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
AI Security
🛡️ AI Security
AI safety, LLM security, prompt injection, adversarial AI
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
498
posts in
8.5
ms
From
prompt
to pwned: chaining
LLM
and web bugs to Admin
🔍
Microsoft Sentinel
Content type:
Blog
blog.quarkslab.com
·
5d
5 days ago
Actions for From prompt to pwned: chaining LLM and web bugs to Admin
Inside ChatGPT’s New Lockdown
Mode
: Is Your Data
Safer
?
🔒
Cloud Security
telecomtalk.info
·
2d
2 days ago
Actions for Inside ChatGPT’s New Lockdown Mode: Is Your Data Safer?
Mathematical proof reveals why fixed
AI
guardrails can never block every
jailbreak
🧠
AI
techxplore.com
·
2h
2 hours ago
Actions for Mathematical proof reveals why fixed AI guardrails can never block every jailbreak
Why OpenAI is disabling ChatGPT web access to fight
prompt
injection
attacks
🔍
Microsoft Sentinel
Content type:
News
livemint.com
·
3d
3 days ago
Actions for Why OpenAI is disabling ChatGPT web access to fight prompt injection attacks
How ChatGPT's new Lockdown
mode
protects you from data theft (and what else it does)
🔍
Microsoft Sentinel
Content type:
News
zdnet.com
·
2d
2 days ago
Actions for How ChatGPT's new Lockdown mode protects you from data theft (and what else it does)
ML4Good Summer 2026 Bootcamps - Applications Open!
🧠
AI
lesswrong.com
·
7h
7 hours ago
Actions for ML4Good Summer 2026 Bootcamps - Applications Open!
ChatGPT's new Lockdown
Mode
lets you disable web access and more to protect sensitive data from
prompt
injection
🔒
Cloud Security
the-decoder.com
·
3d
3 days ago
Actions for ChatGPT's new Lockdown Mode lets you disable web access and more to protect sensitive data from prompt injection
Assessing the Polyglot Chatbot: Multilingual
Safety
in
AI
Systems
🤖
Copilot
cdt.org
·
22h
22 hours ago
Actions for Assessing the Polyglot Chatbot: Multilingual Safety in AI Systems
OpenAI rolls out Lockdown
Mode
to more ChatGPT users to fight
prompt
injection
attacks
🔍
Microsoft Sentinel
alternativeto.net
·
2d
2 days ago
Actions for OpenAI rolls out Lockdown Mode to more ChatGPT users to fight prompt injection attacks
Toward
Secure
LLM
Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
🧠
AI
Content type:
Academic
arxiv.org
·
14h
14 hours ago
Actions for Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
Tiberius: A
Security
Testing Framework for
LLM
Applications in Java
⚙️
DevOps
foojay.io
·
5d
5 days ago
Actions for Tiberius: A Security Testing Framework for LLM Applications in Java
How I Gave My
Security
Blog Its Own
AI
Agent and an Attitude
🤖
Copilot
Content type:
Blog
medium.com
·
1d
1 day ago
Actions for How I Gave My Security Blog Its Own AI Agent and an Attitude
Microsoft releases incident response playbook for Copilot and Azure
AI
🤖
Copilot
4sysops.com
·
20h
20 hours ago
Actions for Microsoft releases incident response playbook for Copilot and Azure AI
[Recorded talk] "
AI
Alignment
Versus
AI
Ethical Treatment: 10 Challenges"
🤝
AI Ops
Content type:
Blog
meditationsondigitalminds.substack.com
·
1d
1 day ago
·
Substack
Actions for [Recorded talk] "AI Alignment Versus AI Ethical Treatment: 10 Challenges"
OpenAI unveils Lockdown
Mode
to protect sensitive data from
prompt
injection
attacks
🔍
Microsoft Sentinel
techcrunch.com
·
3d
3 days ago
·
Hacker News
Actions for OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks
What it looks like: Trusted, compliant
AI
systems at scale - Azure
AI
Tech Accelerator
☁️
Microsoft Azure
techcommunity.microsoft.com
·
5h
5 hours ago
Actions for What it looks like: Trusted, compliant AI systems at scale - Azure AI Tech Accelerator
The
AI
automation tool nobody talks about just replaced my entire workflow setup
🖥️
Homelab
xda-developers.com
·
1d
1 day ago
Actions for The AI automation tool nobody talks about just replaced my entire workflow setup
AI
giant says its own
models
could soon improve themselves — and now it wants a global pause
🧠
AI
thecooldown.com
·
5h
5 hours ago
Actions for AI giant says its own models could soon improve themselves — and now it wants a global pause
Beyond the OWASP Top 10:
Securing
GenAI Apps with Google Cloud
Model
Armor
🧠
AI
Content type:
Blog
medium.com
·
6d
6 days ago
Actions for Beyond the OWASP Top 10: Securing GenAI Apps with Google Cloud Model Armor
OpenAI Unveils ChatGPT Account
Security
Controls
🔒
Cloud Security
Content type:
News
infosecurity-magazine.com
·
2d
2 days ago
Actions for OpenAI Unveils ChatGPT Account Security Controls
« Page 1
·
Page 3 »
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