llm security
AI security interview questions tagged llm security, across every topic.
5 questions · 2 unlocked for you
Concepts behind "llm security"
Explanations of the mechanisms these questions rely on.
Foundational
The OWASP Top 10 for LLM ApplicationsThe OWASP Top 10 for LLM Applications (2026 edition, published in August 2026 by the OWASP GenAI Security Project) lists the most important risks in applications built on language models: prompt injection, sensitive information disclosure, excessive agency, supply chain, data and model poisoning, unbounded consumption, misinformation, hidden context exposure, vector and embedding weaknesses and improper output handling. The 2025 edition used the same risks with different numbers and called hidden context exposure system prompt leakage, so IDs need their year. This lesson explains each by mechanism, example and primary control, and how the items connect. How LLM Systems Work
Foundational
Training-Data Memorisation and ExtractionLanguage models memorise part of their training data verbatim, and an attacker can sometimes make them emit it: personal data, secrets, copyrighted text. Memorisation grows with duplication, model size and prompt context, happens before overfitting, and survives alignment, which only hides it. Defences stack: deduplicate, scrub, train with differential privacy where it fits, filter outputs knowing approximate copies slip through, and measure with canaries and extraction tests. Fine-tuning on customer data is the highest-risk case. Adversarial ML & Privacy
Core
Guardrails and Their LimitsGuardrails are controls placed around a model to check or constrain its inputs and outputs: schema validators, allowlists, PII detectors, topic and safety classifiers, injection detectors and LLM-based judges. Correctly implemented deterministic controls enforce their specified rules independently of model intent; probabilistic controls aim to lower the rate of bad outcomes and need honest measurement of both misses and false positives. A good architecture uses each where it fits and never presents a classifier as a boundary. LLM Application SecuritySign in
Advanced
Threat Modeling AI SystemsThreat modeling an LLM application uses the same data-flow diagram and STRIDE walk as any system, with new elements drawn in: the context assembler, retrieval stores, the tool layer, memory, and the model and its supply chain. Two adjustments make it work. Annotate every input to the context with its author, because any author can steer the model. And classify every control as deterministic or probabilistic, because only deterministic controls can carry a boundary. Security Foundations🔒 Premium
Advanced
AI Gateways and Model Routing as a Security Control PointModel gateways can enforce provider policy, control request resources and record effective dispatches. Their assurance depends on path coverage, trustworthy request facts and controls that survive retries, queued work and concurrent admission. Work through a fictional route matrix and distinguish enforceable limits from delayed accounting. How LLM Systems Work🔒 Premium