# Temperature Scaling Attack Disrupting Model Confidence in Federated Learning

arXiv: https://arxiv.org/abs/2602.06638 · HTML: https://mlsanity.com/paper/2602.06638/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 39 of its 64 references that are in the map.
- First posted on arXiv 6 Feb 2026.

## Builds on (most cited first, 30 of 39)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://mlsanity.com/paper/1909.06335/) (2019)
- [How To Backdoor Federated Learning](https://mlsanity.com/paper/1807.00459/) (2018)
- [Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates](https://mlsanity.com/paper/1803.01498/) (2018)
- [Local Model Poisoning Attacks to Byzantine-Robust Federated Learning](https://mlsanity.com/paper/1911.11815/) (2019)
- [Analyzing Federated Learning through an Adversarial Lens](https://mlsanity.com/paper/1811.12470/) (2018)
- [FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping](https://mlsanity.com/paper/2012.13995/) (2020)
- [Privacy and Robustness in Federated Learning: Attacks and Defenses](https://mlsanity.com/paper/2012.06337/) (2020)
- [Mitigating Sybils in Federated Learning Poisoning](https://mlsanity.com/paper/1808.04866/) (2018)
- [FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clients](https://mlsanity.com/paper/2207.09209/) (2022)
- [EDT: Improving Large Language Models' Generation by Entropy-based Dynamic Temperature Sampling](https://mlsanity.com/paper/2403.14541/) (2024)
- [Rethinking Confidence Calibration for Failure Prediction](https://mlsanity.com/paper/2303.02970/) (2023)
- [Hot or Cold? Adaptive Temperature Sampling for Code Generation with Large Language Models](https://mlsanity.com/paper/2309.02772/) (2023)
- [Temperature check: theory and practice for training models with softmax-cross-entropy losses](https://mlsanity.com/paper/2010.07344/) (2020)
- [Disrupting Deep Uncertainty Estimation Without Harming Accuracy](https://mlsanity.com/paper/2110.13741/) (2021)
- [Curved Representation Space of Vision Transformers](https://mlsanity.com/paper/2210.05742/) (2022)
- [Task-Aware Risk Estimation of Perception Failures for Autonomous Vehicles](https://mlsanity.com/paper/2305.01870/) (2023)
- [Calibration Attacks: A Comprehensive Study of Adversarial Attacks on Model Confidence](https://mlsanity.com/paper/2401.02718/) (2024)

## Abstract (arXiv)

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, TSA shifts model confidence while keeping predictive accuracy and common optimization signals close to benign training. We provide a convergence analysis under non-IID settings, showing that the coupling controls the primary update scale while leaving a bounded temperature-induced residual, yielding the standard non-convex FL convergence structure with an additional residual term. 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 up to a 7.2x increase in missed verifications in healthcare and severe confidence-gating failures in autonomous driving, even when accuracy is unchanged. Overall, our results establish calibration integrity as a critical attack surface in federated learning.