{"content":{"markdown":"From spotting AI scams to governing AI in an organization: five levels on staying safe with AI tools and securing AI systems. The guides explain threats and defenses in simple words, with diagrams and checklists, and refer to the security and detection tools in our comparison and the models in our LLM database.","text":"From spotting AI scams to governing AI in an organization: five levels on staying safe with AI tools and securing AI systems. The guides explain threats and defenses in simple words, with diagrams and checklists, and refer to the security and detection tools in our comparison and the models in our LLM database.\n","words":53},"date":"2026-10-14","description":"Learn AI security in five levels: spot AI scams, protect your data, secure AI systems and govern AI in an organization.","json":"https://abxk.ai/en/ai-security/learn/index.json","kind":"section","language":"en","learning_path":{"category":"ai-security","levels":5},"modified":"2026-10-14","pages":[{"description":"AI security has three sides: scams that use AI, your data in AI tools and the security of AI systems. Real cases for each side and a map of this learning path.","json":"https://abxk.ai/en/ai-security/learn/what-ai-security-means/index.json","kind":"page","title":"What AI Security Means: Three Sides of One Topic","url":"https://abxk.ai/en/ai-security/learn/what-ai-security-means/"},{"description":"How criminals use cloned voices, AI-written messages and deepfakes, the warning signs that still work and three habits that protect you from AI scams.","json":"https://abxk.ai/en/ai-security/learn/ai-scams-and-how-to-spot-them/index.json","kind":"page","title":"AI Scams: Voice Clones, Fake Messages and Deepfakes","url":"https://abxk.ai/en/ai-security/learn/ai-scams-and-how-to-spot-them/"},{"description":"Where your prompts go, how long chats are stored, when people read them or models learn from them, and how business accounts differ from personal ones.","json":"https://abxk.ai/en/ai-security/learn/what-happens-to-your-data-in-ai-chats/index.json","kind":"page","title":"What Happens to Your Data in an AI Chat","url":"https://abxk.ai/en/ai-security/learn/what-happens-to-your-data-in-ai-chats/"},{"description":"Eight checks for safer everyday AI use: accounts and two-factor login, privacy settings, checking answers, extensions, shared links, kids and connected apps.","json":"https://abxk.ai/en/ai-security/learn/ai-safety-checklist-for-users/index.json","kind":"page","title":"A Safety Checklist for Everyday AI Users","url":"https://abxk.ai/en/ai-security/learn/ai-safety-checklist-for-users/"},{"description":"What detectors for AI text, images, audio and video can and cannot do, how watermarks and content credentials work, and how to use detectors fairly.","json":"https://abxk.ai/en/ai-security/learn/can-ai-generated-content-be-detected/index.json","kind":"page","title":"Can AI-Generated Content Be Detected?","url":"https://abxk.ai/en/ai-security/learn/can-ai-generated-content-be-detected/"},{"description":"How AI makes phishing emails, calls and video calls more convincing, which red flags still work, and the habits and processes that protect you and your company.","json":"https://abxk.ai/en/ai-security/learn/phishing-in-the-ai-era/index.json","kind":"page","title":"Phishing in the AI Era: Red Flags That Still Work","url":"https://abxk.ai/en/ai-security/learn/phishing-in-the-ai-era/"},{"description":"What prompt injection is, why AI models cannot reliably tell data from instructions, what attackers can achieve with it and the basic defenses for users and teams.","json":"https://abxk.ai/en/ai-security/learn/prompt-injection-explained/index.json","kind":"page","title":"Prompt Injection Explained Simply","url":"https://abxk.ai/en/ai-security/learn/prompt-injection-explained/"},{"description":"When made-up AI answers become security incidents: invented package names, unsafe fixes, fake legal facts, what benchmarks show and how to check before you act.","json":"https://abxk.ai/en/ai-security/learn/hallucinations-as-a-security-risk/index.json","kind":"page","title":"Hallucinations as a Security Risk","url":"https://abxk.ai/en/ai-security/learn/hallucinations-as-a-security-risk/"},{"description":"Six data classes that need care in AI tools, three safer ways to get the same help, a ten-second decision rule and what to do if you pasted something by mistake.","json":"https://abxk.ai/en/ai-security/learn/what-not-to-paste-into-ai/index.json","kind":"page","title":"What Not to Paste into an AI Tool","url":"https://abxk.ai/en/ai-security/learn/what-not-to-paste-into-ai/"},{"description":"A practical routine for suspicious photos, voice messages and videos: source, reverse search, origin data, visual and audio clues, context and expert help.","json":"https://abxk.ai/en/ai-security/learn/verify-images-audio-and-video/index.json","kind":"page","title":"Verify Images, Audio and Video Step by Step","url":"https://abxk.ai/en/ai-security/learn/verify-images-audio-and-video/"},{"description":"The ten biggest security risks of LLM apps in the OWASP 2026 list, each with an example and a first defense, and how to use the list in a design review.","json":"https://abxk.ai/en/ai-security/learn/owasp-top-10-for-llm-applications/index.json","kind":"page","title":"The OWASP Top 10 for LLM Applications","url":"https://abxk.ai/en/ai-security/learn/owasp-top-10-for-llm-applications/"},{"description":"How companies keep sensitive data out of the wrong AI tools: approved accounts, masking, DLP for prompts, browser controls, access rights, logs and contracts.","json":"https://abxk.ai/en/ai-security/learn/data-leakage-controls-for-ai-tools/index.json","kind":"page","title":"Data