Machine Learning (ML) is a subset of artificial intelligence in which a system learns patterns from data instead of being hand-coded with fixed rules. An ML model is trained on examples, then used to classify, predict, rank, or detect new inputs based on what it learned. The quality of its output depends heavily on the quality and representativeness of the training data.
In cyber security, ML is widely used for spam filtering, malware detection, fraud scoring, and anomaly detection, because it can process large volumes of data faster than manual rules. But it also creates new risks. Attackers may try to poison training data, evade detection with carefully crafted inputs, or exploit weak model validation. Defenders therefore need data integrity checks, access controls, monitoring, and human review for high-impact decisions. In critical environments, ML should be treated as a system that can fail, drift, or be manipulated, not as an infallible oracle.