Targeted Mismatch Adversarial Attack: Query with a Flower to Retrieve the Tower
Access to online visual search engines implies sharing of private user content - the query images. We introduce the concept of targeted mismatch attack for deep learning based retrieval systems to generate an adversarial image to conceal the query image. The generated image looks nothing like the user intended query, but leads to identical or very similar retrieval results. Transferring attacks to fully unseen networks is challenging. We show successful attacks to partially unknown systems, by designing various loss functions for the adversarial image construction. These include loss functions, for example, for unknown global pooling operation or unknown input resolution by the retrieval system. We evaluate the attacks on standard retrieval benchmarks and compare the results retrieved with the original and adversarial image.
Code (1)
Tasks
Adversarial AttackRetrievalSimilar Papers 제목 키워드 기반
Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks
We propose a versatile framework based on random search, Sparse-RS, for score-based sparse targeted and untargeted attacks in the black-box setting. Sparse-RS does not rely on substitute models and achieves state-of-the-…
Malware DetectionA Pilot Study of Query-Free Adversarial Attack against Stable Diffusion
Despite the record-breaking performance in Text-to-Image (T2I) generation by Stable Diffusion, less research attention is paid to its adversarial robustness. In this work, we study the problem of adversarial attack gener…
Adversarial AttackAdversarial RobustnessAdversarial TextYou Only Query Once: Effective Black Box Adversarial Attacks with Minimal Repeated Queries
Researchers have repeatedly shown that it is possible to craft adversarial attacks on deep classifiers (small perturbations that significantly change the class label), even in the "black-box" setting where one only has q…
Query-Efficient Black-box Adversarial Examples (superceded)
Note that this paper is superceded by "Black-Box Adversarial Attacks with Limited Queries and Information." Current neural network-based image classifiers are susceptible to adversarial examples, even in the black-box …
Adversarial AttackBand Together: Untargeted Adversarial Training with Multimodal Coordination against Evasion-based Promotion Attacks
Multimodal recommender systems exploit visual and textual signals to alleviate data sparsity, but this also makes them more vulnerable to evasion-based promotion attacks. Existing defenses are largely limited to single-m…