检索结果-内蒙古大学图书馆

A Prompting-based Approach for Adversarial Example Generation and Robustness Enhancement

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Yuting Huang, Pei Cao, Juan Li, Jintao Lin, Yun Dong, Jin Song Ma, Feifei Zhang, Jian Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Beijing China National University of Singapore Singapore Laboratory of Parallel Software and Computational Science ISCAS Beijing China

Recent years have seen the wide application of NLP models in crucial areas such as finance, medical treatment, and news media, raising concerns of the model robustness and vulnerabilities. In this paper, we propose a novel prompt-based adversarial attack to compromise NLP models and robustness enhancement technique. We first construct malicious prompts for each instance and generate adversarial examples via mask-and-filling under the effect of a malicious purpose. Our attack technique targets the inherent vulnerabilities of NLP models, allowing us to generate samples even without interacting with the victim NLP model, as long as it is based on pre-trained language models (PLMs). Furthermore, we design a prompt-based adversarial training method to improve the robustness of PLMs. As our training method does not actually generate adversarial samples, it can be applied to large-scale training sets efficiently. The experimental results show that our attack method can achieve a high attack success rate with more diverse, fluent and natural adversarial examples. In addition, our robustness enhancement method can significantly improve the robustness of models to resist adversarial attacks. Our work indicates that prompting paradigm has great potential in probing some fundamental flaws of PLMs and fine-tuning them for downstream tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Natural language processing systems

A Hybrid Routing Algorithm based on Destruction Resistance Cost and Reliability in Flying Ad-Hoc Networks 7

学校读者我要写书评

暂无评论

A Hybrid Routing Algorithm based on Destruction Resistance C...

7th International Conference on Computer and Communications, ICCC 2021

作者： Guo, Kun Wang, Dongbin Zhi, Hui Gao, Yibo Zhang, Tao Lv, Tiejun Lu, Yueming Beijing University of Posts and Telecommunications Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing China Beijing University of Posts and Telecommunications National Engineering Laboratory For Mobile Network Beijing China TravelSky Technology Limited Beijing China Beijing University of Posts and Telecommunications Cyberspace Security Research Center Peng Cheng Laboratory Beijing China China Academy of Launch Vehicle Technology Beijing China

ISBN: (纸本)9781665409506

Existing routing algorithms in Flying Ad-Hoc Net- works (FANETs) lack the optimization consideration of destruction resistance cost caused by routing recovery when some nodes fail suddenly. In this paper, we propose a hybrid routing algorithm based on destruction resistance cost and reliability. Based on the real-time network topology and network state, the algorithm can provide a multi-parameters-based routing path with low destruction resistance cost for communication transmission. It can ensure that the main routing path can be quickly recovered after interruption and reduce the process of discovering new routing paths. We have constructed a variety of simulation scenarios to analyze the proposed algorithm and the existing algorithms. The simulation results show that the pro- posed algorithm has good performance in reducing destruction resistance cost. © 2021 IEEE.

关键词： Routing algorithms

An in-depth exploration of LAMOST Unknown spectra based on density clustering

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Hai-Feng Yin, Xiao-Na Cai, Jiang-Hui Yang, Yu-Qing Luo, A-Li Bai, Zhong-Rui Zhou, Li-Chan Zhao, Xu-Jun Xun, Ya-Ling Shanxi Key Laboratory of Big Data Analysis and Parallel Computing Taiyuan University of Science and Technology Taiyuan030024 China School of Computer Science and Technology North University of China Taiyuan030051 China National Astronomical Observatories Chinese Academy of Sciences Beijing100101 China School of Computer Science and Technology Taiyuan University of Science and Technology Taiyuan030024 China

LAMOST (Large Sky Area Multi-Object Fiber Spectroscopic Telescope) has completed the observation of nearly 20 million celestial objects, including a class of spectra labeled ‘Unknown’. Besides low signal-to-noise ratio, these spectra often show some anomalous features that do not work well with current templates. In this paper, a total of 638,000 ‘Unknown’ spectra from LAMOST DR5 are selected, and an unsupervised-based analytical framework of ‘Unknown’ spectra named SA-Frame (Spectra Analysis-Frame) is provided to explore their origins from different perspectives. The SA-Frame is composed of three parts: NAPC-Spec clustering, characterization and origin analysis. First, NAPC-Spec(Nonparametric density clustering algorithm for spectra) characterizes different features in the"unknown" spectrum by adjusting the influence space and divergence distance to minimize the effects of noise and high dimensionality, resulting in 13 types. Second, characteristic extraction and representation of clustering results are carried out based on spectral lines and continuum, where these 13 types are characterized as regular spectra with low S/Ns, splicing problems, suspected galactic emission signals, contamination from city light and un-gregarious type respectively. Third, a preliminary analysis of their origins is made from the characteristics of the observational targets, contamination from the sky, and the working status of the instruments. These results would be valuable for improving the overall data quality of large-scale spectral surveys. Copyright © 2023, The Authors. All rights reserved.

