Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Gluch, Grzegorz"'
We formalize and extend existing definitions of backdoor-based watermarks and adversarial defenses as interactive protocols between two players. The existence of these schemes is inherently tied to the learning tasks for which they are designed. Our
Externí odkaz:
http://arxiv.org/abs/2410.08864
Autor:
Głuch, Grzegorz, Urbanke, Rudiger
We introduce a new notion of complexity of functions and we show that it has the following properties: (i) it governs a PAC Bayes-like generalization bound, (ii) for neural networks it relates to natural notions of complexity of functions (such as th
Externí odkaz:
http://arxiv.org/abs/2303.07874
Is it possible to operationally distinguish every entangled state from all separable states? This is a long-standing open question in quantum information. More concretely, assuming that two non-communicating parties interact classically with a verifi
Externí odkaz:
http://arxiv.org/abs/2303.02080
Modern machine learning systems have been applied successfully to a variety of tasks in recent years but making such systems robust against adversarially chosen modifications of input instances seems to be a much harder problem. It is probably fair t
Externí odkaz:
http://arxiv.org/abs/2112.09625
Autor:
Głuch, Grzegorz, Urbanke, Rüdiger
Symmetries have proven to be important ingredients in the analysis of neural networks. So far their use has mostly been implicit or seemingly coincidental. We undertake a systematic study of the role that symmetry plays. In particular, we clarify how
Externí odkaz:
http://arxiv.org/abs/2104.05508
Autor:
Głuch, Grzegorz, Urbanke, Rüdiger
We prove an exponential separation for the sample complexity between the standard PAC-learning model and a version of the Equivalence-Query-learning model. We then show that this separation has interesting implications for adversarial robustness. We
Externí odkaz:
http://arxiv.org/abs/2102.05475
Given a graph $G$ that can be partitioned into $k$ disjoint expanders with outer conductance upper bounded by $\epsilon\ll 1$, can we efficiently construct a small space data structure that allows quickly classifying vertices of $G$ according to the
Externí odkaz:
http://arxiv.org/abs/2101.05549
Autor:
Głuch, Grzegorz, Urbanke, Rüdiger
There are two main attack models considered in the adversarial robustness literature: black-box and white-box. We consider these threat models as two ends of a fine-grained spectrum, indexed by the number of queries the adversary can ask. Using this
Externí odkaz:
http://arxiv.org/abs/2010.01039
Autor:
Głuch, Grzegorz, Urbanke, Rüdiger
Modern machine learning models with very high accuracy have been shown to be vulnerable to small, adversarially chosen perturbations of the input. Given black-box access to a high-accuracy classifier $f$, we show how to construct a new classifier $g$
Externí odkaz:
http://arxiv.org/abs/1912.07561
In our paper [G{\l}uch, Marcinkowski, Ostropolski-Nalewaja, LICS ACM, 2018] we have solved an old problem stated in [Calvanese, De Giacomo, Lenzerini, Vardi, SPDS ACM, 2000] showing that query determinacy is undecidable for Regular Path Queries. Here
Externí odkaz:
http://arxiv.org/abs/1808.07767