Skip to content

alphaPlan · Cybersecurity · Cheat-sheet 07

Using AI Safely

Use approved AI tools, keep secrets out of them, doubt what comes back, and remember that AI is a helper, a target and a tool for attackers all at once.

Ideas to remember

  1. 01Shadow AI is using tools your workplace has not approved; what you paste in leaves your control and may be stored or used for training.
  2. 02Prompt injection hides instructions in text an AI reads, and anything your AI reads, your AI might obey.
  3. 03Adversarial inputs that look normal to you can push a model to a confident wrong answer, so one AI decision is never the final word.
  4. 04Defensive AI spots phishing, unusual behaviour and new malware at a scale no human team could, but it supports human judgement rather than replacing it.
  5. 05AI systems are targets too: poisoned training data bends a model's behaviour, and trained models get stolen or copied.
  6. 06Organisations that rely on AI have to protect it like any other critical asset, and you can expect that of them.

Words

Shadow AI
Using AI tools and services your workplace has not reviewed or approved.
Prompt injection
Planted instructions in a web page, email, document or file that an AI assistant treats as commands.
Adversarial machine learning
Crafting inputs so a model gets the answer wrong on purpose while looking normal to a person.
Data poisoning
Slipping bad examples into the data a model learns from to quietly bend its behaviour.
Malware
Harmful software; defensive AI can flag it by what a program does, not only by a list of known files.

Do this

  • Use the AI tools your workplace has chosen, and ask IT before pasting anything sensitive into any other.
  • Keep passwords, codes and secrets out of AI assistants, and limit what access they hold on your behalf.
  • Check important claims yourself before acting on an AI summary of outside documents, web pages or emails.
  • Keep a human in the loop and a way to question any automated decision that matters.
  • Before trusting an AI service with your data, check whether the provider says how the model and your data are protected.

Watch out

  • A data leak through an unapproved tool is still a leak even though nothing was 'hacked', and nobody knows the information went out.
  • An AI that suddenly makes an odd, urgent or out-of-character recommendation may be following someone else's hidden instructions.
  • A fooled model gives its wrong answer with full confidence; 'the system said so' is not the end of the conversation.

From the lessons: Shadow AI, Prompt injection, Adversarial machine learning, AI as a defender, AI as a target. codeforalbania.com/en/learn/cybersecurity/07-using-ai-safely

shënim: ky material u krijua në kuadër të projektit 'U.S. Cybersecurity Leadership in AI for Albania', financuar nga departamenti i shtetit i shteteve të bashkuara. mendimet, gjetjet dhe përfundimet e paraqitura këtu janë të autorit(ëve) dhe nuk pasqyrojnë domosdoshmërisht ato të departamentit të shtetit të shteteve të bashkuara.

Disclaimer: This material was created on behalf of the 'U.S. Cybersecurity Leadership in AI for Albania' project, funded by the United States Department of State. The opinions, findings, and conclusions stated herein are those of the author(s) and do not necessarily reflect those of the United States Department of State.

Disclaimer

Found something unclear, outdated or improvable? Suggest an improvement