Who's Afraid Of Adversarial Queries? The Impact Of Image Modifications On Content-based Image Retrieval

Abstract

An adversarial query is an image that has been modified to disrupt content-based image retrieval (CBIR) while appearing nearly untouched to the human eye. This paper presents an analysis of adversarial queries for CBIR based on neural, local, and global features. We introduce an innovative neural image perturbation approach, called Perturbations for Image Retrieval Error (PIRE), that is capable of blocking neural-feature-based CBIR. PIRE differs significantly from existing approaches that create images adversarial with respect to CNN classifiers because it is unsupervised, i.e., it needs no labelled data from the data set to which it is applied. Our experimental analysis demonstrates the surprising effectiveness of PIRE in blocking CBIR, and also covers aspects of PIRE that must be taken into account in practical settings, including saving images, image quality and leaking adversarial queries into the background collection. Our experiments also compare PIRE (a neural approach) with exi

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyliu2019who

Related papers

• QAIR: Practical Query-efficient Black-box Attacks For Image Retrieval (2021)12.54
• Boundary-aware Backward-compatible Representation Via Adversarial Learning In Image Retrieval (2023)9.21
• Targeted Mismatch Adversarial Attack: Query With A Flower To Retrieve The Tower (2019)13.23
• Defense Against Adversarial Images Using Web-scale Nearest-neighbor Search (2019)10.97
• A Review Of Image Retrieval Techniques: Data Augmentation And Adversarial Learning Approaches (2024)0.00
• Adversarial Attack On Deep Product Quantization Network For Image Retrieval (2020)11.29
• Query Attack Via Opposite-direction Feature:towards Robust Image Retrieval (2018)0.00
• Advancements In Content-based Image Retrieval: A Comprehensive Survey Of Relevance Feedback Techniques (2023)0.00