LATIDIA · Ciberseguridad

(A)iSpy: Troyanos parásitos para la infraestructura de aprendizaje automático

arXiv: 2607.17550v2Announce Type: replace Resumen: Las canalizaciones modernas de aprendizaje automático (ML) dependen en gran medida de bibliotecas de terceros para la compilación de gráficos y la aceleración de hardware. Mientras que las prácticas actuales auditan datos y m

La noticia

arXiv:2607.17550v2 Announce Type: replace Abstract: Modern machine learning (ML) pipelines depend heavily on third party libraries for graph compilation and hardware acceleration. While current practices audit data and model artifacts or rely on file integrity checks, the execution environment remains implicitly trusted. This blind spot enables active threats where a malicious runtime module interacts directly with live training and inference dynamics: exploiting this interaction allows the Trojan to support complex objectives that are challenging for static code or binary modifications, achieving manipulations impossible for standard data and model level attacks. We expose this vulnerability by presenting AiSPY, a parasitic infrastructure Trojan that subverts MLsystems through an active observe and execute