Secure By Dezign

By PaxTechnology Tech News

Secure By Dezign episodes

March 13 Multi-Turn Manipulation: The Slow Burn Attack That Bypasses Every Single-Turn Defense
How attackers weaponize conversational context to make LLMs forget their guardrails across multi-turn interactions — and how to build defenses that persist across the full conversation window.
11 min
March 12 Invisible Commands: Visual Prompt Injection Against Multimodal LLMs
When your image is the attack vector, every picture becomes a potential payload. Technical walkthrough of visual prompt injection against multimodal LLMs including GPT-4V and Gemini Vision.
11 min
March 12 Building Your Own Vulnerable AI Agent: A Complete LangChain + Ollama Attack Lab
Set up a local LLM agent with dangerous tools, then systematically exploit it with tool injection, privilege escalation, memory hijacking, and DoS. Full hands-on lab walkthrough.
11 min
March 12 RAG Poisoning: Weaponizing Vector Databases to Hijack LLM Outputs
Your trusted knowledge base is an injection surface — here's how attackers exploit it. Hands-on lab covering document poisoning, embedding manipulation, and retrieval hijacking.
10 min
March 12 Building Your AI Attack Lab: Local LLM Pentesting from Zero to Pwned
Your airgapped playground for prompt injection, jailbreaking, and system prompt extraction. No API keys, no rate limits, no excuses. Complete setup and attack walkthrough with Ollama.
11 min
March 12 Token Smuggling: When Your Tokenizer Becomes the Attack Vector
Exploiting the gap between human-readable text and machine tokenization to bypass every filter you've built. Covers homoglyph attacks, whitespace injection, and tokenizer-aware defenses.
11 min
March 11 Jailbreaking LLMs: The Art of Breaking AI Safety at Scale
Why your carefully aligned model is one clever prompt away from chaos. Covers DAN variants, many-shot jailbreaking, adversarial suffixes, and the cat-and-mouse dynamics of safety alignment.
11 min
March 10 Indirect Prompt Injection: Weaponizing the Web Against Your AI
When your LLM trusts external content, attackers don't need access to your users — they just need a webpage. Technical walkthrough of indirect prompt injection with real-world exploitation chains.
11 min
March 10 Budgeting for AI Security: Where CISOs Should Invest in 2026
A strategic allocation framework for securing AI systems while demonstrating ROI to the board — including tooling prioritization, build vs. buy decisions, and budget defense strategies.
14 min
March 09 Securing AI Training Data Pipelines: A Practitioner's Guide to Protecting Your Model's Foundation
Your model is only as trustworthy as the data that built it. A practitioner's guide to defending every stage of the ML data pipeline — from ingestion to labeling to preprocessing.
16 min

About Secure By Dezign

From the publisher's feed

Secure By Dezign is the AI Security Training Ground for security architects, CISOs, and pentesters who need to stay ahead of adversarial AI. Every episode delivers a deep-dive into a real AI attack…

Share Secure By Dezign

Sign up to save your podcasts

Secure By Dezign

Secure By Dezign episodes

About Secure By Dezign