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
294
posts in
11.6
ms
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
Your
AI
Agent Can Read. That’s the Whole Problem.
💉
Prompt Injection
Content type:
Blog
medium.com
·
5d
5 days ago
Actions for Your AI Agent Can Read. That’s the Whole Problem.
How ChatGPT's new Lockdown
mode
protects you from
data
theft (and what else it does)
💉
Prompt Injection
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)
Agentic
AI
security
: risks, guardrails, and what most teams get wrong
🤖
Agentic AI
Content type:
Blog
udacity.com
·
5d
5 days ago
Actions for Agentic AI security: risks, guardrails, and what most teams get wrong
Survey reveals 80% would
jailbreak
their Kindle before letting Amazon win
💉
Prompt Injection
androidauthority.com
·
2d
2 days ago
Actions for Survey reveals 80% would jailbreak their Kindle before letting Amazon win
Assessing Automated
Prompt
Injection
Attacks
in Agentic Environments
💉
Prompt Injection
Content type:
Academic
arxiv.org
·
15h
15 hours ago
Actions for Assessing Automated Prompt Injection Attacks in Agentic Environments
Prompt
Injection
in RAG Agentic Systems
💉
Prompt Injection
ulad.net
·
2d
2 days ago
·
Hacker News
Actions for Prompt Injection in RAG Agentic Systems
Hackers could use
poisoned
WhatsApp and Slack notifications to take over your Google Gemini – and make it work on their behalf
💉
Prompt Injection
techradar.com
·
6d
6 days ago
Actions for Hackers could use poisoned WhatsApp and Slack notifications to take over your Google Gemini – and make it work on their behalf
Inside ChatGPT’s New Lockdown
Mode
: Is Your
Data
Safer?
💉
Prompt Injection
telecomtalk.info
·
2d
2 days ago
Actions for Inside ChatGPT’s New Lockdown Mode: Is Your Data Safer?
Anthropic Says Its Latest
Model
Is 'Mythos-Level,' but With Strict Safeguards
💉
Prompt Injection
lifehacker.com
·
23h
23 hours ago
Actions for Anthropic Says Its Latest Model Is 'Mythos-Level,' but With Strict Safeguards
Microsoft releases incident response playbook for Copilot and Azure
AI
💉
Prompt Injection
4sysops.com
·
21h
21 hours ago
Actions for Microsoft releases incident response playbook for Copilot and Azure AI
Beyond
AI
Firewalls: The Rise of Runtime Governance
🤖
Agentic AI
Content type:
Blog
medium.com
·
5d
5 days ago
Actions for Beyond AI Firewalls: The Rise of Runtime Governance
OpenAI Rolling Out ChatGPT Account
Security
Controls
💉
Prompt Injection
securityweek.com
·
2d
2 days ago
Actions for OpenAI Rolling Out ChatGPT Account Security Controls
New ChatGPT Lockdown
Mode
Limits Tools That Could Enable
Data
Exfiltration
💉
Prompt Injection
thehackernews.com
·
4d
4 days ago
Actions for New ChatGPT Lockdown Mode Limits Tools That Could Enable Data Exfiltration
‘Only engineers keen on solving code': Inside the secretive operation ran by US Army to hack into its own systems – and keep the salespersons outside the buildi...
💉
Prompt Injection
Content type:
News
techradar.com
·
2d
2 days ago
Actions for ‘Only engineers keen on solving code': Inside the secretive operation ran by US Army to hack into its own systems – and keep the salespersons outside the buildi...
Every set of
AI
guardrails can be broken by the right
prompt
🛡️
Cybersecurity
helpnetsecurity.com
·
10h
10 hours ago
Actions for Every set of AI guardrails can be broken by the right prompt
Zero-Click IP
Leak
in a Privacy Search Engine: Indirect
Prompt
Injection
& Silent Patching
💉
Prompt Injection
infosecwriteups.com
·
1d
1 day ago
Actions for Zero-Click IP Leak in a Privacy Search Engine: Indirect Prompt Injection & Silent Patching
OpenAI Help: Lockdown
Mode
💉
Prompt Injection
simonwillison.net
·
4d
4 days ago
Actions for OpenAI Help: Lockdown Mode
The best new ChatGPT feature is one most people will never use
💉
Prompt Injection
digitaltrends.com
·
3d
3 days ago
Actions for The best new ChatGPT feature is one most people will never use
Apple's
AI
Can Now Change Your Passwords. What Could Possibly Go Wrong?
🤖
Agentic AI
Content type:
Blog
kylereddoch.me
·
1d
1 day ago
·
Hacker News
Actions for Apple's AI Can Now Change Your Passwords. What Could Possibly Go Wrong?
« 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