AI Security

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

Feeds to Scour
SubscribedAll
Scoured 51 posts in 5.6 ms

New HSCC guidance confronts AI cyber risk, champions governance | TechTarget

 🚨Incident Response
techtarget.com
·

Why decades-old attacks still work, and why that should worry you

 🔒Security
techradar.com
·

Targeting World Models to Compromise Robot Learning Pipelines

 🎯Red Team  Content type: Academic
arxiv.org·

Subtle Injection for Ground-truth Inference of LLM Training Data

 🐛Fuzzing  Content type: Academic
arxiv.org·

Agentic AI opens the door to weaponizing financial systems

 🦠Malware Analysis
atlanticcouncil.org·

Where Rectified Flows Leak: Characterising Membership Signals Along the Interpolation Path

 FPGA Security  Content type: Academic
arxiv.org·

Safe-RULE: Safe Reinforcement UnLEarning

 🎯Red Team  Content type: Academic
arxiv.org·

A Controlled Audit of Pretraining Contamination in Public Medical Vision-Language Benchmarks

 🐛Fuzzing  Content type: Academic
arxiv.org·

Certified Robustness to Data Poisoning in Gradient-Based Training

 🔧Hardware Security  Content type: Academic
arxiv.org·

The Chronicles of Radio Frequency Fingerprinting

 🛰️Satellite Security  Content type: Academic
arxiv.org·

Adversarial Robustness of Activation Steering in Large Language Models

 🎯Red Team  Content type: Academic
arxiv.org·

Quantifying the Privacy of Counterfactuals by Leveraging Membership Inference Attacks Against Synthetic Data

 🔐Cryptography  Content type: Academic
arxiv.org·

Securing Self-supervised Data Curation for Foundation Models Robustness

 🦠Malware Analysis  Content type: Academic
arxiv.org·

An Embarrassingly Simple Detector for Model Extraction Attacks in Large Language Model API Traffic

 🦠Malware Analysis  Content type: Academic
arxiv.org·

Securing Code Understanding: Detecting Natural Backdoor Vulnerability in Code Language Models

 ⚙️LLVM Security  Content type: Academic
arxiv.org·

Robust Ensemble of Selectively Strengthened and Augmented Predictors

 🎯Red Team  Content type: Academic
arxiv.org·

Adversarial Attack and Disturbance Detection by Hadamard-Coded Output Representations for Object Detection and Semantic Segmentation

 🎯Red Team  Content type: Academic
arxiv.org·

Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

 🔢Homomorphic Crypto  Content type: Academic
arxiv.org·

Bayesian Membership Privacy for Graph Neural Networks

 🧮Quantum ML  Content type: Academic
arxiv.org·

SoK: Reconstruction Attacks on Synthetic Tabular Data (Insights from Winning the NIST CRC)

 🌌Post-Quantum 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