Zobrazeno 1 - 10
of 8 646
pro vyhledávání: '"Gao, Xiao"'
Autor:
Wang, Yihan, Lu, Yiwei, Zhang, Guojun, Boenisch, Franziska, Dziedzic, Adam, Yu, Yaoliang, Gao, Xiao-Shan
Machine unlearning provides viable solutions to revoke the effect of certain training data on pre-trained model parameters. Existing approaches provide unlearning recipes for classification and generative models. However, a category of important mach
Externí odkaz:
http://arxiv.org/abs/2406.03603
The generalization bound is a crucial theoretical tool for assessing the generalizability of learning methods and there exist vast literatures on generalizability of normal learning, adversarial learning, and data poisoning. Unlike other data poison
Externí odkaz:
http://arxiv.org/abs/2406.00588
This paper studies the challenging black-box adversarial attack that aims to generate adversarial examples against a black-box model by only using output feedback of the model to input queries. Some previous methods improve the query efficiency by in
Externí odkaz:
http://arxiv.org/abs/2405.19098
Availability attacks can prevent the unauthorized use of private data and commercial datasets by generating imperceptible noise and making unlearnable examples before release. Ideally, the obtained unlearnability prevents algorithms from training usa
Externí odkaz:
http://arxiv.org/abs/2402.04010
Unlearnable example attacks are data poisoning attacks aiming to degrade the clean test accuracy of deep learning by adding imperceptible perturbations to the training samples, which can be formulated as a bi-level optimization problem. However, dire
Externí odkaz:
http://arxiv.org/abs/2401.17523
The proof of information inequalities and identities under linear constraints on the information measures is an important problem in information theory. For this purpose, ITIP and other variant algorithms have been developed and implemented, which ar
Externí odkaz:
http://arxiv.org/abs/2401.14916
Stability analysis is an essential aspect of studying the generalization ability of deep learning, as it involves deriving generalization bounds for stochastic gradient descent-based training algorithms. Adversarial training is the most widely used d
Externí odkaz:
http://arxiv.org/abs/2401.03156
Privacy preserving has become increasingly critical with the emergence of social media. Unlearnable examples have been proposed to avoid leaking personal information on the Internet by degrading generalization abilities of deep learning models. Howev
Externí odkaz:
http://arxiv.org/abs/2312.08898
Publikováno v:
Eur. Phys. J. C (2023) 83:1052
In this paper, we investigate the shadows and rings of the charged Horndeski black hole illuminated by accretion flow that is both geometrically and optically thin. We consider two types of accretion models: spherical and thin-disk accretion flow. We
Externí odkaz:
http://arxiv.org/abs/2311.11780
Within the realm of image recognition, a specific category of multi-label classification (MLC) challenges arises when objects within the visual field may occlude one another, demanding simultaneous identification of both occluded and occluding object
Externí odkaz:
http://arxiv.org/abs/2310.11834