ARTIFICIAL INTELLIGENCE: CYBERSECURITY OF THE NEW GENERATION
DOI:
https://doi.org/10.18372/2225-5036.30.19235Keywords:
Artificial Intelligence (AI), cybersecurity, cyber threats, machine learning, deep learning, Intrusion Detection Systems (IDS), Intrusion Prevention Systems (IPS), Deception technologies, SIEM systems, UEBA systems, code analysis, sandboxes, malicious use of AI, digital transformation, Internet of Things (IoT)Abstract
The article discusses the role of artificial intelligence in shaping the cybersecurity of the new generation. With the rise of cyber threats and the sophistication of attackers' methods, traditional defense mechanisms become insufficiently effective. AI offers innovative solutions to counter these challenges by its ability to analyze large volumes of data, detect anomalies, and predict the behavior of attackers. Various applications of AI for data protection are considered, including: early detection of cyber threats; data analysis from various sources to identify potential threats; predicting the likelihood of cyber attacks; developing intelligent access control systems; automating responses to cyber incidents; and improving encryption algorithms. New cyber attack methods used by hackers are also revealed, such as data poisoning, generating malicious software using generative adversarial networks (GANs), creating fake content and deepfakes, IoT device attacks, and using AI to enhance social engineering effectiveness. Additionally, methods for analyzing code vulnerabilities using AI, including static code analysis (SAST) and dynamic code analysis (DAST), as well as the use of sandboxes for secure code testing, are discussed. Special attention is paid to the capabilities and risks associated with the "dark side" of AI, such as FraudGPT, WormGPT, and Evil-GPT, which are used by cybercriminals to carry out cyber attacks. Emphasis is placed on the need for a comprehensive approach to cybersecurity, combining the power of AI algorithms with expert knowledge, user education, and international cooperation. Further research and development in this field are critically important for ensuring the security of the digital world in the face of constantly growing cyber threats. To provide a solid research foundation, a comprehensive study of scientific literature and relevant publications dedicated to the role of artificial intelligence in modern cybersecurity was conducted.
References
Shutenko V. (2023, September 13). AI in Cybersecurity: Exploring the Top 6 Use Cases.
https://www.techmagic.co/blog/ai-in-cybersecurity/
Jansasoy J. (2023, July 24). 10 IoT Security Challenges and Solutions To Protect Your Devices.
https://www.linkedin.com/pulse/10-iot-security-challenges-solutions-protect-your-2023-jansasoy-/
Roytman M. (2024, March 5). The Future Of AI And ML In Cybersecurity.
https://www.forbes.com/sites/forbestechcouncil/2024/03/05/the-future-of-ai-and-ml-in-cybersecurity/
Rjoub G., Bentahar J., Abdel Wahab O., Mizouni R., Song A., Cohen R., Otrok H., Mourad A. (2023). A Survey on Explainable Artificial Intelligence for Cybersecurity.
https://arxiv.org/pdf/2303.12942.pdf
Thwaini Mohammed. (2022). Anomaly Detection in Network Traffic using Machine Learning for Early Threat Detection.
https://dm.saludcyt.ar/index.php/dm/article/view/72/
Bisceglia N. (2023, October 22). ChatGPT and Cybersecurity: Risks, Potential Benefits & More.
https://teampassword.com/blog/chatgpt-and-cybersecurity/
Brundage M., Avin S., Clark J., Toner H., Eckersley P., Garfinkel B., ... & Amodei D. (2018) The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation.
https://arxiv.org/ftp/arxiv/papers/1802/1802.07228.pdf
Binns R. (2024, March 29). AI Names 2024’s Biggest Cybersecurity Threats – and AI is One of Them.
https://www.techopedia.com/ai-names-biggest-cybersecurity-threats
National Institute of Standards and Technology (NIST). (2024, February 26). The NIST Cybersecurity Framework (CSF) 2.0 [NIST Cybersecurity White Paper (CSWP) NIST CSWP 29]. https://doi.org/10.6028/NIST.CSWP.29
International Telecommunication Union (ITU). AI for Good Global Summit. https://aiforgood.itu.int/
OpenAI Blog. https://openai.com/blog
Hu W., Tan Y. A. (2020). Generating Adversarial Malware Examples for Black-Box Attacks Based on GAN.
https://arxiv.org/pdf/1702.05983.pdf
Rosenberg I., Shabtai A., Rokach L., Elovici Y. (2018). Generic Black-Box End-to-End Attack Against State of the Art API Call Based Malware Classifiers.https://arxiv.org/pdf/1707.05970.pdf
Cloudflare. (2023, October 26). The phishing implications of AI chatbots.https://www.cloudflare.com/the-net/chatgpt-phishing/
Stoecklin M. P. (2018, August 8). DeepLocker: How AI Can Power a Stealthy New Breed of Malware.https://securityintelligence.com/deeplocker-how-ai-can-power-a-stealthy-new-breed-of-malware/
Maurel H., Vidal S., Rezk, T. (2021). Statically identifying XSS using deep learning. https://inria.hal.science/hal-03273564/document
Lodeiro-Santiago M., Caballero-Gil C., Caballero-Gil P. (2022). Collaborative SQL-injections detection system with machine learning. https://arxiv.org/pdf/2209.06553.pdf
Allamanis M., Barr E. T., Devanbu P., Sutton C. (2018). A survey of machine learning for big code and naturalness. https://arxiv.org/pdf/1709.06182.pdf
David O. E., Netanyahu N. S. (2015). DeepSign: Deep learning for automatic malware signature generation and classification. https://arxiv.org/pdf/1711.08336.pdf
Zhang J. M., Harman M., Ma L., Liu Y. (2019, May). Machine learning testing: Survey, landscapes and horizons.
https://arxiv.org/pdf/1906.10742.pdf
Hassan A. (2023, May 16). Top Sandbox Environments Using AI. https://www.linkedin.com/pulse/top-sandbox-environments-using-ai-ahmed-hassan
Amos Z. (2023, August 11). What Is FraudGPT?
https://hackernoon.com/what-is-fraudgpt
Berezovskyi D. (2023, March 15). DAN у GPT-4: як обійти модерацію вмісту. https://chatgpt.com.ua/post/dan-gpt-4-hacking-and-jailbreaking
coolaj86. Chat GPT "DAN" (and other "Jailbreaks").https://gist.github.com/coolaj86/6f4f7b30129b0251f61fa7baaa881516
Lukatsky A. (2023, September 7). FraudGPT, DarkGPT, WormGPT, Evil-GPT и другие джепеты.https://www.securitylab.ru/blog/personal/Business_without_danger/353102.php
Buckley O., Nurse J. R. C. (2024, February 8). Cybercriminals are creating their own AI chatbots to support hacking and scam users. https://theconversation.com/cybercriminals-are-creating-their-own-ai-chatbots-to-support-hacking-and-scam-users-222643
WormGPT. https://wormgpt.com.co/
Dutta T. S. (2023, August 10). Hackers Released New Black Hat AI Tool Evil-GPT as a Replacement for Worm GPT. https://cybersecuritynews.com/hackers-released-evil-gpt/
A10 Networks. How a bot herder attacks [Image]. https://www.a10networks.com/wp-content/uploads/how-a-bot-herder-attacks.png
