feature extraction is a main step in all perceptual image hashing schemes in which robust features will led to better results in perceptual robustness. simplicity, discriminative power, computational efficiency and robustness to illumination changes are counted as distinguished properties of local binary pattern features. in this paper, we investigate the use of local binary patterns for percep...

the efficiency and robustness of reliability methods are two important factors in first order reliability method (form). the conjugate choice control (ccc) and directional chaos control method (dcc) were developed to improve the robustness and efficiency of form formula using the stability transformation method. in this paper, the ccc and dcc methods are applied for reliability analysis of a co...

Neural circuit motifs producing coexistent rhythmic patterns are treated as building blocks of multifunctional neuronal networks. We study the robustness of such a motif of inhibitory model neurons to reliably sustain bursting polyrhythms under random perturbations. Without noise, the exponential stability of each of the coexisting rhythms increases with strengthened synaptic coupling, thus ind...

One of the most important parameters in evaluating a watermarking algorithm is its capacity. Generally, watermarking capacity is expressed by bits per pixel (bpp) unit measure. But this measure does not show what the side effects would be on image quality, watermark robustness and capacity. In this paper we propose a three dimensional measure named Capacity surface which shows the effects of ca...

Federated learning (FL) emerges as a popular distributed schema that learns model from set of participating users without sharing raw data. One major challenge FL comes with heterogeneous users, who may have distributionally different (or non-iid) data and varying computation resources. As federated would use the for prediction, they often demand trained to be robust against malicious attackers...

The robustness of complex networks was one the first phenomena studied after inception network science. However, many contemporary presentations this theory do not go beyond original papers. Here we revisit topic with aim providing a deep but didactic introduction. We pay attention to some complications in computation giant component sizes that are commonly ignored. Following an intuitive proce...

In every corner of machine learning and statistics, there is a need for estimators that work not just in an idealized model, but even when their assumptions are violated. Unfortunately, high dimensions, being provably robust efficiently computable often at odds with each other. We give the first efficient algorithm estimating parameters high-dimensional Gaussian able to tolerate constant fracti...