corpus.blog
41,554 blogs · 5,197,919 posts Claim your blog
Record · corpus.blog/posts/01a08c58-7231-711c-a29f-591f53fab94d

Output-Invariant and Time-Based Testing – Practical Techniques for Black-Box Enumeration of LLMs

TrebledJ's Pages - TrebledJ's personal blog on programming, cybersecurity, music, and memes. · published 9 May 2025

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at trebledj.me Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
External links
13
Words captured
4,260

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://portswigger.net/research/backslash-powered-scanning-hunting-unknown-vulnerability-classes
portswigger.net
https://github.com/tldrsec/prompt-injection-defenses
github.com
https://protectai.github.io/llm-guard/output_scanners/sensitive/
protectai.github.io
https://github.com/TrebledJ/trebledj.github.io/blob/65a82f27a84464a6b4e6f1782beb939480a1aced/scripts/prompt-injection-time-metrix/timebased.csv
github.com
https://computers-are-fast.github.io/
computers-are-fast.github.io
https://github.com/TrebledJ/trebledj.github.io/blob/master/scripts/prompt-injection-time-metrix/dumbregex.py
github.com
https://genai.owasp.org/llm-top-10/
genai.owasp.org
https://www.pillar.security/blog/new-vulnerability-in-github-copilot-and-cursor-how-hackers-can-weaponize-code-agents
pillar.security
https://protectai.github.io/llm-guard/input_scanners/anonymize/
protectai.github.io
https://arxiv.org/html/2412.15431v1
arxiv.org
https://en.wikipedia.org/wiki/Twenty_questions
en.wikipedia.org
https://medium.com/@fondu.ai/testing-the-limits-of-prompt-injection-defence-93e5d83a9053
medium.com
https://github.com/protectai/ai-exploits
github.com
Elsewhere on trebledj.me (4)