关键词： Clustering algorithms

Dfier: A Directed Vulnerability Verifier for Ethereum Smart Contracts

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Wang, Zeli Dai, Weiqi Li, Ming Choo, Kim-Kwang Raymond Zou, Deqing Chongqing Key Laboratory of Computational Intelligence Key Laboratory of Big Data Intelligent Computing Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing40065 China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Department of Information Systems and Cyber Security University of Texas at San Antonio San Antonio United States

Existing smart contract vulnerability identification approaches mainly focus on complete program detection. Consequently, lots of known potentially vulnerable locations need manual verification, which is energy-exhaustive and error-prone. Fuzzing is an effective way to detect vulnerabilities. However, current fuzzers cannot effectively probe these suspicious targets because they overlook two key factors: exploring all paths toward the targets and providing high-quality directed seed inputs. This paper presents a Directed vulnerability veriFier (DFier), elaborating effective transaction sequences with directed inputs for the fuzzer, to focus on analyzing target paths and automatically detect whether the given locations are vulnerable. Specifically, DFier fuses the effectiveness of static analysis and the efficiency of fuzzing. The static analysis helps locate target paths and generate directed inputs for the fuzzer under three heuristic strategies. The first prefers inputs with the larger possibility of triggering potential vulnerabilities based on target features. The second guides the value mutation to satisfy the path constraints. The third adequately leverages execution information to help find exploits faster. Extensive experiments demonstrate that DFier is effective in verifying contract security, compared with three existing contract fuzzers (i.e., contractFuzzer, sFuzz, and conFuzzius). And the performance losses are in an acceptable range. © 2023, The Authors. All rights reserved.

关键词： Smart contract

UCL-AST: Active Self-Training with Uncertainty-Aware Clouded Logits for Few-Shot Text Classification

学校读者我要写书评

暂无评论

UCL-AST: Active Self-Training with Uncertainty-Aware Clouded...

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Yi Xu Jie Hu Zhiqiao Gao Jinpeng Chen School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education Beijing China China Telecom Corporation Limited Research Institute Beijing China

Although the recent advances in pre-training language models have achieved great success and migrated annotation bottleneck for many tasks, the task-specific fine-tuning for text classification still requires thousands of labeled samples or even more. When few human annotations are available, active self-training is one of the efficient approaches for reducing human annotation costs which integrates pseudo labels of self-training into the procedure of active learning. The traditional active self-training approaches mix manual labels and pseudo labels indistinguishably without considering the impact of active learning and self-training on each other. There are two problems for active self-training in few-shot text classification: (1) The noise in a large number of pseudo-labels may mislead the model training. (2) The confusing samples in overlap boundaries between classes are especially difficult to identify correctly with a few labels. To solve these problems, we propose UCL-AST, an active self-training framework that boosts the performance of the active teacher model to provide superior pseudo labels for the self-training student model and facilitates the active teacher model to learn more clear class boundaries with uncertainty-aware clouded logits in few-shot. The extensive experiments and visualization analysis have demonstrated the effectiveness of the proposed framework on four datasets compared with state-of-the-art methods.

关键词： Training Visualization Uncertainty Costs Annotations Text categorization Measurement uncertainty

Detecting JVM JIT Compiler Bugs via Exploring Two-Dimensional Input Spaces

学校读者我要写书评

暂无评论

Detecting JVM JIT Compiler Bugs via Exploring Two-Dimensiona...

International Conference on Software Engineering (ICSE)

作者： Haoxiang Jia Ming Wen Zifan Xie Xiaochen Guo Rongxin Wu Maolin Sun Kang Chen Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology China Hubei Key Laboratory of Distributed System Security Services Computing Technology and System Lab Cluster and Grid Computing Lab. Hubei Engineering Research Center on Big Data Security National Engineering Research Center for Big Data Technology and System School of Informatics Xiamen University China School of Computer Science and Technology Huazhong University of Science and Technology China

Java Virtual Machine (JVM) is the fundamental software system that supports the interpretation and execution of Java bytecode. To support the surging performance demands for the increasingly complex and large-scale Java programs, Just-In-Time (JIT) compiler was proposed to perform sophisticated runtime optimization. However, this inevitably induces various bugs, which are becoming more pervasive over the decades and can often cause significant consequences. To facilitate the design of effective and efficient testing techniques to detect JIT compiler bugs. This study first performs a preliminary study aiming to understand the characteristics of JIT compiler bugs and the corresponding triggering test cases. Inspired by the empirical findings, we propose JOpFuzzer, a new JVM testing approach with a specific focus on JIT compiler bugs. The main novelty of JOpFuzzer is embodied in three aspects. First, besides generating new seeds, JOpFuzzer also searches for diverse configurations along the new dimension of optimization options. Second, JOpFuzzer learns the correlations between various code features and different optimization options to guide the process of seed mutation and option exploration. Third, it leverages the profile data, which can reveal the program execution information, to guide the fuzzing process. Such nov-elties enable JOpFuzzer to effectively and efficiently explore the two-dimensional input spaces. Extensive evaluation shows that JOpFuzzer outperforms the state-of-the-art approaches in terms of the achieved code coverages. More importantly, it has detected 41 bugs in OpenJDK, and 25 of them have already been confirmed or fixed by the corresponding developers.

