Separations between Oblivious and Adaptive Adversaries for Natural
Dynamic Graph Problems
Aaron Bernstein, Nick Fischer et al.
Paper
Details
#GraphTheory #MachineLearning #AdversarialRobustness

Low-Rank Compression Improves Neural Network Adversarial Robustness

Researchers compress neural networks by over 94% of parameters while preserving adversarial accuracy, using dynamic low‑rank factors and a spectral regularizer. Read more: getnews.me/low-rank-compression-imp... #lowrank #adversarialrobustness

CIARD: Cyclic Iterative Method Boosts AI Model Robustness and Accuracy

CIARD, a cyclic iterative framework, boosts adversarial defense by 3.53 pp and clean‑sample accuracy by 5.87 pp on CIFAR‑10/100 and Tiny‑ImageNet. Read more: getnews.me/ciard-cyclic-iterative-m... #ciard #adversarialrobustness #machinelearning

a man in a suit and tie is sitting at a desk in front of a computer screen that says founder of the office . ALT: a man in a suit and tie is sitting at a desk in front of a computer screen that says founder of the office .

🚨 New paper alert: Our recent work on LLM safety has been accepted to ICLR 2025 🇸🇬

We propose a new framework for LLMs safety. 🧵

(1/7)

#LLM #AISafety #ICLR2025 #Certification #AdversarialRobustness #NLP #Shhhhhh #DomainCertification #AI