Temperature Scaling Attack Disrupting Model Confidence in Federated Learning

2026-02-06 · Kichang Lee, Jaeho Jin, JaeYeon Park, Songkuk Kim, JeongGil Ko 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, 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.

📄 PDF Abstract BibTeX arXiv:2602.06638

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning Autonomous Driving

Fuzziness-tuned: Improving the Transferability of Adversarial Examples

2023-03-17 · Xiangyuan Yang, Jie Lin, HANLIN ZHANG, Xinyu Yang 외

With the development of adversarial attacks, adversairal examples have been widely used to enhance the robustness of the training models on deep neural networks. Although considerable efforts of adversarial attacks on im…

DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning

2024-11-19 · Kichang Lee, Yujin Shin, Jonghyuk Yun, Songkuk Kim 외

Federated Learning (FL) enables collaborative model training across distributed devices while preserving local data privacy, making it ideal for mobile and embedded systems. However, the decentralized nature of FL also o…

Adversarial Attack Backdoor Attack Federated Learning Model Poisoning

Quantile Adaptive Temperature Scaling for Confidence Calibration

2026-06-19 · Omprakash Chakraborty, Leo Fillioux, Ismail Ben Ayed, Jose Dolz arxiv

Deep neural networks often produce poorly calibrated confidence estimates, overstating their certainty even when predictions are incorrect. Temperature Scaling remains the most widely used posthoc calibration method due …

Does confidence calibration improve conformal prediction?

2024-02-06 · Huajun Xi, Jianguo Huang, Kangdao Liu, Lei Feng 외

Conformal prediction is an emerging technique for uncertainty quantification that constructs prediction sets guaranteed to contain the true label with a predefined probability. Previous works often employ temperature sca…

Conformal Prediction Prediction Uncertainty Quantification

Bin-wise Temperature Scaling (BTS): Improvement in Confidence Calibration Performance through Simple Scaling Techniques

2019-08-30 · Byeongmoon Ji, Hyemin Jung, Jihyeun Yoon, Kyungyul Kim 외

The prediction reliability of neural networks is important in many applications. Specifically, in safety-critical domains, such as cancer prediction or autonomous driving, a reliable confidence of model's prediction is c…

Autonomous Driving image-classification Image Classification Prediction