• M. Sai Bala
• Ch. Sowjanya

Cybercrime is a growing problem worldwide, taking advantage of vulnerabilities in computer systems. Ethical hackers are increasingly focused on identifying these weaknesses and suggesting ways to protect against them. The cybersecurity community has a pressing need for the development of effective techniques to combat cyber threats. Many of the methods currently used in Intrusion Detection Systems (IDS) struggle to cope with the dynamic and complex nature of cyberattacks on computer networks. In response, the use of machine learning in cybersecurity has gained significant importance due to its effectiveness in addressing these issues. Machine learning techniques have been applied to tackle major challenges in cybersecurity, including intrusion detection, malware classification, spam detection, and phishing prevention. While machine learning cannot fully automate a cybersecurity system, it plays a crucial role in identifying threats more efficiently than traditional software-based approaches. This, in turn, eases the workload on security analysts. By employing adaptive methods, such as various machine learning techniques, we can achieve higher detection rates, lower false alarm rates, and reasonable computational and communication costs. Our primary objective is to recognize that the task of identifying cyberattacks is fundamentally distinct from other applications, which presents unique challenges. This distinctiveness makes it more challenging for the intrusion detection community to effectively implement machine learning methods..

Cyber-crime, Machine learning, Cyber-security, Intrusion detection system

"DATA POISONING ATTACKS ON FEDERATED MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 10, page no.h271-h278, October-2023, Available :http://www.jetir.org/papers/JETIR2310633.pdf

"DATA POISONING ATTACKS ON FEDERATED MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 10, page no. pph271-h278, October-2023, Available at : http://www.jetir.org/papers/JETIR2310633.pdf