Searcharxiv⌕ Search

arXiv subjects

Afsana Tasnim

Publications and source records attributed to Afsana Tasnim.

3 recordsLinked to original sources

Decalage: Uncovering the Gap Between Model-Generated Reasoning and Actual Code Implementation in Small Language Models

Agentic code generation often asks a model to explain its reasoning before it writes code, and a common way to make such a workflow safer is to add a security instruction to the prompt. We test what that instruction does in small language models, which are attractive because they run locally and cheaply. Four open code models of 1.5B to 3B parameters generate C++ from 166 sections of eleven public requirements documents, once with a general prompt and once with a secure prompt. The secure prompt more than doubles the share of reasoning about validation, resource handling and threats, and we find no evidence that the rise is larger for requirements with security content. The code changes only in part. Among functions with a body and reasoning, the share with a check that our lexical test recognises rises from 23% to 39%, but more than a quarter of the functions remain stubs, compile rates stay low, and half or more of the functions whose reasoning mentions a check contain no such check. Two rounds of compiler-feedback repair leave more than 80% of sections unusable, and neither cppcheck nor an exploratory ESBMC run separates the prompts on the usable code. A hand check by two annotators supports the stub measure and the direction of the reasoning result. For small models, a security instruction changes the reasoning broadly but the code only in part, so the reasoning should be checked against the code rather than trusted.

cs.SE↗

ShikumiMiner: Mining Recurring Implementation Patterns in AI Codebases

Large language models are paving the way towards innovation by understanding, analyzing, summarizing and generating content in the modern world. Currently there are thousands of LLM projects developed by engineers in open-source repositories. However, whether these LLM projects have underlying patterns or not remains a question. Exploring these underlying patterns will give new dimensions to the developers who aim to develop these LLM projects. In this paper, we propose ShikumiMiner, a static-analysis framework that combines Abstract Syntax Tree (AST) and Control Flow Graph (CFG) features to detect and compare recurring implementation patterns in C++ local LLM codebases. We analyze ten GitHub open-source repositories and classify functions into seven study-specific categories using a multi-label Random Forest model. Studying these patterns can provide useful insights for developers aiming to design LLM applications.

cs.SE↗

Illegal Border Cross Detection and Warning System Using IR Sensor and Node MCU

We often find illegal immigrants moving from one country to another. By means of land these illegal immigrants move over the fence cut the border wires and moves to the other part of the land. What do you think our soldiers are not doing their job? It is not that actually. It is very difficult to watch consistently over the border. Soldiers have a limited vision to check around the whole land mass. So for them we have come up with a solution that we have built a device that will sense the presence of an intruder (illegal immigrant). This device will be installed over the fences. When an intruder passes over the fence this device will transmit the signal to the soldiers Smartphone app (BLYNK app). The soldier will be notified with the signal and after receiving the signal, the soldier can switch on the alarm and the emergency lights via the app. By this the soldiers in the camp will be alerted and can take their respective positions and arrest the intruder which was passing the border illegally. By this device we can alert the soldiers in the border to take more safety precautions to keep our country safe. Index Terms-Node MCU ESP32, infrared sensor, Blynk app.

eess.SP↗