Many things, such as goods, products, and websites are evaluated based on user's notes and comments. One popular research project is sentiment analysis, which aims to extract information from notes and comments as...
详细信息
Medical imaging coupled with Artificial Intelligence (AI) applications, in particular Deep learning (DL) and Machine Learning (ML), can speed up the disease diagnostic process. The purpose of this work is to present a...
详细信息
Steganography is a technique used to hide data within other data, emerging from the realization that information is valuable and must be concealed. By considering the potential of blockchain technology, which produces...
详细信息
We propose a hybrid e-book recommendation mechanism that leverages collaborative filtering and content-based recommendation paradigms to address inherent challenges in e-learning systems. For collaborative filtering, ...
详细信息
With the rise of real-time data collection through mobile devices such as smartphones, user-driven decision-making systems in various fields such as transportation and healthcare have advanced significantly. However, ...
详细信息
Fires are becoming one of the major natural hazards that threaten the ecology, economy, human life and even more worldwide. Therefore, early fire detection systems are crucial to prevent fires from spreading out of co...
详细信息
Real-world images often encompass embedded texts that adhere to disparate disciplines like business, education, and amusement, to name a few. Such images are graphically rich in terms of font attributes, color distrib...
详细信息
Recently it was shown that the response time of First-Come- First-Served (FCFS) scheduling can be stochastically and asymptotically improved upon by the Nudge scheduling algorithm in case of light-tailed job size dist...
详细信息
Evasion attacks on cyber-enabled machine learning (ML) models have recently gained significant traction for their ability to swiftly compel ML models to deviate from their original decisions without substantially affe...
详细信息
Evasion attacks on cyber-enabled machine learning (ML) models have recently gained significant traction for their ability to swiftly compel ML models to deviate from their original decisions without substantially affecting model accuracy during the testing phase. In this article, we initially present a meticulously formulated theoretical framework for a novel and potent evasion attack, leveraging mean-shift perturbation. This attack demonstrates remarkable efficiency in deceiving a wide array of ML models. Subsequently, the urgency of fortifying against such evasion attacks is underscored. It’s worth noting that existing defenses are predominantly model-driven, and their efficacy diminishes when concurrently deployed as a universal defense against both poisoning and evasion attacks. Moreover, empirical evidence from various studies suggests that a single defense mechanism falls short in safeguarding learning models against the myriad forms of adversarial attacks. To alleviate these challenges, we introduced Adaptive Ensemble of Filters (AEF), a defense framework characterized by its robust, transferable, model-agnostic, input distribution-independent, and cross-model-supportive nature. The AEF strategically selects filters to safeguard a target ML model from various well-known poisoning (e.g., Metapoison) and evasion (utilizing mean-shift perturbations, JSMA, FGSM, PGD, BIM, and C&W) attacks, establishing itself as a universal defense against diverse adversarial attacks. Theoretical analysis assures the existence of optimal filter ensembles across different input distributions and adversarial attack landscapes, without encountering mode collapses and vanishing gradients. Our claims are substantiated through validation on three publicly available image datasets—MNIST, CIFAR-10, and EuroSAT. IEEE
We propose a novel way of combining two canonical models used in Artificial Intelligence (AI): Bayesian Networks (BN) and Ant Colony Optimisation (ACO) in order to obtain a fast graph-traversal algorithm that establis...
详细信息
暂无评论