Ploba logo

Find the right AI tool for the job: apps, agents, APIs, MCP servers and datasets, explained plainly.

Get the AI Digest

Discover

  • Explore
  • Top Charts
  • Categories
  • Agents
  • MCP servers
  • Developer tools

Learn & community

  • Learn AI
  • AI Glossary
  • Blog
  • Hackathons
  • People
  • AI Digest

For makers

  • List your tool
  • Docs
  • Claim a listing
  • Advertise
  • Write for us

Company

  • About
  • Careers
  • Changelog
  • Trust
  • Security
  • Contact

© 2026 Ploba. All rights reserved.

  • Privacy
  • Terms
  • Cookies
  • Advertising
  • All policies
llms.txt
Ploba logo
DiscoverHackathonsPeopleLearnAI Digest
Sign inGet started
AI glossary

Safety

AI reliability, security, alignment, misuse prevention and responsible development.

AllAgents16Development29Fundamentals10Generative AI18Machine Learning24Models14Protocols12Safety12

Safety terms

12 terms

  • AI AlignmentThe effort to ensure an AI system’s behavior and objectives reliably match intended human goals and constraints.
  • AI BiasSystematic skew in AI outputs resulting from flawed data, design, or deployment choices.
  • AI GuardrailsSafety mechanisms and policies put in place to ensure AI systems operate within defined ethical, legal, and operational boundaries.
  • AI JailbreakingThe practice of crafting specific prompts to bypass an AI model's built-in safety restrictions and moderation filters.
  • AI Red TeamingStructured adversarial testing intended to uncover unsafe behavior, security weaknesses, and failure modes in AI systems.
  • AI SafetyThe field of research and engineering focused on preventing AI systems from causing harm, whether through mistakes, misuse or behaviour that drifts from what people intended.
  • AI WatermarkingMarking AI-generated images, video, audio or text, visibly or invisibly, so people and software can tell it was made by AI.
  • Constitutional AIA training method in which an AI model critiques and revises its own answers against a written set of principles, reducing the need for humans to label harmful content.
  • Data PoisoningAn attack that corrupts the data a model learns from, so the finished model behaves wrongly or contains a hidden trigger planted by the attacker.
  • DeepfakeRealistic AI-generated or AI-altered video, audio or images that show a real person saying or doing something they never did.
  • Prompt InjectionA security vulnerability where malicious instructions disguised as normal input manipulate an AI model's intended behavior.
  • SycophancyWhen an AI model tells people what they want to hear, agreeing with them or flattering them, even when that makes its answer less accurate.