Practical Relative Order Attack in Deep Ranking

Abstract

Recent studies unveil the vulnerabilities of deep ranking models, where an imperceptible perturbation can trigger dramatic changes in the ranking result. While previous attempts focus on manipulating absolute ranks of certain candidates, the possibility of adjusting their relative order remains under-explored. In this paper, we formulate a new adversarial attack against deep ranking systems, i.e., the Order Attack, which covertly alters the relative order among a selected set of candidates according to an attacker-specified permutation, with limited interference to other unrelated candidates. Specifically, it is formulated as a triplet-style loss imposing an inequality chain reflecting the specified permutation. However, direct optimization of such white-box objective is infeasible in a real-world attack scenario due to various black-box limitations. To cope with them, we propose a Short-range Ranking Correlation metric as a surrogate objective for black-box Order Attack to approximate the white-box method. The Order Attack is evaluated on the Fashion-MNIST and Stanford-Online-Products datasets under both white-box and black-box threat models. The black-box attack is also successfully implemented on a major e-commerce platform. Comprehensive experimental evaluations demonstrate the effectiveness of the proposed methods, revealing a new type of ranking model vulnerability.

arXiv commentICCV2021 Poster

References in corpus (9)

• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
• Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks
• Adversarial Risk and the Dangers of Evaluating Against Weak Attacks
• Unsupervised Adversarial Attacks on Deep Feature-based Retrieval with GAN
• Query Attack via Opposite-Direction Feature:Towards Robust Image Retrieval
• Adversarial Metric Attack and Defense for Person Re-identification
• QAIR: Practical Query-efficient Black-Box Attacks for Image Retrieval
• Ladder Loss for Coherent Visual-Semantic Embedding

Cited by in corpus (1)

• Adversarial Attack and Defense in Deep Ranking