Misleading Authorship Attribution of Source Code using Adversarial Learning

05/29/2019
by   Erwin Quiring, et al.
0

In this paper, we present a novel attack against authorship attribution of source code. We exploit that recent attribution methods rest on machine learning and thus can be deceived by adversarial examples of source code. Our attack performs a series of semantics-preserving code transformations that mislead learning-based attribution but appear plausible to a developer. The attack is guided by Monte-Carlo tree search that enables us to operate in the discrete domain of source code. In an empirical evaluation with source code from 204 programmers, we demonstrate that our attack has a substantial effect on two recent attribution methods, whose accuracy drops from over 88 under attack. Furthermore, we show that our attack can imitate the coding style of developers with high accuracy and thereby induce false attributions. We conclude that current approaches for authorship attribution are inappropriate for practical application and there is a need for resilient analysis techniques.

READ FULL TEXT
research
04/26/2023

SHIELD: Thwarting Code Authorship Attribution

Authorship attribution has become increasingly accurate, posing a seriou...
research
01/30/2020

Authorship Attribution of Source Code: A Language-Agnostic Approach and Applicability in Software Engineering

Authorship attribution of source code has been an established research t...
research
08/26/2022

I still know it's you! On Challenges in Anonymizing Source Code

The source code of a program not only defines its semantics but also con...
research
03/14/2019

Attribution-driven Causal Analysis for Detection of Adversarial Examples

Attribution methods have been developed to explain the decision of a mac...
research
09/22/2022

Talking Trojan: Analyzing an Industry-Wide Disclosure

While vulnerability research often focuses on technical findings and pos...
research
04/26/2023

On Pitfalls of RemOve-And-Retrain: Data Processing Inequality Perspective

Approaches for appraising feature importance approximations, alternative...

Please sign up or login with your details

Forgot password? Click here to reset