RoME introduces robust low-rank experts for enhanced adversarial defense

Researchers have developed RoME (Robust Mixture of Low-Rank Experts), a novel approach to enhance adversarial robustness in machine learning models. RoME utilizes a mixture of experts (MoE) architecture where each expert is a low-rank update to a shared backbone, enabling better specialization in handling threat-specific features while efficiently capturing commonalities. The system also incorporates dual-scale gating and threat-guided diversification to ensure effective routing and expert utilization across different adversarial perturbations. Experiments show RoME surpasses current state-of-the-art methods in combined robustness and natural accuracy, even improving resilience against previously unseen threats. AI

IMPACT Enhances model resilience against adversarial attacks, potentially improving the safety and reliability of AI systems in real-world applications.

RANK_REASON The cluster contains a research paper detailing a new method for adversarial robustness in machine learning.

Read on arXiv cs.AI →

• alphaXiv
• arXiv
• CatalyzeX
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• Influence Flower
• Low-Rank Experts
• Mathematics Genealogy Project
• Mixture of Experts (MoE)
• RoME
• ScienceCast

• paper
• safety

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →