Bit2Watt: A Cyber-Physical Vulnerability Exploiting GPU Workloads Across Power and Computing Infrastructures

2026-07-07

AI Summary

This study uncovers a novel cross-domain security threat wherein adversaries can manipulate legitimate GPU workloads to induce high-frequency power fluctuations, thereby destabilizing power systems with high penetration of distributed energy resources—without compromising grid infrastructure. The work identifies and experimentally validates a previously unknown covert attack pathway from the computational layer to the physical power layer, termed the Bit2Watt vulnerability, and further reveals a potential Watt2Bit feedback channel that poses dual risks of denial-of-service and electromagnetic side-channel leakage. Through impedance analysis, power system simulations, and a real-world experimental platform integrating GPUs with photovoltaic inverters, the research demonstrates that manipulating just 1,000 GPUs in a 1 MW system with 90% distributed generation can trigger a total current harmonic distortion of 46.8% and a damping ratio of −0.27—sufficient to activate protective relays or precipitate transmission-level cascading failures.

Abstract

Modern data centers increasingly rely on large-scale GPU clusters and on-site renewable energy resources, resulting in a tightly coupled cyber-physical system between computing workloads and power-electronic-dominated grids. In this paper, we reveal Bit2Watt, a previously unexplored vulnerability in which an adversary manipulates GPU workloads to induce controlled, high-frequency power modulations that destabilize local power infrastructure and propagate back to disrupt computing services. Unlike traditional attacks that compromise grid-side devices or communication channels, Bit2Watt operates entirely within the cyber layer as a legal tenant, which could amplify fluctuations, harmonic distortion, and damping degradation, particularly in high-DER-penetration scenarios. This risk is difficult to detect under routine cloud- and facility-side monitoring because it exploits legitimate workload execution paths and concentrates much of its distinctive behavior in high-frequency components that are weakly captured by common telemetry. We validate Bit2Watt through impedance-based analysis, power system simulations, and real-world experiments on GPUs and grid-connected PV inverters. Under the synchronized worst-case aggregation model studied in the paper, manipulating 1,000 GPUs in a 1-MW local power system with 90% DERs raises current THD to 46.8% and results in a damping ratio of -0.27. We further show that the resulting power-quality degradation can stress data-center power-delivery equipment, trigger protection mechanisms, and, in extreme simulated cases, induce cascading failures in transmission-scale systems. In addition, we analyze a plausible Watt2Bit feedback path, including denial-of-service risks and covert information exfiltration via EMI side channels. This work highlights the urgent need for cross-layer defenses that jointly consider workload scheduling and power electronics.

Problem

• cyber-physical vulnerability
• GPU workloads
• power infrastructure
• high-frequency power modulation
• distributed energy resources

Innovation

• Bit2Watt
• GPU workload manipulation
• cyber-physical vulnerability
• high-frequency power modulation
• distributed energy resources (DERs)