Stealthy Backdoor Attack for Code Models Article Swipe

MAKE IMPACT

Zhou Yang , Bowen Xu , Jie M. Zhang , Hong Jin Kang , Jieke Shi , Junda He , David Lo · YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2301.02496

Code models, such as CodeBERT and CodeT5, offer general-purpose representations of code and play a vital role in supporting downstream automated software engineering tasks. Most recently, code models were revealed to be vulnerable to backdoor attacks. A code model that is backdoor-attacked can behave normally on clean examples but will produce pre-defined malicious outputs on examples injected with triggers that activate the backdoors. Existing backdoor attacks on code models use unstealthy and easy-to-detect triggers. This paper aims to investigate the vulnerability of code models with stealthy backdoor attacks. To this end, we propose AFRAIDOOR (Adversarial Feature as Adaptive Backdoor). AFRAIDOOR achieves stealthiness by leveraging adversarial perturbations to inject adaptive triggers into different inputs. We evaluate AFRAIDOOR on three widely adopted code models (CodeBERT, PLBART and CodeT5) and two downstream tasks (code summarization and method name prediction). We find that around 85% of adaptive triggers in AFRAIDOOR bypass the detection in the defense process. By contrast, only less than 12% of the triggers from previous work bypass the defense. When the defense method is not applied, both AFRAIDOOR and baselines have almost perfect attack success rates. However, once a defense is applied, the success rates of baselines decrease dramatically to 10.47% and 12.06%, while the success rate of AFRAIDOOR are 77.05% and 92.98% on the two tasks. Our finding exposes security weaknesses in code models under stealthy backdoor attacks and shows that the state-of-the-art defense method cannot provide sufficient protection. We call for more research efforts in understanding security threats to code models and developing more effective countermeasures.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2301.02496

PDF

https://arxiv.org/pdf/2301.02496

OA Status

green

Cited By

16

Related Works

10

OpenAlex ID

https://openalex.org/W4313936359

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4313936359

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2301.02496

Digital Object Identifier

Title

Stealthy Backdoor Attack for Code Models

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2023

Year of publication

Publication date

2023-01-06

Full publication date if available

Authors

Zhou Yang, Bowen Xu, Jie M. Zhang, Hong Jin Kang, Jieke Shi, Junda He, David Lo

List of authors in order

Landing page

https://arxiv.org/abs/2301.02496

Publisher landing page

PDF URL

https://arxiv.org/pdf/2301.02496

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2301.02496

Direct OA link when available

Concepts

Backdoor, Computer science, Code (set theory), Computer security, Vulnerability (computing), Key (lock), Programming language, Set (abstract data type)

Top concepts (fields/topics) attached by OpenAlex

Cited by

16

Total citation count in OpenAlex

Citations by year (recent)

2025: 2, 2024: 9, 2023: 5

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload