Polishing Decision-Based Adversarial Noise With a Customized Sampling
As an effective black-box adversarial attack, decision-based methods polish adversarial noise by querying the target model. Among them, boundary attack is widely applied due to its powerful noise compression capability, especially when combined with transfer-based methods. Boundary attack splits the noise compression into several independent sampling processes, repeating each query with a constant sampling setting. In this paper, we demonstrate the advantage of using current noise and historical queries to customize the variance and mean of sampling in boundary attack to polish adversarial noise. We further reveal the relationship between the initial noise and the compressed noise in boundary attack. We propose Customized Adversarial Boundary (CAB) attack that uses the current noise to model the sensitivity of each pixel and polish adversarial noise of each image with a customized sampling setting. On the one hand, CAB uses current noise as a prior belief to customize the multivariate normal distribution. On the other hand, CAB keeps the new samplings away from historical failed queries to avoid similar mistakes. Experimental results measured on several image classification datasets emphasizes the validity of our method.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial Attackimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Adversarial multi-task learning to solve holistic semantic polishing problem of Chinese text
For the core obstacles faced by Chinese proofreading, we think that the effective holistic semantic feature representation of a sentence and its characteristics is a key. Here, we propose a novel adversarial multi-task l…
Multi-Task LearningSentenceStage-Aware and Roughness-Constrained Diffusion Policy for Multi-Stage Robotic Polishing
Polishing is a critical finishing process in high-end manufacturing fields such as aerospace, where surface quality directly affects the service performance and reliability of components. Robotic imitation learning provi…
Anchor then Polish for Low-light Enhancement
Low-light image enhancement is challenging due to entangled degradations, mainly including poor illumination, color shifts, and texture interference. Existing methods often rely on complex architectures to address these …
Low-Light Image EnhancementTV-3DG: Mastering Text-to-3D Customized Generation with Visual Prompt
In recent years, advancements in generative models have significantly expanded the capabilities of text-to-3D generation. Many approaches rely on Score Distillation Sampling (SDS) technology. However, SDS struggles to ac…
3D GenerationText to 3DDeep Stacked Networks with Residual Polishing for Image Inpainting
Deep neural networks have shown promising results in image inpainting even if the missing area is relatively large. However, most of the existing inpainting networks introduce undesired artifacts and noise to the repaire…
DenoisingImage Inpainting