Results for "privacy attack"

Privacy Attack

Intermediate

Attacks that infer whether specific records were in training data, or reconstruct sensitive training examples.

Imagine if someone could tell whether your personal information was used to train a smart assistant just by asking it questions. That’s what a privacy attack does—it tries to find out if specific data was part of the training set. This can be really concerning because it means that private detail...

AdvertisementAd space — search-top

17 results

Differential Privacy Intermediate

A formal privacy framework ensuring outputs do not reveal much about any single individual’s data contribution.

Security & Privacy
Privacy Attack Intermediate

Attacks that infer whether specific records were in training data, or reconstruct sensitive training examples.

Foundations & Theory
Supply Chain Attack Intermediate

Compromising AI systems via libraries, models, or datasets.

AI Economics & Strategy
Gradient Leakage Intermediate

Recovering training data from gradients.

AI Economics & Strategy
Data Protection Impact Assessment Intermediate

Privacy risk analysis under GDPR-like laws.

Governance & Ethics
Model Inversion Intermediate

Inferring sensitive features of training data.

AI Economics & Strategy
Prompt Injection Intermediate

Attacks that manipulate model instructions (especially via retrieved content) to override system goals or exfiltrate data.

Foundations & Theory
Synthetic Data Intermediate

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

Foundations & Theory
PII Intermediate

Information that can identify an individual (directly or indirectly); requires careful handling and compliance.

Foundations & Theory
Federated Learning Intermediate

Training across many devices/silos without centralizing raw data; aggregates updates, not data.

Foundations & Theory
Responsible AI Intermediate

A discipline ensuring AI systems are fair, safe, transparent, privacy-preserving, and accountable throughout lifecycle.

Governance & Ethics
Data Poisoning Intermediate

Maliciously inserting or altering training data to implant backdoors or degrade performance.

Foundations & Theory
Chain-of-Thought Intermediate

Stepwise reasoning patterns that can improve multi-step tasks; often handled implicitly or summarized for safety/privacy.

Foundations & Theory
NIST AI RMF Intermediate

US framework for AI risk governance.

Governance & Ethics
Edge Inference Intermediate

Running models locally.

AI Economics & Strategy
Predictive Policing Intermediate

AI predicting crime patterns (highly controversial).

AI in Law
AI Treaty Intermediate

International agreements on AI.

Governance & Ethics

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.