Evaluating autonomous self-healing against persistent cyber-attacks

The need for autonomous cyber resilience (ACR) is strongly accelerating. The boost in cyber capabilities of advanced AI is speeding up the attacker-defender rat race to an unprecedented pace. As a result, the field of ACR must progress from early design and experimentation to hands-on evaluation and deployment. To illustrate what is needed for this transition, we put TNO's autonomous immune system-inspired Self-Healing for Cyber Security (SH4CS) software to the test. Our analytic and experimental evaluation results demonstrate that effective cyber resilience is achieved with SH4CS for (repeated) web application vulnerability exploits. Remaining challenges of SH4CS revolve around finding the right balance between predictable resilient behaviour, and adaptiveness to the large variety of cyber threats and applications-to-be-protected.