LLMSec newsletter
Subscribe
Sign in
Home
Archive
About
RPO: optimizing prompts for defense
Improving defenses against jailbreaks
Feb 2
•
Zander Mackie
2
Share this post
RPO: optimizing prompts for defense
www.llm-sec.com
Copy link
Facebook
Email
Note
Other
Adversarial AI - NIST AI 100-2 E2023
Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations. Summary of NIST AI 100-2 E2023
Feb 1
•
Zander Mackie
1
Share this post
Adversarial AI - NIST AI 100-2 E2023
www.llm-sec.com
Copy link
Facebook
Email
Note
Other
January 2024
Signed-Prompt
Robust defense against prompt injection. Signatures for prompts using rare character combos ➡️*️⃣⬇️↘️2️⃣
Jan 23
•
Zander Mackie
Share this post
Signed-Prompt
www.llm-sec.com
Copy link
Facebook
Email
Note
Other
Sleeper Agents
Deceptive AI systems. New Research from Anthropic.
Jan 22
•
Zander Mackie
Share this post
Sleeper Agents
www.llm-sec.com
Copy link
Facebook
Email
Note
Other
Introducing LLMsec
AI is here to stay. Lets help keep it secure.
Jan 22
•
Zander Mackie
1
Share this post
Introducing LLMsec
www.llm-sec.com
Copy link
Facebook
Email
Note
Other
Share
Copy link
Facebook
Email
Note
Other
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts