检索结果-内蒙古大学图书馆

Enhancing information transmission security with stochastic codes

学校读者我要写书评

暂无评论

Enhancing information transmission security with stochastic ...

2024 Workshop on Classic, Quantum, and Post-Quantum Cryptography, CQPC 2024

作者： Zhurakovskyi, Bohdan Otrokh, Sergei Poliakov, Mykhailo Poliakov, Oleksii Skladannyi, Pavlo National Technical University of Ukraine Igor Sikorsky Kyiv Polytechnic Institute 37 Peremogy ave. Kyiv03056 Ukraine National University "Zaporizhzhia Polytechnic" 64 Zhukovsky str. Zaporizhzhia69063 Ukraine Borys Grinchenko Kyiv Metropolitan University 18/2 Bulvarno-Kudriavska str. Kyiv04053 Ukraine

All known algorithms of cryptographic systems, which have the property of interference resistance, are based on codes that detect and correct errors. This work proposes a study of stochastic codes for their potential use in cryptographic system algorithms. For stochastic codes, there is a "copy" decoding algorithm when two or more values of a code block of a stochastic code, including (n, n-1) is a code with the detection of errors that are the same during their transmission, it is possible to carry out joint decoding of the extended code with bug fixes. Furthermore, the number of errors that can be corrected in a single block of the extended code is significantly higher than the total number of errors that can be corrected in each block. To simplify the comparative analysis, we converted the given value Pq to the probability of flipping the binary symbol P0. We estimated this probability for different degrees of error grouping using the Portov model with the coefficient a. © 2024 Copyright for this paper by its authors.

关键词： coding errors

Towards Understanding the Characteristics of Code Generation errors Made by Large Language Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Zhijie Zhou, Zijie Song, Da Huang, Yuheng Chen, Shengmai Ma, Lei Zhang, Tianyi University of Alberta EdmontonAB Canada University of Illinois Urbana-Champaign ChampaignIL United States The University of Tokyo Tokyo Japan Purdue University West LafayetteIN United States

Large Language Models (LLMs) have demonstrated unprecedented capabilities in code generation. However, there remains a limited understanding of code generation errors that LLMs can produce. To bridge the gap, we conducted an in-depth analysis of code generation errors across six representative LLMs on the HumanEval dataset. Specifically, we first employed open coding and thematic analysis to distill a comprehensive taxonomy of code generation errors. We analyzed two dimensions of error characteristics—semantic characteristics and syntactic characteristics. Our analysis revealed that LLMs often made nontrivial, multi-line code generation errors in various locations and with various root causes. We further analyzed the correlation between these errors and task complexity as well as test pass rate. Our findings highlighted several challenges in locating and fixing code generation errors made by LLMs. In the end, we discussed several future directions to address these challenges. Copyright © 2024, The Authors. All rights reserved.

关键词： coding errors

Fixing Function-Level Code Generation errors for Foundation Large Language Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wen, Hao Zhu, Yueheng Liu, Chao Ren, Xiaoxue Du, Weiwei Yan, Meng Chongqing University Chongqing China Zhejiang University Hangzhou China Army Logistics Academy Chongqing China

Function-level code generation leverages foundation Large Language Models (LLMs) like CodeLlama to automatically produce source code with expected functionality. It has been widely investigated and applied in intelligent programming assistants, such as GitHub Copilot, to enhance software development productivity and reduce repetitive tasks. Despite advancements in foundation LLMs, the generation involves many errors. Existing studies leverage static analysis tools (e.g., TBar and ReCoder) or add another fixing LLM (i.e., CoR and LDB) to post-process these errors. However, there are still many errors remaining to be solved because their root causes have not been investigated yet, making it challenging to design better fixing tools. In this paper, we first conducted an empirical study on the generation errors. Specifically, we reproduced 14 representative open/closed source LLMs on the HumanEval dataset and verified their correctness. We obtained 12,837 code generation errors and conducted an in-depth analysis of their causes, leading to 19 categories of error causes. Our empirical analysis indicated that three of these causes can be directly fixed. Based on the findings, we proposed a fixing method called LlmFix, which is a rule-based static analysis approach and addresses these three types of errors through a three-step process: filtering code for indentation correction, truncating redundant generated code, and importing missing modules. Evaluations of LlmFix are conducted from two perspectives: its performance on error-fixing tasks and its impact on improving function-level code generation tasks. For error fixing performance, we built an evaluation dataset LlmErrorEval based on our collected 12k+ errors. Experimental results show that LlmFix achieves a fix rate of 17.1% outperforming the best state-of-the-art LDB by 8.9%. For code generation improvements, evaluations of LlmFix on both the HumanEval and MBPP datasets demonstrate its effectiveness, significantly impr

关键词： coding errors

Noise-Agnostic Multitask Whisper Training for Reducing False Alarm errors in Call-for-Help Detection

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ryu, Myeonghoon Kim, June-Woo Oh, Minseok Lee, Suji Park, Han Deeply Inc. Seoul Korea Republic of Department of Artificial Intelligence Kyungpook National University Daegu Korea Republic of RSC LAB MODULABS Seoul Korea Republic of

Keyword spotting is often implemented by keyword classifier to the encoder in acoustic models, enabling the classification of predefined or open vocabulary keywords. Although keyword spotting is a crucial task in various applications and can be extended to call-for-help detection in emergencies, however, the previous method often suffers from scalability limitations due to retraining required to introduce new keywords or adapt to changing contexts. We explore a simple yet effective approach that leverages off-the-shelf pretrained ASR models to address these challenges, especially in call-for-help detection scenarios. Furthermore, we observed a substantial increase in false alarms when deploying call-for-help detection system in real-world scenarios due to noise introduced by microphones or different environments. To address this, we propose a novel noise-agnostic multitask learning approach that integrates a noise classification head into the ASR encoder. Our method enhances the model’s robustness to noisy environments, leading to a significant reduction in false alarms and improved overall call-for-help performance. Despite the added complexity of multitask learning, our approach is computationally efficient and provides a promising solution for call-for-help detection in real-world scenarios. © 2025, CC BY.

