A Survey of Trojans in Neural Models of Source Code: Taxonomy and Techniques

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hussain, Aftab, Rabin, Md Rafiqul Islam, Ahmed, Toufique, Ayoobi, Navid, Xu, Bowen, Devanbu, Prem, Alipour, Mohammad Amin
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916212993163264
author Hussain, Aftab
Rabin, Md Rafiqul Islam
Ahmed, Toufique
Ayoobi, Navid
Xu, Bowen
Devanbu, Prem
Alipour, Mohammad Amin
author_facet Hussain, Aftab
Rabin, Md Rafiqul Islam
Ahmed, Toufique
Ayoobi, Navid
Xu, Bowen
Devanbu, Prem
Alipour, Mohammad Amin
contents In this work, we study literature in Explainable AI and Safe AI to understand poisoning of neural models of code. In order to do so, we first establish a novel taxonomy for Trojan AI for code, and present a new aspect-based classification of triggers in neural models of code. Next, we highlight recent works that help us deepen our conception of how these models understand software code. Then we pick some of the recent, state-of-art poisoning strategies that can be used to manipulate such models. The insights we draw can potentially help to foster future research in the area of Trojan AI for code.
format Preprint
id arxiv_https___arxiv_org_abs_2305_03803
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A Survey of Trojans in Neural Models of Source Code: Taxonomy and Techniques
Hussain, Aftab
Rabin, Md Rafiqul Islam
Ahmed, Toufique
Ayoobi, Navid
Xu, Bowen
Devanbu, Prem
Alipour, Mohammad Amin
Software Engineering
In this work, we study literature in Explainable AI and Safe AI to understand poisoning of neural models of code. In order to do so, we first establish a novel taxonomy for Trojan AI for code, and present a new aspect-based classification of triggers in neural models of code. Next, we highlight recent works that help us deepen our conception of how these models understand software code. Then we pick some of the recent, state-of-art poisoning strategies that can be used to manipulate such models. The insights we draw can potentially help to foster future research in the area of Trojan AI for code.
title A Survey of Trojans in Neural Models of Source Code: Taxonomy and Techniques
topic Software Engineering
url https://arxiv.org/abs/2305.03803