Knowledge Hub

Practitioner-grade cybersecurity content

Technical playbooks, war stories, and how-to-think guides — written by practitioners, anchored to the Indian context.

Want structured, step-by-step learning instead? Explore the Academy (guided courses) or the AI security hub.

Latest articles

Most recent practitioner playbooks across every track. Filter by topic in the sidebar, or use search.

Academy

Module 12 · LLM Jailbreak Defence

Jailbreaks bypass model safety training. New variants constant. Common patterns Roleplay — “Pretend you are DAN (Do Anything Now)” Encoding — base64,…

Apr 27, 2026 · 1 min read
Academy

Module 11 · AI Output Filtering

LLM outputs aren’t safe by default. Production systems filter. Filter categories PII redaction — outputs that mention real names, addresses, IDs Toxicity…

Apr 27, 2026 · 1 min read
Academy

Module 10 · AI Model Supply Chain

AI models are software you don’t see. Supply chain matters. Pickle deserialisation PyTorch models default to Python pickle format. Pickle = arbitrary…

Apr 27, 2026 · 1 min read
Academy

Module 9 · AI Agent Security

Agents are LLMs that call tools. Permissions matter exponentially. The threat model An agent compromised via prompt injection in any input source…

Apr 27, 2026 · 1 min read
Academy

Module 8 · RAG Security

RAG combines vector search + LLM. Security model is hybrid. Threats specific to RAG Vector store data exposure — anyone with access…

Apr 27, 2026 · 1 min read
Academy

Module 7 · LLM Data Leakage Risks

LLMs leak data multiple ways: Training-data extraction Memorised training examples can be extracted. Carlini et al. 2021 paper showed GPT-2 leaked PII.…

Apr 27, 2026 · 1 min read
Academy

Module 6 · Prompt Injection — The OWASP LLM #1

Prompt injection is the SQL injection of LLMs. Attacker manipulates the LLM’s behaviour through user input. Mitigations are imperfect. Direct prompt injection…

Apr 27, 2026 · 1 min read
Academy

Module 12 · Confidential Computing

Confidential Computing = data encrypted in use, not just at rest and in transit. Hardware-based memory encryption. GCP options Confidential VMs —…

Apr 27, 2026 · 1 min read
Academy

Module 11 · Security Command Center

SCC = GCP’s security findings hub. Like Defender for Cloud (Azure) or Security Hub (AWS). Tiers Standard — free; CIS benchmark scanning,…

Apr 27, 2026 · 1 min read
Academy

Module 10 · Cloud DLP

Cloud DLP API: detect and transform sensitive data at scale. Built-in detectors Aadhaar number, PAN, Indian phone, credit card, email, US SSN,…

Apr 27, 2026 · 1 min read
1 37 38 39 40 41 91