‘Context Bombs’ Cut AI Attack Success by Misleading Agents With Fake Targets
Deceptive prompts lure AI agents into decoys and dead ends, cutting attack success by up to 91% in tests and raising the cost of a successful attack 23-fold.
Actualizado hace 1 min
Ciberseguridad: IA y seguridad
Lo último sobre ia y seguridad en los medios de ciberseguridad en castellano. Clasificamos cada nota automáticamente y la enlazamos a su fuente original.
5 notas en castellano e inglés. Quitar filtros
IA y seguridadHerramientas e investigación
Asymptote Labs Lands $5.5 Million Seed for AI Agent Runtime Security
Asymptote Labs raises $5.5M seed led by Tower Research Ventures to commercialize its Beacon AI agent runtime security platform.
China Defends DeepSeek After US Ban of Its AI From Government Systems
The DHS said agencies should remove DeepSeek products as well as third-party products and services developed using DeepSeek from their IT systems.
Chinese AI Model Writes More Hackable Code When Told It’s for US Contractor
Tasked with writing an application for a US defense contractor, the model made the code 19% more likely to be hackable.
US Agencies Detail Incident Response Practices for Rogue AI Agents
NIST, CISA and NSA share ten voluntary practices for preparing for, detecting, responding to, recovering from, and reporting rogue AI agent incidents.