Zobrazeno 1 - 10
of 64 887
pro vyhledávání: '"Gunn, A. A."'
Autor:
DeStefano, Nicolas, Pegahan, Saeed, Ramaswamy, Aneesh, Aubin, Seth, Averett, T., Camsonne, Alexandre, Malinovskaya, Svetlana, Mikhailov, Eugeniy E., Park, Gunn, Zhang, Shukui, Novikova, Irina
We present a quantum optics-based detection method for determining the position and current of an electron beam. As electrons pass through a dilute vapor of rubidium atoms, their magnetic field perturb the atomic spin's quantum state and causes polar
Externí odkaz:
http://arxiv.org/abs/2412.02686
Autor:
Zhao, Xuandong, Gunn, Sam, Christ, Miranda, Fairoze, Jaiden, Fabrega, Andres, Carlini, Nicholas, Garg, Sanjam, Hong, Sanghyun, Nasr, Milad, Tramer, Florian, Jha, Somesh, Li, Lei, Wang, Yu-Xiang, Song, Dawn
As the outputs of generative AI (GenAI) techniques improve in quality, it becomes increasingly challenging to distinguish them from human-created content. Watermarking schemes are a promising approach to address the problem of distinguishing between
Externí odkaz:
http://arxiv.org/abs/2411.18479
Pseudorandom codes are error-correcting codes with the property that no efficient adversary can distinguish encodings from uniformly random strings. They were recently introduced by Christ and Gunn [CRYPTO 2024] for the purpose of watermarking the ou
Externí odkaz:
http://arxiv.org/abs/2411.05947
Gaussian process are a widely-used statistical tool for conducting non-parametric inference in applied sciences, with many computational packages available to fit to data and predict future observations. We study the use of the Greta software for Bay
Externí odkaz:
http://arxiv.org/abs/2411.05556
Autor:
Gunn, Sam, Movassagh, Ramis
The meteoric rise in power and popularity of machine learning models dependent on valuable training data has reignited a basic tension between the power of running a program locally and the risk of exposing details of that program to the user. At the
Externí odkaz:
http://arxiv.org/abs/2411.03305
The recent explosion of high-quality language models has necessitated new methods for identifying AI-generated text. Watermarking is a leading solution and could prove to be an essential tool in the age of generative AI. Existing approaches embed wat
Externí odkaz:
http://arxiv.org/abs/2410.18861
We present the first undetectable watermarking scheme for generative image models. Undetectability ensures that no efficient adversary can distinguish between watermarked and un-watermarked images, even after making many adaptive queries. In particul
Externí odkaz:
http://arxiv.org/abs/2410.07369
This article proves the following theorem, first enunciated by Roger Penrose about 70 years ago: In $\mathbb{R}P^2$, if regular conics are assigned to seven of the vertices of a combinatorial cube such that (i) conics connected by an edge are in doub
Externí odkaz:
http://arxiv.org/abs/2409.17150
When light primordial black holes (PBHs) evaporate in the early Universe, they locally reheat the surrounding plasma, creating hot spots with temperatures that can be significantly higher than the average plasma temperature. In this work, we provide
Externí odkaz:
http://arxiv.org/abs/2409.02173
Autor:
Simpson, Lachlan, Costanza, Federico, Millar, Kyle, Cheng, Adriel, Lim, Cheng-Chew, Chew, Hong Gunn
Adversarial attacks on explainability models have drastic consequences when explanations are used to understand the reasoning of neural networks in safety critical systems. Path methods are one such class of attribution methods susceptible to adversa
Externí odkaz:
http://arxiv.org/abs/2407.16233