Search

Compiler bugs pose a significant threat to safety-critical applications, and promptly and effectively isolating these bugs is crucial for assuring the quality of compilers. However, the limited availability of debugging information on reported bugs complicates the compiler bug isolation task. Existing compiler bug isolation approaches typically convert the problem into a test program mutation problem, but they are still limited by ineffective mutation strategies or high human effort requirements. Drawing inspiration from the recent progress of pre-trained Large Language Models (LLMs), such as ChatGPT, in code generation, we propose a new approach named LLM4CBI to tame LLMs to generate effective test programs for compiler bug isolation. However, using LLMs directly for test program mutation may not yield the desired results due to the challenges associated with formulating precise prompts and selecting specialized prompts. To overcome the challenges, three new components are designed in LLM4CBI. (1) LLM4CBI utilizes a program complexity-guided prompt production component, which leverages data and control flow analysis to identify the most valuable variables and locations in programs for mutation. (2) LLM4CBI employs a memorized prompt selection component, which adopts reinforcement learning to select specialized prompts for mutating test programs continuously. (3) A test program validation component is proposed to select specialized feedback prompts to avoid repeating the same mistakes during the mutation process. Compared with the state-of-the-art approaches (DiWi and RecBi), our evaluation demonstrates the advantages of LLM4CBI: It isolates more bugs, ranging from 13.6% to 90.9% in various settings, than the other approaches. Additionally, we demonstrate that LLM4CBI is extensible, allowing for easy integration with other LLMs., Comment: Under review of IEEE Transactions on Software Engineering

This article studies a kind of new advanced packet marking method through analyzing the problems existing in traditional advanced packet marking method. This method has made it unnecessary for the victim to know the network topological information of upstream to the victim while reconstructing attack route. In addition, it can effectively reduce the quantity of misinformation caused by route reconstruction, in the meantime, it also has relatively low amount of calculation.

Network flow is an important parameter for measuring network operation load and status, it is also the important parameter that plays an important role in network planning and flow management etc. In flow management, the flow model is used to evaluate access control mechanism and predict network performance. We have proposed a new network forecasting method on the basis of grey neural network study, we revise the residual generated due to grey neural combined model through self-adapting filtration method to achieve more precise effect. The experimental results show that this method is effective and practical.