关键词：

Multi-representation knowledge distillation for audio classification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Gao, Liang Xu, Kele Wang, Huaimin Peng, Yuxing National Key Laboratory of Parallel and Distributed Processing College of Computer National University of Defense Technology Changsha410073 China

As an important component of multimedia analysis tasks, audio classification aims to discriminate between different audio signal types and has received intensive attention due to its wide applications. Generally speaking, the raw signal can be transformed into various representations (such as Short Time Fourier Transform and Mel Frequency Cepstral Coefficients), and information implied in different representations can be complementary. Ensembling the models trained on different representations can greatly boost the classification performance, however, making inference using a large number of models is cumbersome and computationally expensive. In this paper, we propose a novel end-to-end collaborative learning framework for the audio classification task. The framework takes multiple representations as the input to train the models in parallel. The complementary information provided by different representations is shared by knowledge distillation. Consequently, the performance of each model can be significantly promoted without increasing the computational overhead in the inference stage. Extensive experimental results demonstrate that the proposed approach can improve the classification performance and achieve state-of-the-art results on both acoustic scene classification tasks and general audio tagging tasks. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolutional neural networks

On the Effectiveness of Function-Level Vulnerability Detectors for Inter-Procedural Vulnerabilities

学校读者我要写书评

暂无评论

On the Effectiveness of Function-Level Vulnerability Detecto...

International Conference on Software Engineering (ICSE)

作者： Zhen Li Ning Wang Deqing Zou Yating Li Ruqian Zhang Shouhuai Xu Chao Zhang Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Jin YinHu Laboratory Wuhan China Department of Computer Science University of Colorado Colorado Springs Colorado Springs Colorado USA Institute for Network Sciences and Cyberspace Tsinghua University Beijing China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798400702174

ISBN: (纸本)9798350382143

Software vulnerabilities are a major cyber threat and it is important to detect them. One important approach to detecting vulnerabilities is to use deep learning while treating a program function as a whole, known as function-level vulnerability detectors. However, the limitation of this approach is not understood. In this paper, we investigate its limitation in detecting one class of vulnerabilities known as inter-procedural vulnerabilities, where the to-be-patched statements and the vulnerability-triggering statements belong to different functions. For this purpose, we create the first Inter -Procedural Vulnerability Dataset (InterPVD) based on C/C++ open-source software, and we propose a tool dubbed VulTrigger for identifying vulnerability-triggering statements across functions. Experimental results show that VulTrigger can effectively identify vulnerability-triggering statements and inter-procedural vulnerabilities. Our findings include: (i) inter-procedural vulnerabilities are prevalent with an average of 2.8 inter-procedural layers; and (ii) function-level vulner-ability detectors are much less effective in detecting to-be-patched functions of inter-procedural vulnerabilities than detecting their counterparts of intra-procedural vulnerabilities.

关键词： Deep learning Detectors Open source software Software engineering

ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Xianlong Hu, Shengshan Zhang, Yechao Zhou, Ziqi Zhang, Leo Yu Xu, Peng Wan, Wei Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Information and Communication Technology Griffith University SouthportQLD4215 Australia

Clean-label indiscriminate poisoning attacks add invisible perturbations to correctly labeled training images, thus dramatically reducing the generalization capability of the victim models. Recently, defense mechanisms such as adversarial training, image transformation techniques, and image purification have been proposed. However, these schemes are either susceptible to adaptive attacks, built on unrealistic assumptions, or only effective against specific poison types, limiting their universal applicability. In this research, we propose a more universally effective, practical, and robust defense scheme called ECLIPSE. We first investigate the impact of Gaussian noise on the poisons and theoretically prove that any kind of poison will be largely assimilated when imposing sufficient random noise. In light of this, we assume the victim has access to an extremely limited number of clean images (a more practical scene) and subsequently enlarge this sparse set for training a denoising probabilistic model (a universal denoising tool). We then introduce Gaussian noise to absorb the poisons and apply the model for denoising, resulting in a roughly purified dataset. Finally, to address the trade-off of the inconsistency in the assimilation sensitivity of different poisons by Gaussian noise, we propose a lightweight corruption compensation module to effectively eliminate residual poisons, providing a more universal defense approach. Extensive experiments demonstrate that our defense approach outperforms 10 state-of-the-art defenses. We also propose an adaptive attack against ECLIPSE and verify the robustness of our defense scheme. Our code is available at https://***/CGCL-codes/ECLIPSE. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks