LLM Security

Feeds to Scour
SubscribedAll
Scoured 668 posts in 12.8 ms

fix(gateway): fail closed for unknown model auth · openclaw/openclaw@85343ea

 🔓Pentest  Content type: Code
github.com·

Compromise OpenClaw with Prompt Injections in Message Objects | Imperva

 🔓Pentest  Content type: Blog
imperva.com·

The Neutral Mask: How RLHF Provides Shallow Alignment while Leaving Partisan Structure Intact in a Large Language Model

 🤖AI  Content type: Academic
arxiv.org·

Claude Code vulnerability exposes developer credentials via prompt injection

 💥Binary Exploitation
4sysops.com·

Infosecurity Europe: Prompt Injection Remains Unsolved, OWASP Researcher Warns

 🔒CyberSecurity  Content type: News
infosecurity-magazine.com·

Indirect Prompt Injection remains a fundamental security challenge for AI

 🔒CyberSecurity  Content type: Blog
brave.com·

Inferoa AI harness claimed 90% cache savings. We ran it and measured 97.8%

 🤖AI
zozo123.github.io··Hacker News

Zero-Click IP Leak in a Privacy Search Engine: Indirect Prompt Injection & Silent Patching

 🔒CyberSecurity
infosecwriteups.com
·

Prompt injection still drives most agentic AI security failures in production

 🔒CyberSecurity
helpnetsecurity.com·

Sequent: scale and automation for higher confidence in alignment

 🤖AI
lesswrong.com·

local llm on laptop 780M GPU using llama + gemma 4 qat

 💥Binary Exploitation  Content type: Blog
alper.bearblog.dev·

MTP Isn't Always a Win: 1.95x on My 3090, but Speculative Decoding Is Hardware-Dependent

 💥Binary Exploitation  Content type: Blog
bric.pe.kr··DEV

Security Flaw in Claude Code Illustrates the Risk of AI in Developer Workflows

 💥Binary Exploitation
devops.com·

What are AI parameters — and why does everyone keep talking about billions of them?

 🤖AI  Content type: Blog
medium.com·

AI Can Write Code Fast, but Is It Secure? Building Code Security Skill

 🔒CyberSecurity  Content type: Blog
medium.com
·

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

 💥Binary Exploitation  Content type: News
livemint.com·

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

 🔒CyberSecurity  Content type: News
pcworld.com·

RoboHack AI CTF (Robotic Hacking Community at DEFCON 34)

 🚩CTF
ctftime.org·

How ChatGPT's new Lockdown mode protects you from data theft (and what else it does)

 🔒CyberSecurity  Content type: News
zdnet.com·

AI Pentesting Roadmap: Labs, Challenges, Writeups & Research

 🔒CyberSecurity  Content type: Blog
osintteam.blog
·

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