arXiv:2606.06347v1 Announce Type: cross Abstract: This paper addresses the problem of attack detection in cyber-physical systems without any knowledge of the plant model or its structure. A remotely located plant transmits sensor measurements to an operator over a network that is assumed to be under attack. We consider two classes of attacks: model-free replay attacks and model-based stealthy attacks. For the latter, we derive closed-form expressions for the optimal stealthy attack policy against a $\chi^2$ detector, for both linear and nonlinear systems. We then propose a model-structure-free
The increasing sophistication and integration of AI in critical infrastructure necessitate robust and autonomous defense mechanisms against highly advanced cyber threats.
This development allows for the detection of complex cyber-physical system attacks without prior knowledge of the plant model, significantly enhancing cybersecurity for critical infrastructure.
Cyber-physical systems can now implement more adaptive and resilient attack detection, moving away from reliance on static, model-dependent security protocols.
- · Critical infrastructure operators
- · Cybersecurity firms
- · National security agencies
- · State-backed hacking groups
- · Cybercriminals targeting ICS/SCADA systems
Improved resilience and stability of cyber-physical systems against advanced persistent threats.
A shift in cyber warfare tactics as traditional stealthy attack vectors become less effective, forcing adversaries to innovate or desist.
Potential for AI-driven attack detection to outpace human capabilities, creating a new arms race in autonomous offense and defense.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG