Cybersecurity, learned like a practitioner.
24 learning paths · 398 modules live · every lesson written by someone who has shipped the control or run the engagement. Free to start.
AI / LLM Security — Beginner to Expert · modules
22 modules, theory + hands-on. Prompt injection, data poisoning, agent threat models, building your own AI, optimisation, and reverse-engineering trending products like Cursor & Perplexity.
Prompt Injection Defense Architecture: Beyond Input Filtering
Why input filtering cannot be the primary control Prompt injection is not a fixed signature; it is any natural-language text that redirects a model’s behaviour. The input space is unbounded and the adversary is adaptive: paraphrase, translate into another language, encode in base64, split across turns, hide in a modality the classifier does not read, […]
Agentic AI Red Teaming: A Methodology for Testing Autonomous Agents
The agentic attack surface is bigger than the prompt A tool-using agent has five components an attacker can reach, and each is a distinct test target: the system prompt and policy, the tool set it can invoke, its memory (short-term context and any persistent store), the planning loop that decides the next action, and the […]
MCP Server Security Architecture: Threat Model and Hardening
The MCP trust model, and why it breaks MCP standardises how an LLM client discovers and invokes external tools — functions exposed by an MCP server that read files, query databases, call APIs, or execute code. The protocol is deliberately thin: it defines transport, tool discovery, and invocation, and leaves authentication, authorisation, and output handling […]
LLM Jailbreaks 2026 — Universal Suffixes, Many-Shot, Crescendo, and What Constitutional AI Actually Stops
LLM jailbreak research in 2026: GCG universal suffixes, AutoDAN, many-shot context-poisoning, Crescendo multi-turn, multimodal vision attacks. Why alignment is structurally defence-in-depth, the production controls that actually work, and a test harness for measuring your model versions.
Multi-Modal Attacks — Image Prompt Injection and Audio Adversarials
GPT-4V, Claude 3.5 Sonnet, and Gemini accept images. Whisper, ElevenLabs, and others accept audio. Each modality is an injection surface. This module covers documented multi-modal attacks (invisible-text prompt injection, audio-watermark adversarials, deepfake-driven phishing) an
Building Like Cursor / Perplexity / v0 — Backend Architecture of Trending AI Tools
Cursor, Perplexity, v0, Claude Artifacts, Lovable — the products defining 2026 AI UX. Their backends share patterns: streaming LLM gateways, smart context windows, agentic loops with tool use, observability-first design. This module reverse-engineers the architecture and shows ho
AI Supply Chain — Hugging Face Hijacks, Pickle Attacks, Model Card Poisoning
You download a model from Hugging Face. The model file format (Pickle) supports arbitrary code execution on load. The model card lies about training data. Adversaries upload typo-squat model names. This is the AI version of the npm supply chain problem and most teams have no cont
Browser-Use Agents — Risks When LLMs Browse the Web
Anthropic computer-use Claude, OpenAI Operator, and frameworks like browser-use let agents control real browsers. They click, type, fill forms, log in. Every webpage is now an attack surface against the agent. This module covers the documented attacks (visual prompt injection, de
Practitioners who've
shipped the controls.
Every module is written by someone who has built the defence or run the engagement. No repackaged tutorials, no generic theory.
Why learn here
Practitioner-written.
Each lesson is authored by someone who has shipped the control or run the engagement in production.
Quiz after every module.
20+ questions with explanations. 70%+ to mark complete. Unlimited retries.
Progress tracked.
Completions, scores and streaks saved automatically. Resume exactly where you left off.
India-priced.
Start free. ₹499/mo for intermediate. ₹4,999/yr for advanced. No hidden fees, ever.