变异
发表于 2025-3-28 15:16:21
http://reply.papertrans.cn/24/2343/234239/234239_41.png
Introduction
发表于 2025-3-28 21:07:46
Deep ,-NN Defense Against Clean-Label Data Poisoning Attacks minimally-perturbed samples into the training data, causing a model to misclassify a particular test sample during inference. Although defenses have been proposed for general poisoning attacks, no reliable defense for clean-label attacks has been demonstrated, despite the attacks’ effectiveness and
arcane
发表于 2025-3-29 02:06:58
http://reply.papertrans.cn/24/2343/234239/234239_43.png
重叠
发表于 2025-3-29 03:51:43
http://reply.papertrans.cn/24/2343/234239/234239_44.png
ONYM
发表于 2025-3-29 09:17:50
Jacks of All Trades, Masters of None: Addressing Distributional Shift and Obtrusiveness via Transparccess and obtrusiveness via the design of novel semi-transparent patches. This work is motivated by our pursuit of a systematic performance analysis of patch attack robustness with regard to geometric transformations. Specifically, we first elucidate a) key factors underpinning patch attack success
Needlework
发表于 2025-3-29 15:20:49
http://reply.papertrans.cn/24/2343/234239/234239_46.png
scrape
发表于 2025-3-29 18:31:16
http://reply.papertrans.cn/24/2343/234239/234239_47.png
卡死偷电
发表于 2025-3-29 20:25:12
WaveTransform: Crafting Adversarial Examples via Input Decompositionformation present in images have been extracted and learnt by a host of representation learning techniques, including deep learning. Inspired by this observation, we introduce a novel class of adversarial attacks, namely ‘WaveTransform’, that creates adversarial noise corresponding to low-frequency
spondylosis
发表于 2025-3-30 02:32:05
Robust Super-Resolution of Real Faces Using Smooth Featuresependent noises. So, in order to successfully super-resolve real faces, a method needs to be robust to a wide range of noise, blur, compression artifacts etc. Some of the recent works attempt to model these degradations from a dataset of real images using a Generative Adversarial Network (GAN). They
种类
发表于 2025-3-30 06:43:42
Improved Robustness to Open Set Inputs via Tempered Mixupent for training. However, real-world classifiers must handle inputs that are far from the training distribution including samples from unknown classes. Open set robustness refers to the ability to properly label samples from previously unseen categories as novel and avoid high-confidence, incorrect