Search Results for author: Shushan Arakelyan

Found 3 papers, 1 papers with code

Exploring Distributional Shifts in Large Language Models for Code Analysis

no code implementations16 Mar 2023 Shushan Arakelyan, Rocktim Jyoti Das, Yi Mao, Xiang Ren

We systematically study how three large language models with code capabilities - CodeT5, Codex, and ChatGPT - generalize to out-of-domain data.

Code Generation Code Summarization

NS3: Neuro-Symbolic Semantic Code Search

1 code implementation21 May 2022 Shushan Arakelyan, Anna Hakhverdyan, Miltiadis Allamanis, Luis Garcia, Christophe Hauser, Xiang Ren

We compare our model - NS3 (Neuro-Symbolic Semantic Search) - to a number of baselines, including state-of-the-art semantic code retrieval methods, and evaluate on two datasets - CodeSearchNet and Code Search and Question Answering.

Code Search Question Answering +2

Bin2vec: Learning Representations of Binary Executable Programs for Security Tasks

no code implementations9 Feb 2020 Shushan Arakelyan, Sima Arasteh, Christophe Hauser, Erik Kline, Aram Galstyan

We demonstrate the versatility of this approach by using our representations to solve two semantically different binary analysis tasks - functional algorithm classification and vulnerability discovery.

Vulnerability Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.