A deepfake is an image, video or audio clip created or altered with AI that convincingly shows real people saying or doing things that never happened. Alongside legitimate uses in film or dubbing, deepfakes are used for disinformation, reputational damage and fraud – for example fake calls from a supposed manager requesting a bank transfer. Protection includes call-backs via known channels, clear approval processes and labelling of AI-generated content.
A generative adversarial network (GAN) consists of two neural networks trained against each other: the generator creates artificial data such as images, and the discriminator tries to tell them apart from real ones. Through this contest the results become increasingly realistic. GANs were introduced in 2014 and shaped image generation before diffusion models became more widespread; they are used, for example, for synthetic training data or image enhancement.
Generative AI refers to AI systems that create new content – text, images, audio, video or program code – rather than merely sorting or assessing existing data. They are based on models that learn patterns from large amounts of data and use them to produce plausible new outputs. In business it is used, for example, to draft emails, summaries, product descriptions or image ideas. Results can contain errors and should be checked before use.
AI ethics deals with the moral questions surrounding the development and use of AI: fairness and discrimination, transparency and explainability, data protection, responsibility for errors, safety and the effects on work and society. For organisations it becomes concrete in guidelines, risk assessments, human oversight and honest communication about AI's limitations. Example: before a CV screening tool is introduced, it is checked for whether it disadvantages particular groups.
Fraud detection covers methods that identify suspicious transactions, orders, accounts or applications at an early stage. Rules and learning models look for warning signs such as differing delivery and billing addresses, unusual quantities, conspicuous time pressure or disposable email addresses. It is used in e-commerce, banking, insurance and payment services. As false alarms can affect genuine customers, hits should be reviewed by people rather than rejected automatically.
