LATIDIA · Ciberseguridad

Robustez rotada: una defensa sin entrenamiento contra ataques de inversión de bits en modelos de lenguaje grandes.

arXiv:2603.16382v2 Anuncio Tipo: reemplazar Resumen: La corrupción por inversión de bits de pesos cuantizados representa una seria amenaza para la confiabilidad de los modelos de lenguaje grandes (LLM), ya que incluso un pequeño número de fallas de peso puede desencadenar una catástrofe

La noticia

arXiv:2603.16382v2 Announce Type: replace Abstract: Bit-flip corruption of quantized weights poses a serious reliability threat to Large Language Models (LLMs), as even a small number of weight faults can trigger catastrophic model degradation. We show that such failures can be strongly amplified when corrupted weights are coupled to high-sensitivity activation channels. Based on this observation, we propose Rotated Robustness (RoR), a training-free sensitivity-aware hierarchical rotation that applies matched orthogonal transformations to activations and weights, redistributing sensitive channel contributions across feature dimensions while preserving the underlying linear mapping in exact arithmetic. Across eight evaluated LLMs, RoR matches or exceeds all compared methods in the number of cumulative PBS flips sustained before