关键词： coding errors

Improving LLM Classification of Logical errors by Integrating Error Relationship into Prompts

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lee, Yanggyu Jeong, Suchae Kim, Jihie Department of Computer Science and AI Dongguk University Seoul Korea Republic of College of AI Convergence Dongguk University Seoul Korea Republic of

LLMs trained in the understanding of programming syntax are now providing effective assistance to developers and are being used in programming education such as in generation of coding problem examples or providing code explanations. A key aspect of programming education is understanding and dealing with error message. However, 'logical errors' in which the program operates against the programmer's intentions do not receive error messages from the compiler. In this study, building on existing research on programming errors, we first define the types of logical errors that can occur in programming in general. Based on the definition, we propose an effective approach for detecting logical errors with LLMs that makes use of relations among error types in the Chain-of-Thought and Tree-of-Thought prompts. The experimental results indicate that when such logical error descriptions in the prompt are used, the average classification performance is about 21% higher than the ones without them. We also conducted an experiment for exploiting the relations among errors in generating a new logical error dataset using LLMs. As there is very limited dataset for logical errors such benchmark dataset can be very useful for various programming related applications. We expect that our work can assist novice programmers in identifying the causes of code errors and correct them more effectively. © 2024, CC BY.

关键词： coding errors

CSI: Haskell - Tracing Lazy Evaluations in a Functional Language 35

学校读者我要写书评

暂无评论

CSI: Haskell - Tracing Lazy Evaluations in a Functional Lang...

35th Symposium on Implementation and Application of Functional Languages, IFL 2023

作者： Gissurarson, Matthías Páll Applis, Leonhard Herbert Computer Science and Engineering Chalmers University of Technology Gothenburg Sweden Delft University of Technology Delft Netherlands

ISBN: (纸本)9798400716317

In non-strict languages such as Haskell the execution of individual expressions in a program significantly deviates from the order in which they appear in the source code. This can make it difficult to find bugs related to this deviation, since the evaluation of expressions does not occur in the same order as in the source code. At the moment, Haskell errors focus on values being produced, whereas it is often the case that faults are due to values being consumed. For non-strict languages, values involved in a bug are often generated immediately prior to the evaluation of the buggy code. This creates an opportunity for evaluation traces, tracking recently evaluated locations (which can deviate from call-order) to help establish the origin of values involved in faults. In this paper, we describe an extension of GHC's Haskell Program Coverage with evaluation traces, recording recent evaluations in the coverage file, and reporting an evaluation trace alongside the call stack on exception. This lets us reconstruct the chain of events and locate the origin of faults. As a case study, we applied our initial implementation to the nofib-buggy data set and found that some runtime errors greatly benefit from trace information. © 2023 Owner/Author.

关键词： coding errors

Class of codes correcting absorptions and emissions

学校读者我要写书评

暂无评论

Physical Review A 2025年第2期111卷 022415-022415页

作者： Arda Aydin Alexander Barg ISR and Department of ECE University of Maryland College Park Maryland 20742 USA QuICS NIST University of Maryland College Park Maryland 20742 USA

We construct a general family of quantum codes that protect against all emission, absorption, dephasing, and raising or lowering errors up to an arbitrary fixed order. Such codes are known in the literature as absorption-emission (AE) codes. We derive simplified error correction conditions for a general AE code and show that any permutation-invariant code that corrects t or fewer errors can be mapped to an AE code that corrects up to order-t transitions. Carefully tuning the parameters of permutationally invariant codes, we construct several examples of efficient AE codes, hosted in systems with low total angular momentum. Our results also imply that spin codes can be mapped to AE codes, enabling us to characterize logical operators for certain subclasses of such codes.

关键词： coding errors

A Group-Type Distributed Coded Computation Scheme Based on a Gabidulin Code 17

学校读者我要写书评

暂无评论

A Group-Type Distributed Coded Computation Scheme Based on a...

17th International Symposium on Information Theory and its Applications (ISITA)

作者： Kazama, Koki Matsushima, Toshiyasu Waseda Univ Tokyo Japan

ISBN: (纸本)9784885523410

We focus on a distributed coded computation scheme for matrix multiplication. In this system, the product matrix is encoded and decoded through the overall system to correct errors in computation. We propose a group-type distributed coded computation scheme, for one example, a scheme based on a Gabidulin code, and evaluate the computation time complexity and the error-correcting capability of the overall system. The full version of this paper is in [1].

关键词： coding errors

On the Second-Order Achievabilities of Indirect Quadratic Lossy Source coding

学校读者我要写书评

暂无评论

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Yang, Huiyuan Yuan, Xiaojun University of Electronic Science and Technology of China National Key Laboratory on Wireless Communications Chengdu611731 China

This paper studies the second-order achievabilities of indirect quadratic lossy source coding for a specific class of source models, where the term "quadratic"denotes that the reconstruction fidelity of the hidden source is quantified by a squared error distortion measure. Specifically, it is assumed that the hidden source S can be expressed as S=(X)+W, where X is the observable source with alphabet X, () is a deterministic function, and W is a random variable independent of X, satisfying E[W]=0, E[W2]>0, E[W3]=0, and E[W6] © 2015 IEEE.

关键词： coding errors