EUVIMEDEUVIMED entdecken
Crossref

A General Framework for Defending against Query-based Black-box Attacks on Neural Network Models

Shaofei Li, Ruqin Li, Ziqi Zhang, Zhenkai Liang, Yao Guo, Xiangqun Chen, Ding Li

ACM Transactions on Software Engineering and Methodology · 12.06.2026

DOI: 10.1145/3820765 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 12.06.2026. Verfasst von Shaofei Li und 6 weiteren Autor:innen. Die Arbeit nennt 93 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As Machine Learning as a Service (MLaaS) becomes increasingly prevalent, query-based black-box attacks pose a significant threat to machine learning systems. These attacks manipulate input queries to generate adversarial examples, resulting in misclassification or undesired outputs. To address these threats, researchers have developed various query moderation techniques. However, recent studies have revealed that these techniques are vulnerable to sophisticated adaptive attacks. In this paper, we propose a general framework, Query Provenance Analysis (QPA), to defend against query-based black-box attacks both robustly (against non-adaptive and adaptive attacks) and efficiently (in real-time). Our key insight is that, instead of focusing on individual queries, utilizing features from the query sequence (termed query provenance ) can distinguish malicious queries from benign queries more effectively. We construct a query provenance graph to capture the relationship between a new query and prior historical queries, and then design efficient algorithms to detect malicious queries based on the query provenance graphs. We evaluate QPA on image classification and Natural Language Processing (NLP) tasks. QPA significantly reduces the Attack Success Rate (ASR) compared to baselines, achieving up to 20 \(\times\) lower ASR for image classification and 10 \(\times\) lower ASR for NLP, while also improving throughput and latency across all tasks.

Zitieren

APA

Li, S., Li, R., Zhang, Z., Liang, Z., Guo, Y., Chen, X., & Li, D. (2026). A General Framework for Defending against Query-based Black-box Attacks on Neural Network Models. ACM Transactions on Software Engineering and Methodology. https://doi.org/10.1145/3820765

Vancouver

Li S, Li R, Zhang Z, Liang Z, Guo Y, Chen X, et al. A General Framework for Defending against Query-based Black-box Attacks on Neural Network Models. ACM Transactions on Software Engineering and Methodology. 2026. doi:10.1145/3820765

BibTeX
@article{Li2026,
  author = {Li, Shaofei and Li, Ruqin and Zhang, Ziqi and Liang, Zhenkai and Guo, Yao and Chen, Xiangqun and Li, Ding},
  title = {A General Framework for Defending against Query-based Black-box Attacks on Neural Network Models},
  journal = {ACM Transactions on Software Engineering and Methodology},
  year = {2026},
  doi = {10.1145/3820765}
}
Kostenlos starten →