Information Systems (IS) are the organized collection, processing, maintenance, transmission, and dissemination...
Read more
A membership inference attack is a machine learning privacy attack in which an attacker tries to determine...
Read more
Chain of thought, or chain of thought prompting, is a prompt engineering technique where the user asks an AI...
Read more
A model inversion attack is a machine learning privacy attack in which an attacker uses a model’s outputs to...
Read more
Adversarial Example / Adversarial Machine Learning (Adversarial ML) refers to techniques where attackers...
Read more
Prompt injection is a class of attacks in which a malicious actor crafts inputs designed to manipulate a large...
Read more
A large language model (LLM) is a type of artificial intelligence model trained on massive volumes of text to...
Read more
Retrieval-Augmented Generation (RAG) is an AI architecture pattern that combines a search or retrieval step with...
Read more
A model extraction attack is a technique in which an adversary repeatedly queries a hosted machine learning or AI...
Read more
Data poisoning is an attack in which an adversary deliberately injects malicious, misleading, or biased data into...
Read more
Prompt engineering is the practice of designing, structuring, and refining the instructions given to a large...
Read more
A vector database, also called a vector store, is a specialized data system designed to store and search vector...
Read moreGet sharper eyes on human risks, with the positive approach that beats traditional phish testing.
