How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses
원문 초록
Deep Learning is currently used to perform multiple tasks, such as object recognition, face recognition, and natural language processing. However, Deep Neural Networks (DNNs) are vulnerable to perturbations that alter the network prediction (adversarial examples), raising concerns regarding its usage in critical areas, such as self-driving vehicles, malware detection, and healthcare. This paper compiles the most recent adversarial attacks, grouped by the attacker capacity, and modern defenses clustered by protection strategies. We also present the new advances regarding Vision Transformers, summarize the datasets and metrics used in the context of adversarial settings, and compare the state-of-the-art results under different attacks, finishing with the identification of open issues.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Efficient Estimation of Regularized Tyler's M-Estimator Using Approximate LOOCV
Attributes Shape the Embedding Space of Face Recognition Models
SASep: Saliency-Aware Structured Separation of Geometry and Feature for Open Set Learning on Point Clouds
Inverting Black-Box Face Recognition Systems via Zero-Order Optimization in Eigenface Space
STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving
EMBER2024 -- A Benchmark Dataset for Holistic Evaluation of Malware Classifiers
토론
이 논문과 연결된 포럼 글이 아직 없습니다.