specifically combining visual and audio information, to enhance detection accuracy. While some studies have explored intra-video separation techniques, the primary emphasis remains on distinguishing potentially anomalous events scoring highest from those scoring lowest as normal events. Nevertheless, challenges persist in delineating boundaries between normal and abnormal events, particularly when visual differences are subtle. Our proposed framework, called Audio-Visual Collaborative Learning (AVCL), addresses the challenge of ambiguity in weakly supervised anomaly detection. Our core idea centers around utilizing both audio track variations and the perceptual robustness of visual information to detect and differentiate challenging cases, which composed of two essential modules: the Audio-Visual collaborative Hard cases Separation (AVHS) module and the Multi-modal Mutual Learning (MML) module. The AVHS module aims to address the challenge of discerning visually ambiguous clips in anomaly videos, differentiating between normal and abnormal events. To further improve detection accuracy, we introduce the Multi-modal Mutual Learning (MML) module, and this module enables a process of mutual learning to facilitate the exchange of knowledge and expertise between the single-modal branch and the multi-modal branch. We demonstrate that the proposed approach achieves state-of-the-art detection performance on benchmarks of XD-Violence and CCTV-Fightssub datasets. © 1999-2012 IEEE.

关键词： Self-supervised learning

WiViPose: A Video-aided Wi-Fi Framework for Environment-Independent 3D Human Pose Estimation

学校读者我要写书评

暂无评论

IEEE Transactions on Multimedia 2025年

作者： Zhang, Lei Ning, Haoran Tang, Jiaxin Chen, Zhenxiang Zhong, Yaping Han, Yahong Tianjin University College of Intelligence and Computing the Tianjin Key Laboratory of Advanced Network Technology and Application Tianjin300050 China Key Laboratory of Computing Power Network and Information Security Ministry of Education China University of Jinan Shandong Provincial Key Laboratory of Ubiquitous Intelligent Computing the School of Information Science and Engineering Jinan250022 China Wuhan Sports University Sports Big-data Research Center Wuhan430079 China Tianjin University College of Intelligence and Computing the Tianjin Key Laboratory of Machine Learning Tianjin300350 China

The inherent complexity of Wi-Fi signals makes video-aided Wi-Fi 3D pose estimation difficult. The challenges include the limited generalizability of the task across diverse environments, its significant signal heterogeneity, and its inadequate ability to analyze local and geometric information. To overcome these challenges, we introduce WiViPose, a video-aided Wi-Fi framework for 3D pose estimation, which attains enhanced cross-environment generalization through cross-layer optimization. Bilinear temporal-spectral fusion (BTSF) is initially used to fuse the time-domain and frequency-domain features derived from Wi-Fi. Video features are derived from a multiresolution convolutional pose machine and enhanced by local self-attention. Cross-modality data fusion is facilitated through an attention-based transformer, with the process further refined under a supervisory mechanism. WiViPose demonstrates effectiveness by achieving an average percentage of correct keypoints (PCK)@50 of 91.01% across three typical indoor environments. © 2025 IEEE.

关键词： Frequency domain analysis

Non-Markovian effect enhanced quantum noises in a coherent Ising machine

学校读者我要写书评

暂无评论

Optics Express 2025年第11期33卷 22208-22221页

作者： Chen-Rui Fan Bo Lu Yi-Xuan Yao Qing Ai Chuan Wang School of Artificial Intelligence Beijing Normal University Beijing 100875 China Laboratory for Advanced Computing and Intelligence Engineering Zhengzhou 450001 China lubo@*** School of Physics and Astronomy Applied Optics Beijing Area Major Laboratory Beijing 100875 China Key Laboratory of Multiscale Spin Physics Ministry of Education Beijing Normal University Beijing 100875 China wangchuan@***

Combinatorial optimization problems (COPs) constitute a fundamental class of computational challenges with extensive applications across scientific and industrial domains. The emergence of the coherent Ising machine (CIM) as a computational paradigm has demonstrated exceptional capabilities in rapidly generating arbitrary spin configurations and effectively solving large-scale COPs. Despite its promising potential, the CIM framework encounters an inherent limitation related to amplitude heterogeneity. Current approaches to this limitation primarily rely on Gaussian approximations to model quantum noise in the system’s amplitude dynamics within the original CIM framework. However, these methods generally fail to account for the temporal and periodic non-Markovian characteristics of pulses in practical environments. In this study, we introduce temporally correlated non-Markovian noise into the dynamics of both conventional and spiking neural network-based CIM systems, investigating their performance through comprehensive hyperparameter analysis. Our method incorporates a detailed examination of hyperparameter selection and its influence on algorithmic efficiency. Through extensive numerical simulations, we demonstrate that the integration of non-Markovian noise significantly accelerates variance evolution in both canonical coordinates and amplitude dynamics over time. The proposed approach not only exhibits enhanced computational performance but also shows superior scalability for large-scale problem instances. These findings suggest that our approach offers distinct advantages in addressing complex COPs, potentially opening new avenues for efficient optimization in various applications.

关键词： Neural networks Nonlinear optical fibers Numerical simulation Optical parametric oscillators Optical systems Quantum noise