Zobrazeno 1 - 10
of 306
pro vyhledávání: '"Sipper, Moshe"'
Kolmogorov-Arnold Networks (KANs) have recently emerged as a novel approach to function approximation, demonstrating remarkable potential in various domains. Despite their theoretical promise, the robustness of KANs under adversarial conditions has y
Externí odkaz:
http://arxiv.org/abs/2408.13809
We present two novel domain-independent genetic operators that harness the capabilities of deep learning: a crossover operator for genetic algorithms and a mutation operator for genetic programming. Deep Neural Crossover leverages the capabilities of
Externí odkaz:
http://arxiv.org/abs/2407.10477
This paper presents RADAR-Robust Adversarial Detection via Adversarial Retraining-an approach designed to enhance the robustness of adversarial detectors against adaptive attacks, while maintaining classifier performance. An adaptive attack is one wh
Externí odkaz:
http://arxiv.org/abs/2404.12120
Publikováno v:
Transactions on Machine Learning Research, 2024
We introduce a novel methodology for identifying adversarial attacks on deepfake detectors using eXplainable Artificial Intelligence (XAI). In an era characterized by digital advancement, deepfakes have emerged as a potent tool, creating a demand for
Externí odkaz:
http://arxiv.org/abs/2403.02955
Autor:
Sipper, Moshe, Moore, Jason H.
Publikováno v:
Genetic Programming and Evolvable Machines (2020) 21:169-179
The GPTP workshop series, which began in 2003, has served over the years as a focal meeting for genetic programming (GP) researchers. As such, we think it provides an excellent source for studying the development of GP over the past fifteen years. We
Externí odkaz:
http://arxiv.org/abs/2402.00425
Publikováno v:
J. Romero et al. (Eds.), EvoMUSART 2020, LNCS 12103, pp. 165-178, 2020
We have recently developed OMNIREP, a coevolutionary algorithm to discover both a representation and an interpreter that solve a particular problem of interest. Herein, we demonstrate that the OMNIREP framework can be successfully applied within the
Externí odkaz:
http://arxiv.org/abs/2401.11167
Publikováno v:
W. Banzhaf et al. (eds.), Genetic Programming Theory and Practice XVII, Genetic and Evolutionary Computation, 2020
The simultaneous evolution of two or more species with coupled fitness -- coevolution -- has been put to good use in the field of evolutionary computation. Herein, we present two new forms of coevolutionary algorithms, which we have recently designed
Externí odkaz:
http://arxiv.org/abs/2401.10515
Autor:
Sipper, Moshe
Explainability in deep networks has gained increased importance in recent years. We argue herein that an AI must be tasked not just with a task but also with an explanation of why said task was accomplished as such. We present a basic framework -- Ta
Externí odkaz:
http://arxiv.org/abs/2401.01732
We present a novel approach to performing fitness approximation in genetic algorithms (GAs) using machine-learning (ML) models, through dynamic adaptation to the evolutionary state. Maintaining a dataset of sampled individuals along with their actual
Externí odkaz:
http://arxiv.org/abs/2309.03318
Publikováno v:
ICLR 2024 Workshop on Secure and Trustworthy Large Language Models
Large language models (LLMs), designed to provide helpful and safe responses, often rely on alignment techniques to align with user intent and social guidelines. Unfortunately, this alignment can be exploited by malicious actors seeking to manipulate
Externí odkaz:
http://arxiv.org/abs/2309.01446