Security, privacy, and fairness · MLD-0034
Adversarial example
An input deliberately modified to induce a model error under a specified perturbation model.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Test image classifiers with bounded input perturbations.
Original caveat
Imperceptibility is common but not required in every definition.
Context and aliases
Level: Intermediate. Stages: Data · Training · Evaluation · Deployment · Governance.
Tags: ML · DL · SLM · LLM · Security · Privacy · Safety.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- The Algorithmic Foundations of Differential Privacy ↗ · Reference link
- Google Machine Learning Glossary ↗ · Consulted
- OWASP Top 10 for LLM Applications ↗ · Reference link
- Original reference URL ↗