LATIDIA · Ciberseguridad

Sobre la privacidad de los LLM: un estudio de ablación

arXiv: 2605.02255v2Tipo de anuncio: reemplazar Resumen: Los modelos de lenguaje grandes (LLM) enfrentan diversas amenazas a la privacidad, sin embargo, los estudios existentes generalmente evalúan los ataques individuales de forma aislada, ofreciendo una orientación limitada sobre qué

La noticia

arXiv:2605.02255v2 Announce Type: replace Abstract: Large language models (LLMs) face diverse privacy threats, yet existing studies typically evaluate individual attacks in isolation, offering limited guidance on which system factors drive privacy vulnerabilities. This paper presents a unified threat model and a systematic ablation study of four representative attacks: Membership Inference (MIA), Attribute Inference (AIA), Data Extraction (DEA), and Backdoor Attacks (BA). Our findings reveal attack-specific sensitivities: membership inference depends strongly on dataset characteristics and attack strategy, attribute inference is influenced by model and training characteristics, data extraction increases with model scale and training-data repetition, and backdoor attacks achieve consistently high success rates. Based on these findings, we derive practical recommendations