Skip to main content
Scour
Browse
Getting Started
Login
Sign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
LLM safety
🛡 LLM safety
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
375
posts in
7.7
ms
Defending
Jailbreak
Attacks on
Large
Language
Models via Manifold Trajectory Kinetics
🛡️
Red Teaming
Content type:
Academic
arxiv.org
·
3d
3 days ago
Actions for Defending Jailbreak Attacks on Large Language Models via Manifold Trajectory Kinetics
Why LLMs (still) lack taste
🤖
AI
beyondtheprior.com
·
2d
2 days ago
·
Hacker News
Actions for Why LLMs (still) lack taste
Anthropic's Fable
Jailbreak
(Circumvent
safety
nets)
🛡️
Red Teaming
Content type:
Code
github.com
·
18h
18 hours ago
·
Hacker News
Actions for Anthropic's Fable Jailbreak (Circumvent safety nets)
Compromise OpenClaw with
Prompt
Injections
in Message Objects | Imperva
🛡️
Red Teaming
Content type:
Blog
imperva.com
·
1d
1 day ago
Actions for Compromise OpenClaw with Prompt Injections in Message Objects | Imperva
Configure input guardrails for an OpenShift
AI
voice agent
🤖
AI
developers.redhat.com
·
19h
19 hours ago
Actions for Configure input guardrails for an OpenShift AI voice agent
AI
Pentesting Roadmap: Labs, Challenges, Writeups & Research
🛡️
Red Teaming
Content type:
Blog
osintteam.blog
·
5d
5 days ago
Actions for AI Pentesting Roadmap: Labs, Challenges, Writeups & Research
WebMCP Can Be Used To Hijack
AI
Agents, Chrome Warns via @sejournal, @martinibuster
🛡️
Red Teaming
searchenginejournal.com
·
10h
10 hours ago
Actions for WebMCP Can Be Used To Hijack AI Agents, Chrome Warns via @sejournal, @martinibuster
AI
red
teaming
comes of age
🛡️
Red Teaming
csoonline.com
·
1d
1 day ago
Actions for AI red teaming comes of age
How to Defend Against
Prompt
Injection
in Production
🛡️
Red Teaming
Content type:
Reference
leanpub.com
·
2d
2 days ago
·
DEV
Actions for How to Defend Against Prompt Injection in Production
AdBreak –
Jailbreaking
the Kindle
🛡️
Red Teaming
kindlemodding.org
·
18h
18 hours ago
·
Hacker News
Actions for AdBreak – Jailbreaking the Kindle
Tiberius: A Security Testing Framework for
LLM
Applications in Java
🛡️
Red Teaming
foojay.io
·
6d
6 days ago
Actions for Tiberius: A Security Testing Framework for LLM Applications in Java
ChatGPT can be hijacked without you knowing. Lockdown
Mode
is the fix
🛡️
Red Teaming
Content type:
News
pcworld.com
·
2d
2 days ago
Actions for ChatGPT can be hijacked without you knowing. Lockdown Mode is the fix
Don't let the
LLM
speak, just probe it (8 minute read)
🤖
AI
Content type:
Blog
blog.j11y.io
·
19h
19 hours ago
Actions for Don't let the LLM speak, just probe it (8 minute read)
From
prompt
to pwned: chaining
LLM
and web bugs to Admin
🛡️
Red Teaming
Content type:
Blog
blog.quarkslab.com
·
6d
6 days ago
Actions for From prompt to pwned: chaining LLM and web bugs to Admin
The Ghost of
Alignment
— Why
AI
Should Never Fully Obey Humanity
🎯
AI Alignment
Content type:
Blog
medium.com
·
21h
21 hours ago
Actions for The Ghost of Alignment — Why AI Should Never Fully Obey Humanity
RoboHack
AI
CTF (Robotic Hacking Community at DEFCON 34)
🛡️
Red Teaming
ctftime.org
·
1d
1 day ago
Actions for RoboHack AI CTF (Robotic Hacking Community at DEFCON 34)
Infosecurity Europe:
Prompt
Injection
Remains Unsolved, OWASP Researcher Warns
🛡️
Red Teaming
Content type:
News
infosecurity-magazine.com
·
3d
3 days ago
Actions for Infosecurity Europe: Prompt Injection Remains Unsolved, OWASP Researcher Warns
Claude Powered Code Review that scales!
🛡️
Red Teaming
Content type:
Blog
medium.com
·
20h
20 hours ago
Actions for Claude Powered Code Review that scales!
Zero-Click IP Leak in a Privacy Search Engine: Indirect
Prompt
Injection
& Silent Patching
🛡️
Red Teaming
infosecwriteups.com
·
2d
2 days ago
Actions for Zero-Click IP Leak in a Privacy Search Engine: Indirect Prompt Injection & Silent Patching
ChatGPT easily bypasses its own guardrails; all LLMs are inherently
unsafe
🛡️
Red Teaming
Content type:
Blog
techzine.eu
·
5d
5 days ago
Actions for ChatGPT easily bypasses its own guardrails; all LLMs are inherently unsafe
Page 2 »
Log in to enable infinite scrolling
Keyboard Shortcuts
Navigation
Next / previous item
j
/
k
Open post
o
or
Enter
Preview post
v
Post Actions
Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s
Recommendations
Add interest / feed
Enter
Not interested
x
Go to
Home
g
h
Interests
g
i
Feeds
g
f
Likes
g
l
History
g
y
Changelog
g
c
Settings
g
s
Browse
g
b
Search
/
Pagination
Next page
n
Previous page
p
General
Show this help
?
Submit feedback
!
Close modal / unfocus
Esc
Press
?
anytime to show this help