Cyber Security Glossary

Find definitions for IT security and compliance in our online glossary of key terms, acronyms, and vocabulary.

AJAX progress indicator
All categories All categories
  • Term
    Definition
  • "Functionality for providing details on or causes for fairness metric results."
  • "Systems deliver accompanying evidence or reason(s) for all outputs."
  • Definition: A technique to breach the security of a network or information system in violation of security policy.
  • Definition: In the NICE Framework, cybersecurity work where a person: Analyzes collected information to identify vulnerabilities and potential for exploitation.
  • "Exploratory Data Analysis (EDA) is an approach/philosophy for data analysis that employs a variety of techniques (mostly graphical) to 1. maximize insight into a data set; 2. uncover underlying structure; 3. extract important variables; 4. detect outliers and anomalies; 5. test underlying(...)
  • Definition: The condition of being unprotected, thereby allowing access to information or access to capabilities that an attacker can use to enter a system or network.
  • "A study has external validity to the degree that its results can be extended (generalized) beyond the limited research setting and sample in which they were obtained"
  • An Internet based access method to a corporate intranet site by limited or total access through a security firewall. This type of access is typically utilized in cases of joint venture and vendor client relationships. 
  • "A technology for identifying specific people based on pictures or videos. It operates by analyzing features such as the structure of the face, the distance between the eyes, and the angles between a person’s eyes, nose, and mouth. It is controversial because of worries about privacy invasion,(...)
  • Definition: The inability of a system or component to perform its required functions within specified performance requirements.
  • "promoting the false perception that a machine learning model respects some ethical values"
  • ""“cultural assumptions” regarding “the regulation of [human] life effected by stated and unstated rules of interaction,” rules that most interactants see as “generally applicable” and “reasonable.” (We have to get the full definition from the book..."
  • "A quantification of unwanted bias in training data or models."
  • "An example in which the predictive model mistakenly classifies an item as in the negative class."
  • "An example in which the model mistakenly classifies an item as in the positive class"
  • A family range describes the range of documents from the first Bates production number assigned to the first page of the top most parent document through the last Bates production number assigned to the last page of the last child document. 
  • A family relationship is formed among two or more documents that have a connection or relatedness because of some factor. 
  • "The ability of a system or component to continue normal operation despite the presence of hardware or software faults"
  • "A label whose value corresponds to an outcome that provides an advantage to the recipient. The opposite is an unfavorable label."
  • "An attribute containing information for predicting the label."
  • "a more general method in which one tries to develop a transformation of the input space onto the lowdimensional subspace that preserves most of the relevant information"
  • "how important the feature was for the classification performance of the model; a measure of the individual contribution of the corresponding feature for a particular classifier, regardless of the shape (e.g., linear or nonlinear relationship) or direction of the feature effect"
  • "Unlike joint distribution shift detection, which cannot localize which features caused the shift, we define a new hypothesis test for each feature individually. Naïvely, the simplest test would be to check if the marginal distributions have changed for each feature (as explored by [25]);(...)
  • "a learning model which addresses the problem of data governance and privacy by training algorithms collaboratively without transferring the data to another location."
  • "describes the process of leveraging the output of an AI system and corresponding end-user actions in order to retrain and improve models over time. The AI-generated output (predictions or recommendations) are compared against the final decision (for example, to perform work or not) and(...)