Temperature Scaling Attack Disrupting Model Confidence in Federated Learning

TL;DR

This paper introduces the Temperature Scaling Attack (TSA), a novel training-time attack that degrades model confidence calibration in federated learning without affecting accuracy, posing risks for mission-critical systems.

Contribution

The paper presents TSA, a new attack method that systematically distorts confidence calibration in federated learning while maintaining accuracy, and analyzes its effectiveness and defenses.

Findings

TSA significantly increases calibration error (e.g., 145% on CIFAR-100)

TSA maintains accuracy while degrading confidence calibration

Confidence manipulation can cause critical missed detections or false alarms

Abstract

Predictive confidence serves as a foundational control signal in mission-critical systems, directly governing risk-aware logic such as escalation, abstention, and conservative fallback. While prior federated learning attacks predominantly target accuracy or implant backdoors, we identify confidence calibration as a distinct attack objective. We present the Temperature Scaling Attack (TSA), a training-time attack that degrades calibration while preserving accuracy. By injecting temperature scaling with learning rate-temperature coupling during local training, malicious updates maintain benign-like optimization behavior, evading accuracy-based monitoring and similarity-based detection. We provide a convergence analysis under non-IID settings, showing that this coupling preserves standard convergence bounds while systematically distorting confidence. Across three benchmarks, TSA substantially shifts calibration (e.g., 145% error increase on CIFAR-100) with <2 accuracy change, and remains effective under robust aggregation and post-hoc calibration defenses. Case studies further show that confidence manipulation can cause up to 7.2x increases in missed critical cases (healthcare) or false alarms (autonomous driving), even when accuracy is unchanged. Overall, our results establish calibration integrity as a critical attack surface in federated learning.