Zobrazeno 1 - 10
of 9 026
pro vyhledávání: '"Shilov, A."'
Generative Artificial Intelligence (Gen-AI) models are increasingly used to produce content across domains, including text, images, and audio. While these models represent a major technical breakthrough, they gain their generative capabilities from b
Externí odkaz:
http://arxiv.org/abs/2412.08549
Membership inference attacks (MIAs) are widely used to empirically assess the privacy risks of samples used to train a target machine learning model. State-of-the-art methods however require training hundreds of shadow models, with the same size and
Externí odkaz:
http://arxiv.org/abs/2411.05743
Autor:
Meeus, Matthieu, Shilov, Igor, Jain, Shubham, Faysse, Manuel, Rei, Marek, de Montjoye, Yves-Alexandre
Whether LLMs memorize their training data and what this means, from privacy leakage to detecting copyright violations -- has become a rapidly growing area of research over the last two years. In recent months, more than 10 new methods have been propo
Externí odkaz:
http://arxiv.org/abs/2406.17975
Autor:
Shilov, A. L., Elesin, L., Grebenko, A., Kleshch, V. I., Kashchenko, M. A., Mazurenko, I., Titova, E., Zharkova, E., Yakovlev, D. S., Novoselov, K. S., Ghazaryan, D. A., Dremov, V., Bandurin, D. A.
Multilayer van der Waals (vdW) heterostructures have become an important platform in which to study novel fundamental effects emerging at the nanoscale. Standard nanopatterning techniques relying on electron-beam lithography and reactive ion etching,
Externí odkaz:
http://arxiv.org/abs/2406.16354
Autor:
Wicker, Matthew, Sosnin, Philip, Shilov, Igor, Janik, Adrianna, Müller, Mark N., de Montjoye, Yves-Alexandre, Weller, Adrian, Tsay, Calvin
Differential privacy upper-bounds the information leakage of machine learning models, yet providing meaningful privacy guarantees has proven to be challenging in practice. The private prediction setting where model outputs are privatized is being inv
Externí odkaz:
http://arxiv.org/abs/2406.13433
The immense datasets used to develop Large Language Models (LLMs) often include copyright-protected content, typically without the content creator's consent. Copyright traps have been proposed to be injected into the original content, improving conte
Externí odkaz:
http://arxiv.org/abs/2405.15523
Autor:
Kravtsov, M., Shilov, A. L., Yang, Y., Pryadilin, T., Kashchenko, M. A., Popova, O., Titova, M., Voropaev, D., Wang, Y., Shein, K., Gayduchenko, I., Goltsman, G. N., Lukianov, M., Kudriashov, A., Taniguchi, T., Watanabe, K., Svintsov, D. A., Principi, A., Adam, S., Novoselov, K. S., Bandurin, D. A.
Publikováno v:
Nature Nanotechnology (2024)
Light incident upon materials can induce changes in their electrical conductivity, a phenomenon referred to as photoresistance. In semiconductors, the photoresistance is negative, as light-induced promotion of electrons across the band gap enhances t
Externí odkaz:
http://arxiv.org/abs/2403.18492
Questions of fair use of copyright-protected content to train Large Language Models (LLMs) are being actively debated. Document-level inference has been proposed as a new task: inferring from black-box access to the trained model whether a piece of c
Externí odkaz:
http://arxiv.org/abs/2402.09363
Autor:
Shilov, A. O., Kamalov, R. V., Karabanalov, M. S., Chukin, A. V., Vokhmintsev, A. S., Mikhalevsky, G. B., Zamyatin, D. A., Henaish, A. M. A., Weinstein, I. A.
Hafnia-based nanostructures and other high-k dielectrics are promising wide-gap materials for developing new opto- and nanoelectronics devices. They possess a unique combination of physical and chemical properties such as insensitivity to electrical
Externí odkaz:
http://arxiv.org/abs/2311.06939
Autor:
Shilov, A. L., Kashchenko, M. A., Pantaleón, P. A., Kravtsov, M., Kudriashov, A., Zhan, Z., Taniguchi, T., Watanabe, K., Slizovskiy, S., Novoselov, K. S., Fal'ko, V. I., Guinea, F., Bandurin, D. A.
Publikováno v:
ACS Nano 2024
Twist-controlled moire superlattices (MS) have emerged as a versatile platform in which to realize artificial systems with complex electronic spectra. Bernal-stacked bilayer graphene (BLG) and hexagonal boron nitride (hBN) form an interesting example
Externí odkaz:
http://arxiv.org/abs/2311.05124