The Threat Prompt Newsletter

The Threat Prompt Newsletter

Home
Archive
About

Sitemap - 2023 - The Threat Prompt Newsletter

TP#26 AI knows what you typed

TP#25 Reverse Engineering PII from Vectors

TP#24 Create Burp Web Security Checks in Seconds with AI (without extensions)

TP#23 Detect Phishing Sites Using ChatGPT

TP#22 Uncovering Model Weaknesses with Garak

TP#21 Prompt Injection Snake Oil

TP#20 Eight Automated AI Attack Frameworks

TP#19 Silently Prompting Your AI Assistant

TP#18 The AI Trust Paradox

TP#17 ChatGPT Plugins and Prompt Injections

TP#16 AI Security Techniques

TP#15 Explain Your Security Controls and Boost Secure Choices

TP#14 How To Avoid Leaking PII to ChatGPT

TP#13 AI Security is Probabilistic Security

TP#12 Lies from an Inscrutable Blackbox

TP#11 Apply AI to Solve Security Challenges at Scale

TP#10 BadDiffusion: Is that a backdoor in your diffusion model?

TP#9 Meta's LLaMA Escaped

TP#8 Use Public AI to Generate Unit Tests Without Revealing Proprietary Code

TP#7 Does AI need Hallucination Traps?

TP#6 Deep Fake Fools Lloyds Bank Voice Biometrics

TP#5 I Will Not Harm You Unless You Harm Me First

TP#4 Stalling an AI with Weird Prompts

TP#3 The CISO view on AI

TP#2 Outpainting: Place Anyone Anywhere

TP#1 Prepare Yourself: Five Traps Lurking in AI Tech

© 2025 Craig Balding
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture

Share

Copy link
Facebook
Email
Notes
More