Resilience and resilient systems of artificial intelligence: taxonomy, models and methods

V Moskalenko, V Kharchenko, A Moskalenko… - Algorithms, 2023 - mdpi.com
Artificial intelligence systems are increasingly being used in industrial applications, security
and military contexts, disaster response complexes, policing and justice practices, finance …

A survey of bit-flip attacks on deep neural network and corresponding defense methods

C Qian, M Zhang, Y Nie, S Lu, H Cao - Electronics, 2023 - mdpi.com
As the machine learning-related technology has made great progress in recent years, deep
neural networks are widely used in many scenarios, including security-critical ones, which …

Stain: Stealthy avenues of attacks on horizontally collaborated convolutional neural network inference and their mitigation

AA Adeyemo, JJ Sanderson, TA Odetola… - IEEE …, 2023 - ieeexplore.ieee.org
With significant potential improvement in device-to-device (D2D) communication due to
improved wireless link capacity (eg, 5G and NextG systems), a collaboration of multiple …

Scaling Model Checking for DNN Analysis via State-Space Reduction and Input Segmentation (Extended Version)

M Naseer, O Hasan, M Shafique - arXiv preprint arXiv:2306.17323, 2023 - arxiv.org
Owing to their remarkable learning capabilities and performance in real-world applications,
the use of machine learning systems based on Neural Networks (NNs) has been …

Testing the Depth of ChatGPT's Comprehension via Cross-Modal Tasks Based on ASCII-Art: GPT3. 5's Abilities in Regard to Recognizing and Generating ASCII-Art …

D Bayani - arXiv preprint arXiv:2307.16806, 2023 - arxiv.org
Over the eight months since its release, ChatGPT and its underlying model, GPT3. 5, have
garnered massive attention, due to their potent mix of capability and accessibility. While a …

A Dynamic Architecture of an Anomaly Detection System in IoT Devices

MH Bhavsar - 2023 - search.proquest.com
Abstract As the Internet of Things (IoT) networks expand globally with an annual increase of
connected devices, providing better privacy and security to threats is becoming more …

Towards Securing Edge Intelligence for Inference in Horizontal Collaborative Environments

AA Adeyemo - 2023 - search.proquest.com
With the growing demand for real-time intelligence driven by device-to-device (D2D)
communication, deploying Deep Learning (DL) applications at the network edge becomes …

[PDF][PDF] Resilience-aware MLOps for resource-constrained AI-system

V Moskalenko, A Moskalenko, A Kudryavtsev… - 2024 - ceur-ws.org
Artificial intelligence systems are increasingly used in security-critical applications with
limited computing resources, which makes them vulnerable to such disturbances as …

Threats and Countermeasures in Digital Crime and Cyberterrorism

M Kumar, RS Raw, B Nagpal - Computational Intelligent Security …, 2023 - taylorfrancis.com
In the current era of the cyber space or cyber world, threats are the most difficult thing to
handle in which we have to maintain and manage the cyber security system to not get …

[PDF][PDF] Інформаційна технологія підвищення стійкості cистеми розпізнавання зображень до програмно-апаратних помилок

АВ Шелест - 2023 - essuir.sumdu.edu.ua
МІНІСТЕРСТВО ОСВІТИ І НАУКИ УКРАЇНИ Сумський державний університет Ф Page 1
МІНІСТЕРСТВО ОСВІТИ І НАУКИ УКРАЇНИ Сумський державний університет Факультет …