Mirroring Security: Digital Twins Fortify IoT Networks
A new framework uses digital twin technology and game theory to enhance secure service selection in the complex landscape of space-air-ground integrated networks.
Science
Securing Medical AI: A New Approach to Collaborative Learning
![Clients employ a privacy-preserving federated learning approach by extracting $768$-dimensional $[CLS]$ tokens from a Vision Transformer, encrypting them with the CKKS scheme, and enabling the server to aggregate information across numerous clients while performing encrypted inference.](https://arxiv.org/html/2511.20983v1/x1.png)
A novel framework combines the power of vision transformers with lightweight encryption to enable privacy-preserving medical image analysis across distributed datasets.
The Evasion Game: Finding the Perfect Zigzag
New research proves an optimal strategy for dodging pursuers relies on sharp, on-off maneuvers, and presents a practical method for implementing it in real-time.
RDMA Gets a Memory Boost: Handling Faults on the Fly
A new approach efficiently manages memory page faults during Remote Direct Memory Access, eliminating the need for pre-pinned buffers and unlocking performance gains.
Bridging the Language Gap: Smarter SQL Queries in Arabic
Researchers have developed a new dataset and technique to significantly improve the accuracy of converting natural language questions into SQL queries for Arabic databases.
Taming Attention: Stabilizing Transformers for Faster Training
A new approach to controlling attention logit changes enables higher learning rates and improved performance in transformer models.
Reinforcement Learning’s Safety Net: Predicting the Unpredictable
A new approach safeguards Dyna-Q reinforcement learning agents against unexpected environmental shifts by proactively evaluating potential outcomes.
Ask Anything: Building Conversational AI with Knowledge Graphs
Researchers have developed a new system that combines the power of large language models with structured knowledge to deliver more accurate and adaptable conversational question answering.
When Agreement Fails: The Limits of Collective Behavior
New research reveals a critical threshold governing how groups of interacting agents transition from unified consensus to stable, yet fragmented, clusters.
SQL from Words: A New Approach to Database Queries
Researchers are exploring how to better translate natural language questions into accurate database queries, achieving improved performance with a novel reasoning framework.