EVIL (Exploiting software VIa natural Language) is an approach to automatically generate software exploits in assembly/Python language from descriptions in natural language. The approach leverages Neural Machine Translation (NMT) techniques and a dataset that we developed for this work.

Neural search engine for discovering semantically similar Python repositories on GitHub

Repository about small code models

This repository contains the code, the dataset and the experimental results related to the paper "Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attacks" accepted for publication at The 32nd IEEE/ACM International Conference on Program Comprehension (ICPC 2024).

Augmenting the Interpretability of GraphCodeBERT for Code Similarity Tasks

Fine-tuning CodeBERT for Vulnerability Detection

Improving Source Code Similarity Detection with GraphCodeBERT and Additional Feature Integration

Django implementation of CodeBERT for detecting vulnerable code.

The modern web development landscape is plagued by a peculiar paradox: despite the abundance of UI components and design systems, developers still spend countless hours reimplementing similar interfaces. S0 addresses this challenge by introducing a novel approach that combines advanced vector search capabilities.

This study compares three transformer-based mod- els—CodeT5, CodeBERT, and CodeGen.

Reproducibility report ofCoSQA: 20,000+ Web Queries for Code Search and QuestionAnswering for ML Reproducibility Challenge 2021

"AI-powered vulnerability detection for Solidity smart contracts using Mistral + CodeBERT"

AI/ML Trained Python Code Validator with Gradio Web Interface

CodeOpt: A framework for optimizing code performance using Two-Stage Sampling, Few-Shot Learning, and Iterative Self-Reflection with support for Genetic Algorithm Inspired Chain-of-Thought (GA-COT).