Leakage Controls for AI Tools","url":"https://abxk.ai/en/ai-security/learn/data-leakage-controls-for-ai-tools/"},{"description":"What jailbreaks are and why they work, which types of guardrails stop them, and how to combine and test guardrails in layers – without attack recipes.","json":"https://abxk.ai/en/ai-security/learn/jailbreaks-and-guardrails/index.json","kind":"page","title":"Jailbreaks and Guardrails in AI Applications","url":"https://abxk.ai/en/ai-security/learn/jailbreaks-and-guardrails/"},{"description":"How statistical tests, classifiers, watermarks and content credentials work, how to read accuracy claims, why base rates matter and how to use detectors fairly.","json":"https://abxk.ai/en/ai-security/learn/how-ai-detectors-work-and-fail/index.json","kind":"page","title":"How AI Detectors Work and Where They Fail","url":"https://abxk.ai/en/ai-security/learn/how-ai-detectors-work-and-fail/"},{"description":"Why employees use AI tools without approval, what can go wrong, how to find shadow AI and how to respond with good alternatives instead of punishment.","json":"https://abxk.ai/en/ai-security/learn/shadow-ai-in-companies/index.json","kind":"page","title":"Shadow AI: Unapproved AI Tools in Companies","url":"https://abxk.ai/en/ai-security/learn/shadow-ai-in-companies/"},{"description":"Map the assets, data flows and trust boundaries of an LLM app, apply STRIDE to AI, find its attack surfaces and decide which risks to fix first.","json":"https://abxk.ai/en/ai-security/learn/threat-modeling-for-ai-systems/index.json","kind":"page","title":"Threat Modeling for AI Systems","url":"https://abxk.ai/en/ai-security/learn/threat-modeling-for-ai-systems/"},{"description":"How to secure RAG and AI agents: document-level permissions, least privilege for tools, sandboxes, approval steps, output validation and audit logs.","json":"https://abxk.ai/en/ai-security/learn/secure-rag-and-ai-agents/index.json","kind":"page","title":"Secure RAG and AI Agents: Permissions, Tools, Sandboxes","url":"https://abxk.ai/en/ai-security/learn/secure-rag-and-ai-agents/"},{"description":"How AI red teams work: goals, scope and rules of engagement, test categories, manual and automated testing, reporting, fixing and re-testing.","json":"https://abxk.ai/en/ai-security/learn/red-teaming-llms/index.json","kind":"page","title":"Red Teaming LLMs: How Teams Test AI Safely","url":"https://abxk.ai/en/ai-security/learn/red-teaming-llms/"},{"description":"Downloaded models, poisoned data, malicious plugins and risky dependencies: how to vet the parts of your AI system with model cards, signatures and an AI-BOM.","json":"https://abxk.ai/en/ai-security/learn/ai-supply-chain-security/index.json","kind":"page","title":"AI Supply Chain Security: Models, Data, Plugins","url":"https://abxk.ai/en/ai-security/learn/ai-supply-chain-security/"},{"description":"What counts as an AI incident, which signals reveal one, what to log, and a playbook to contain, assess, notify, fix and learn, with clear roles.","json":"https://abxk.ai/en/ai-security/learn/ai-incident-response/index.json","kind":"page","title":"AI Incident Response: Logging, Monitoring, Playbooks","url":"https://abxk.ai/en/ai-security/learn/ai-incident-response/"},{"description":"What the NIST AI RMF, ISO/IEC 42001 and the EU AI Act each require, how their parts map onto each other and where a security team should start.","json":"https://abxk.ai/en/ai-security/learn/ai-governance-frameworks/index.json","kind":"page","title":"AI Governance Frameworks: NIST AI RMF, ISO/IEC 42001, EU AI Act","url":"https://abxk.ai/en/ai-security/learn/ai-governance-frameworks/"},{"description":"How attackers fool, poison and copy machine learning models, how the NIST taxonomy names each attack, and which defenses help — explained without attack code.","json":"https://abxk.ai/en/ai-security/learn/adversarial-machine-learning/index.json","kind":"page","title":"Adversarial Machine Learning: Evasion, Poisoning, Extraction","url":"https://abxk.ai/en/ai-security/learn/adversarial-machine-learning/"},{"description":"Epsilon and privacy budgets, federated learning, secure enclaves, homomorphic encryption and synthetic data: what each protects, what it costs and how to choose.","json":"https://abxk.ai/en/ai-security/learn/privacy-preserving-ai-techniques/index.json","kind":"page","title":"Privacy-Preserving AI: Differential Privacy, Federated Learning and More","url":"https://abxk.ai/en/ai-security/learn/privacy-preserving-ai-techniques/"},{"description":"How to evaluate AI for factuality, robustness, refusals, bias and calibration, what public benchmarks cannot show, and how to build and run your own eval suite.","json":"https://abxk.ai/en/ai-security/learn/evaluate-model-safety-and-reliability/index.json","kind":"page","title":"Evaluate Model Safety and Reliability","url":"https://abxk.ai/en/ai-security/learn/evaluate-model-safety-and-reliability/"},{"description":"The eight parts of an AI security program, from inventory and policy to monitoring and metrics, a simple maturity model and a plan for the first 90 days.","json":"https://abxk.ai/en/ai-security/learn/build-a-secure-ai-program/index.json","kind":"page","title":"Build a Secure AI Program in Your Organization","url":"https://abxk.ai/en/ai-security/learn/build-a-secure-ai-program/"}],"section":"ai-security","seo_title":"Learn AI Security: From Beginner to Expert","title":"Learn AI Security","translations":[{"json":"https://abxk.ai/de/ai-security/learn/index.json","language":"de","url":"https://abxk.ai/de/ai-security/learn/"}],"url":"https://abxk.ai/en/ai-security/learn/"}