#neural-network-safety News & Analysis

2 articles tagged with #neural-network-safety. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

2 articles

AIBullisharXiv – CS AI · Jun 197/10

🧠

Formal Verification of Learned Multi-Agent Communication Policies via Decision Tree Distillation

Researchers present the first formal verification framework for multi-agent reinforcement learning (MARL) communication policies by distilling neural networks into interpretable decision trees and verifying them with probabilistic model checking. The approach achieves 97.9% fidelity to original policies while enabling safety verification for critical robotic applications like drone swarms and autonomous vehicle fleets.

AINeutralarXiv – CS AI · Jun 26/10

🧠

CEAR: Certified Ensemble Adversarial Robustness in DNNs

Researchers propose CEAR, an ensemble-based defense mechanism combining empirical and certified robustness techniques to protect deep neural networks against adversarial attacks. The method uses varying Gaussian noise, temperature adjustments, and novel voting mechanisms while extending randomized smoothing to ensemble classifiers, demonstrating improved certified accuracy across benchmark datasets.