AI Security

🧠 AI Security

Model Poisoning, Adversarial Attacks, ML Pipeline Security, Federated Learning Threats

Feeds to Scour
SubscribedAll
Scoured 51 posts in 7.7 ms

Sequential Data Poisoning in LLM Post-Training

 ⚙️LLVM Security  Content type: Academic
arxiv.org·

AI Security Best Practices for Regulated Industries

 🎯Red Team
orca.security·

RoboHack AI CTF (Robotic Hacking Community at DEFCON 34)

 🎯Red Team
ctftime.org·

AI Will Not Start a Nuclear War, but Humans Might: Conclusions and Policy Recommendations The notion that AI could start a nuclear war may be attention-grabbing...

 🎯Red Team
ai-frontiers.org
·

Algebraic Cryptanalytic Extraction on Hard-Label Neural Networks

 🔐Cryptography
eprint.iacr.org·

How to reduce capability degradation from off-model SFT

 🐛Fuzzing
lesswrong.com·

Pythia 1.4B reproduces 3.6% of training samples verbatim given 950-token prompts

 🐛Fuzzing  Content type: Blog
ret2libc.com··Hacker News

Mathematical proof reveals why fixed AI guardrails can never block every jailbreak

 🔒Security
techxplore.com·

Meta’s AI Support Hack Is a Warning for Every Team Automating User Access

 💻Hacking  Content type: Discussion
langprotect.com··DEV

Article Series: Securing the AI Stack: From Model to Production

 🔧Hardware Security  Content type: News
infoq.com·

ChatGPT is recommending scam websites that will steal your credit card info

 🌐Network Protocols
digitaltrends.com·

Auditing Training Data in Domain-adapted LLMs: LoRA-MINT

 ✅Formal Verification  Content type: Academic
arxiv.org·

Machine Unlearning: Can Artificial Intelligence Really Forget?

 🐛Fuzzing  Content type: Blog
medium.com·

The Rise of Agentic AI Threats: How Attackers Are Weaponizing AI Agents Against Your Business

 🚨Incident Response  Content type: Blog
medium.com·

Claude Fable 5 is here — and it's based on a model Anthropic once deemed too risky for the public

 🎯Red Team  Content type: News
tomsguide.com
·

Advancing the State-of-the-Art in Empirical Privacy Auditing

 🦠Malware Analysis  Content type: Academic
arxiv.org·

TryHackMe LockdownAI — Auditing a RAG Assistant for Three Hidden Vulnerabilities

 🚨Incident Response  Content type: Blog
medium.com·

Beyond the OWASP Top 10: Securing GenAI Apps with Google Cloud Model Armor

 💻Hacking  Content type: Blog
medium.com
·

AI Pentesting Roadmap: Labs, Challenges, Writeups & Research

 💻Hacking  Content type: Blog
osintteam.blog
·

On Choosing the $\mu$ Parameter in Gaussian Differential Privacy

 🔢Homomorphic Crypto  Content type: Academic
arxiv.org·

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