Query Provenance Analysis: Efficient and Robust Defense against Query-based Black-box Attacks
Shaofei Li, Ziqi Zhang, Haomin Jia, Ding Li, Yao Guo, Xiangqun Chen

TL;DR
This paper introduces Query Provenance Analysis (QPA), a novel defense method against query-based black-box attacks that leverages historical query relationships to improve robustness and efficiency.
Contribution
QPA is a new approach that captures query sequence relationships for more effective and efficient defense against adaptive black-box attacks.
Findings
QPA reduces Attack Success Rate (ASR) to 4.08%.
QPA outperforms baselines in defense effectiveness.
QPA achieves significantly higher throughput.
Abstract
Query-based black-box attacks have emerged as a significant threat to machine learning systems, where adversaries can manipulate the input queries to generate adversarial examples that can cause misclassification of the model. To counter these attacks, researchers have proposed Stateful Defense Models (SDMs) for detecting adversarial query sequences and rejecting queries that are "similar" to the history queries. Existing state-of-the-art (SOTA) SDMs (e.g., BlackLight and PIHA) have shown great effectiveness in defending against these attacks. However, recent studies have shown that they are vulnerable to Oracle-guided Adaptive Rejection Sampling (OARS) attacks, which is a stronger adaptive attack strategy. It can be easily integrated with existing attack algorithms to evade the SDMs by generating queries with fine-tuned direction and step size of perturbations utilizing the leaked…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsCloud Data Security Solutions · Security and Verification in Computing · Network Security and Intrusion Detection
