一句话：实证表明三种先进 API 推荐系统均无法抵御训练数据投毒，亟需有效防御手段。
软件工程领域的推荐系统为开发者提供了大量有价值的条目，其中 API 推荐系统近年来在建议 API 调用或代码片段方面表现日益突出。尽管这些系统在预测准确率上已被证明有效，但其面对对抗性攻击的鲁棒性却少有研究。事实上，攻击者可以通过精心构造推荐系统的学习材料（例如来自大型开源软件仓库的数据）注入恶意数据，从而危及采用 API 推荐系统的软件客户端。本文对对抗性机器学习技术及其对推荐系统的潜在影响开展了实证研究。作者在三个当前最先进的 API 推荐系统上进行评估，得到了令人担忧的结果：它们无一能免疫恶意数据。这一结论呼唤有效的对策，以保护推荐系统免受隐藏在训练数据中的恶意攻击。
Recommender systems in software engineering provide developers with a wide range of valuable items to help them complete their tasks. Among others, API recommender systems have gained momentum in recent years as they became more successful at suggesting API calls or code snippets. While these systems have proven to be effective in terms of prediction accuracy, there has been less attention for what concerns such recommenders’ resilience against adversarial attempts. In fact, by crafting the recommenders’ learning material, e.g., data from large open-source software (OSS) repositories, hostile users may succeed in injecting malicious data, putting at risk the software clients adopting API recommender systems. In this paper, we present an empirical investigation of adversarial machine learning techniques and their possible influence on recommender systems. The evaluation performed on three state-of-the-art API recommender systems reveals a worrying outcome: all of them are not immune to malicious data. The obtained result triggers the need for effective countermeasures to protect recommender systems against hostile attacks disguised in training data.
DOI 原文 ·
@inproceedings{paperbot6490,
title = {Adversarial Attacks to API Recommender Systems: Time to Wake Up and Smell the Coffee?},
author = {Phuong T. Nguyen and Claudio Di Sipio and Juri Di Rocco and Massimiliano Di Penta and Davide Di Ruscio},
booktitle = {ASE},
year = {2021},
doi = {10.1109/ase51524.2021.9678946}
}