Why Al Models Forget & How MIT Fixed It With Knowledge Retention

MIT introduces Self-Distillation Fine-Tuning to reduce catastrophic forgetting; it uses student-teacher demonstrations and needs 2.5x compute.

LLMs can unmask pseudonymous users at scale with surprising accuracy

If LLMs’ success in deanonymizing people improves, the researchers warn, governments could use the techniques to unmask online critics, corporations could assemble customer profiles for ...
IEEE

Graph Neural Network-Based Entity Extraction and Relationship Reasoning in Complex Knowledge Graphs

Abstract: This study proposed a knowledge graph entity extraction and relationship reasoning algorithm based on a graph neural network, using a graph convolutional network and graph attention network ...
IEEE

A Hybrid Graph Neural Network Model for Predicting Cyber Attacks From Heterogeneous and Dynamic Network Data

Abstract: With valuable data constantly under attack, reactive security measures are no longer sufficient. Predicting cyber threats before they emerge is crucial. Cyberattacks do not occur randomly; ...