Archive - The Threat Prompt Newsletter

New

Top

Discussion

TP#20 Eight Automated AI Attack Frameworks

Plus: The AI Jedi Mind Trick

Jun 5 •

May 2023

TP#19 Silently Prompting Your AI Assistant

Plus: A PolyGlot in your AI pipeline?

May 28 •

TP#18 The AI Trust Paradox

Plus: High Impact Prompt Injection through ChatGPT Plugins

May 20 •

TP#17 ChatGPT Plugins and Prompt Injections

Plus: Unlimited OpenAI Credits

May 15 •

TP#16 AI Security Techniques

Plus: Tracking the Space

May 6 •

April 2023

TP#15 Explain Your Security Controls and Boost Secure Choices

Plus: Is That an AI Model Running In Your Browser?

Apr 29 •

TP#14 How To Avoid Leaking PII to ChatGPT

Plus: Trust in AI: Low vs. High Assurance

Apr 22 •

TP#13 AI Security is Probabilistic Security

Plus: ChatML, Guardrails and Auto-GPT

Apr 15 •

TP#12 Lies from an Inscrutable Blackbox

Plus: Reverse Engineering Neural Networks

Apr 8 •

TP#11 Apply AI to Solve Security Challenges at Scale

Plus: Navigating the Complexities of AI Safety

Apr 1 •

March 2023

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

Plus: Insurers Ask Cyber Insurance Applicants to Disclose ChatGPT Use

Mar 25 •

TP#9 Meta's LLaMA Escaped

Plus: GPT-4 Jailbreak and Indirect Prompt Injections

Mar 18 •

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts