Results for "adversarial"

Adversarial Example

Intermediate

Inputs crafted to cause model errors or unsafe behavior, often imperceptible in vision or subtle in text.

An adversarial example is like a trick question designed to confuse a machine learning model. Imagine you have a smart assistant that can recognize pictures of cats and dogs. If someone changes a picture of a cat just a little bit, the assistant might get confused and think it's a dog instead. Th...

AdvertisementAd space — search-top

23 results

Adversarial Example Intermediate

Inputs crafted to cause model errors or unsafe behavior, often imperceptible in vision or subtle in text.

Foundations & Theory
Red Teaming Intermediate

Stress-testing models for failures, vulnerabilities, policy violations, and harmful behaviors before release.

Security & Privacy
Adversarial Market Advanced

Market reacting strategically to AI.

Agents & Autonomy
GAN Advanced

Two-network setup where generator fools a discriminator.

Diffusion & Generative Models
Latent Space Intermediate

The internal space where learned representations live; operations here often correlate with semantics or generative factors.

Foundations & Theory
Bias Intermediate

Systematic differences in model outcomes across groups; arises from data, labels, and deployment context.

Foundations & Theory
Synthetic Data Intermediate

Artificially created data used to train/test models; helpful for privacy and coverage, risky if unrealistic.

Foundations & Theory
Model Stealing Intermediate

Reconstructing a model or its capabilities via API queries or leaked artifacts.

Foundations & Theory
Backdoor / Trojan Intermediate

Hidden behavior activated by specific triggers, causing targeted mispredictions or undesired outputs.

Foundations & Theory
Secure Inference Intermediate

Methods to protect model/data during inference (e.g., trusted execution environments) from operators/attackers.

Foundations & Theory
Generative Model Advanced

Models that learn to generate samples resembling training data.

Diffusion & Generative Models
Mode Collapse Advanced

Generator produces limited variety of outputs.

Diffusion & Generative Models
Diffusion Model Advanced

Generative model that learns to reverse a gradual noise process.

Diffusion & Generative Models
Voice Conversion Intermediate

Changing speaker characteristics while preserving content.

Speech & Audio AI
Neural Vocoder Intermediate

Generates audio waveforms from spectrograms.

Speech & Audio AI
Specification Gaming Advanced

Model exploits poorly specified objectives.

AI Safety & Alignment
Reward Hacking Advanced

Maximizing reward without fulfilling real goal.

AI Safety & Alignment
Inner Alignment Advanced

Ensuring learned behavior matches intended objective.

AI Safety & Alignment
Robust Alignment Advanced

Maintaining alignment under new conditions.

AI Safety & Alignment
Spurious Correlation Intermediate

Model relies on irrelevant signals.

Model Failure Modes
Latent Dynamics Frontier

Modeling environment evolution in latent space.

World Models & Cognition
Algorithmic Bias Intermediate

Unequal performance across demographic groups.

AI in Healthcare
Competitive Game Advanced

Agents have opposing objectives.

Agents & Autonomy

Welcome to AI Glossary

The free, self-building AI dictionary. Help us keep it free—click an ad once in a while!

Search

Type any question or keyword into the search bar at the top.

Browse

Tap a letter in the A–Z bar to browse terms alphabetically, or filter by domain, industry, or difficulty level.

3D WordGraph

Fly around the interactive 3D graph to explore how AI concepts connect. Click any word to read its full definition.