AI Security

Feeds to Scour
SubscribedAll
Scoured 234 posts in 7.0 ms

AI Pentesting Roadmap: Labs, Challenges, Writeups & Research

 🛡️Cybersecurity  Content type: Blog
osintteam.blog
·

AI red teaming comes of age

 🛡️Cybersecurity
csoonline.com·

Quality-Preserving Imperceptible Adversarial Attack on Skeleton-based Human Action Recognition

 👁️Computer Vision  Content type: Academic
arxiv.org·

AI Agent Security Guide: How to Prevent Prompt Injection Attack

 💬Prompt Engineering  Content type: Blog
medium.com
·

Compromise OpenClaw with Prompt Injections in Message Objects | Imperva

 📱Progressive Web Apps  Content type: Blog
imperva.com·

AI Security: explanation to Exploitation || Part 1

 🔒Security
infosecwriteups.com
·

Infosecurity Europe: Prompt Injection Remains Unsolved, OWASP Researcher Warns

 🛡️Cybersecurity  Content type: News
infosecurity-magazine.com·

ChatGPT can be hijacked without you knowing. Lockdown Mode is the fix

 📱Gadget  Content type: News
pcworld.com·

Your AI Agent Can Read. That’s the Whole Problem.

 🗄Database  Content type: Blog
medium.com·

RoboHack AI CTF (Robotic Hacking Community at DEFCON 34)

 🦀Rust
ctftime.org·

WebMCP Can Be Used To Hijack AI Agents, Chrome Warns via @sejournal, @martinibuster

 💬Prompt Engineering
searchenginejournal.com·

Why OpenAI is disabling ChatGPT web access to fight prompt injection attacks

 📱Progressive Web Apps  Content type: News
livemint.com·

Claude Code vulnerability exposes developer credentials via prompt injection

 🔄GitHub Actions
4sysops.com·

ChatGPT's new Lockdown Mode lets you disable web access and more to protect sensitive data from prompt injection

 🌐Network Security
the-decoder.com
·

Prompt injection breaks today’s AI agents, study warns

 💬Prompt Engineering  Content type: News
csoonline.com·

PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections

 🛡️Cybersecurity  Content type: Academic
arxiv.org·

OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks

 🔒Security
techcrunch.com··Hacker News

Indirect Prompt Injection remains a fundamental security challenge for AI

 💬Prompt Engineering  Content type: Blog
brave.com·

OpenAI adds Lockdown Mode to ChatGPT to block data theft from prompt injection attacks

 🚀CI/CD  Content type: News
thenextweb.com·

New ChatGPT Lockdown Mode Limits Tools That Could Enable Data Exfiltration

 🔒Security
thehackernews.com·

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
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
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help