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 threats, model security, adversarial ML, AI vulnerability
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
293
posts in
6.5
ms
AI
Pentesting Roadmap: Labs, Challenges, Writeups & Research
💉
Prompt Injection
Content type:
Blog
osintteam.blog
·
4d
4 days ago
Actions for AI Pentesting Roadmap: Labs, Challenges, Writeups & Research
RoboHack
AI
CTF (Robotic Hacking Community at DEFCON 34)
💉
Prompt Injection
ctftime.org
·
5h
5 hours ago
Actions for RoboHack AI CTF (Robotic Hacking Community at DEFCON 34)
Defending
Jailbreak
Attacks
on Large Language
Models
via Manifold Trajectory Kinetics
💉
Prompt Injection
Content type:
Academic
arxiv.org
·
2d
2 days ago
Actions for Defending Jailbreak Attacks on Large Language Models via Manifold Trajectory Kinetics
Infosecurity Europe:
Prompt
Injection
Remains Unsolved, OWASP Researcher Warns
💉
Prompt Injection
Content type:
News
infosecurity-magazine.com
·
2d
2 days ago
Actions for Infosecurity Europe: Prompt Injection Remains Unsolved, OWASP Researcher Warns
Security
Flaw in Claude Code Illustrates the Risk of
AI
in Developer Workflows
💉
Prompt Injection
devops.com
·
5h
5 hours ago
Actions for Security Flaw in Claude Code Illustrates the Risk of AI in Developer Workflows
AI
Security
Newsletter - May 2026
💉
Prompt Injection
Content type:
Blog
medium.com
·
5d
5 days ago
Actions for AI Security Newsletter - May 2026
Claude Code
vulnerability
exposes developer credentials via
prompt
injection
💉
Prompt Injection
4sysops.com
·
2h
2 hours ago
Actions for Claude Code vulnerability exposes developer credentials via prompt injection
Meta’s
AI
Support Hack Is a Warning for Every Team Automating User Access
💉
Prompt Injection
Content type:
Discussion
langprotect.com
·
2d
2 days ago
·
DEV
Actions for Meta’s AI Support Hack Is a Warning for Every Team Automating User Access
What it looks like: Trusted, compliant
AI
systems at scale - Azure
AI
Tech Accelerator
💉
Prompt Injection
techcommunity.microsoft.com
·
7h
7 hours ago
Actions for What it looks like: Trusted, compliant AI systems at scale - Azure AI Tech Accelerator
Indirect
Prompt
Injection
remains a fundamental
security
challenge for AI
💉
Prompt Injection
Content type:
Blog
brave.com
·
2d
2 days ago
Actions for Indirect Prompt Injection remains a fundamental security challenge for AI
Why OpenAI is disabling ChatGPT web access to fight
prompt
injection
attacks
💉
Prompt Injection
Content type:
News
livemint.com
·
3d
3 days ago
Actions for Why OpenAI is disabling ChatGPT web access to fight prompt injection attacks
Mathematical proof reveals why fixed
AI
guardrails can never block every
jailbreak
💉
Prompt Injection
techxplore.com
·
4h
4 hours ago
Actions for Mathematical proof reveals why fixed AI guardrails can never block every jailbreak
ChatGPT can be hijacked without you knowing. Lockdown
Mode
is the fix
💉
Prompt Injection
Content type:
News
pcworld.com
·
1d
1 day ago
Actions for ChatGPT can be hijacked without you knowing. Lockdown Mode is the fix
How Fable 5 And Mythos 5 Change
AI
Security
,
Data
Retention, And Vendor Risk
🛡️
Cybersecurity
Content type:
Blog
forrester.com
·
2h
2 hours ago
Actions for How Fable 5 And Mythos 5 Change AI Security, Data Retention, And Vendor Risk
ChatGPT's new Lockdown
Mode
lets you disable web access and more to protect sensitive
data
from
prompt
injection
💉
Prompt Injection
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
How I Gave My
Security
Blog Its Own
AI
Agent and an Attitude
💉
Prompt Injection
Content type:
Blog
medium.com
·
1d
1 day ago
Actions for How I Gave My Security Blog Its Own AI Agent and an Attitude
Anthropic Releases Claude Fable 5, Its Most Powerful
AI
Yet, With Cyber Safeguards
🛡️
Cybersecurity
thehackernews.com
·
12h
12 hours ago
Actions for Anthropic Releases Claude Fable 5, Its Most Powerful AI Yet, With Cyber Safeguards
OpenAI unveils Lockdown
Mode
to protect sensitive
data
from
prompt
injection attacks
💉
Prompt Injection
techcrunch.com
·
3d
3 days ago
·
Hacker News
Actions for OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks
OpenAI rolls out Lockdown
Mode
to more ChatGPT users to fight
prompt
injection
attacks
💉
Prompt Injection
alternativeto.net
·
2d
2 days ago
Actions for OpenAI rolls out Lockdown Mode to more ChatGPT users to fight prompt injection attacks
How to Defend Against
Prompt
Injection
in Production
💉
Prompt Injection
Content type:
Reference
leanpub.com
·
1d
1 day ago
·
DEV
Actions for How to Defend Against Prompt Injection in Production
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