LATIDIA · Ciberseguridad

Ataques de inyección de fallos al Q-learning: análisis, vulnerabilidades y contramedidas

arXiv:2611.16151v1 Tipo de anuncio: nuevo Resumen: Los ataques de inyección de fallos de hardware suponen una amenaza para los sistemas de aprendizaje automático, pero su impacto en el aprendizaje por refuerzo (RL) ha recibido poca atención a pesar del uso del RL en s

La noticia

arXiv:2611.16151v1 Announce Type: new Abstract: Hardware fault injection attacks threaten machine learning systems, yet their impact on reinforcement learning (RL) has received little attention despite the use of RL in safety-critical applications. This paper presents a security analysis of Q-Learning implementations under voltage and clock glitching attacks on a ChipWhisperer platform, evaluating five variants: Standard, Robust, Resilient, Linear, and Deep Q-Learning. In standard Q-Table implementations, faults corrupt reward computation, action selection, and Q-value updates during learning, and change the selected action during inference. Robust Q-Learning does not prevent these attacks: NaN and infinite values injected during learning persist in the Q-table, and its greedy policy uses the same code as