QUESTION: 33

Which of the following pieces of AI technology provides the ability to create fake videos?

Generative adversarial networks (GAN)
Long short-term memory (LSTM) networks
Recurrent neural networks (RNN)
Support-vector machines (SVM)

Answer(s): A

Explanation:

Generative adversarial networks (GAN) are a type of AI technology that can create fake videos, images, audio, or text that are realistic and indistinguishable from real ones. GAN consist of two neural networks: a generator and a discriminator. The generator tries to produce fake samples from random noise, while the discriminator tries to distinguish between real and fake samples. The two networks compete against each other in a game-like scenario, where the generator tries to fool the discriminator and the discriminator tries to catch the generator. Through this process, both networks improve their abilities until they reach an equilibrium where the generator can produce convincing fakes.

Reveal Solution Next Question

QUESTION: 34

Which database is designed to better anticipate and avoid risks of AI systems causing safety, fairness, or other ethical problems?

Asset
Code Repository
Configuration Management
Incident

Answer(s): D

Explanation:

An incident database is a database that is designed to better anticipate and avoid risks of AI systems causing safety, fairness, or other ethical problems. An incident database collects and stores information about incidents or events where AI systems have caused or contributed to negative outcomes or harms, such as accidents, errors, biases, discriminations, or violations. An incident database can help identify patterns, trends, causes, impacts, and solutions for AI-related incidents, as well as provide guidance and best practices for preventing or mitigating future incidents.

Reveal Solution Next Question

QUESTION: 35

What is the open framework designed to help detect, respond to, and remediate threats in ML

systems?

Adversarial ML Threat Matrix
MITRE ATT&CK® Matrix
OWASP Threat and Safeguard Matrix
Threat Susceptibility Matrix

Answer(s): A

Explanation:

The Adversarial ML Threat Matrix is an open framework designed to help detect, respond to, and remediate threats in ML systems. The Adversarial ML Threat Matrix is inspired by the MITRE

ATT&CK® Matrix1, which is a framework for describing cyberattacks across various stages of an attack lifecycle. The Adversarial ML Threat Matrix adapts this framework to address specific threats and vulnerabilities in ML systems, such as data poisoning, model stealing, model evasion, or model inversion. The Adversarial ML Threat Matrix provides a structured way to organize and classify adversarial techniques, tactics, procedures, examples, and mitigations for ML systems.

Reveal Solution Next Question

QUESTION: 36

Which two techniques are used to build personas in the ML development lifecycle? (Select two.)

Population estimates
Population regression
Population resampling
Population triage
Population variance

Answer(s): A,D

Explanation:

Personas are fictional characters that represent the potential users or customers of an ML system. Personas can help understand the needs, goals, preferences, and behaviors of the target audience, as well as design and evaluate the system from their perspective. Some of the techniques that are used to build personas in the ML development lifecycle are:
Population estimates: Population estimates are statistical methods that estimate the size, characteristics, and distribution of a population based on a sample or a census. Population estimates can help identify and quantify the potential market segments and user groups for an ML system, as well as their demographics, locations, and behaviors.
Population triage: Population triage is a process of prioritizing and selecting the most relevant and representative personas for an ML system based on some criteria or metrics. Population triage can help focus on the key user needs and scenarios, as well as avoid creating too many or too few personas.

Reveal Solution Next Question

Free AIP-210 Exam Braindumps

QUESTION: 33

Explanation:

QUESTION: 34

Explanation:

QUESTION: 35

Explanation:

QUESTION: 36

Explanation: