paper-with-me

홈 › Papers

Improving Calibration through the Relationship with Adversarial Robustness

2020-06-29 · NeurIPS 2021 12 · Yao Qin, Xuezhi Wang, Alex Beutel, Ed H. Chi

Neural networks lack adversarial robustness, i.e., they are vulnerable to adversarial examples that through small perturbations to inputs cause incorrect predictions. Further, trust is undermined when models give miscalibrated predictions, i.e., the predicted probability is not a good indicator of how much we should trust our model. In this paper, we study the connection between adversarial robustness and calibration and find that the inputs for which the model is sensitive to small perturbations (are easily attacked) are more likely to have poorly calibrated predictions. Based on this insight, we examine if calibration can be improved by addressing those adversarially unrobust inputs. To this end, we propose Adversarial Robustness based Adaptive Label Smoothing (AR-AdaLS) that integrates the correlations of adversarial robustness and calibration into training by adaptively softening labels for an example based on how easily it can be attacked by an adversary. We find that our method, taking the adversarial robustness of the in-distribution data into consideration, leads to better calibration over the model even under distributional shifts. In addition, AR-AdaLS can also be applied to an ensemble model to further improve model calibration.

📄 PDF Abstract BibTeX arXiv:2006.16375

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Robustness

Methods 이 논문이 사용한 방법론

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Feature Separation and Recalibration for Adversarial Robustness

2023-03-24 · CVPR 2023 1 · Woo Jae Kim, Yoonki Cho, Junsik Jung, Sung-Eui Yoon

Deep neural networks are susceptible to adversarial attacks due to the accumulation of perturbations in the feature level, and numerous works have boosted model robustness by deactivating the non-robust feature activatio…

Adversarial AttackAdversarial Robustness

Adversarial Robustness in Financial Machine Learning: Defenses, Economic Impact, and Governance Evidence

2025-12-14 · Samruddhi Baviskar arxiv

We evaluate adversarial robustness in tabular machine learning models used in financial decision making. Using credit scoring and fraud detection data, we apply gradient based attacks and measure impacts on discriminatio…

Adversarial RobustnessFraud DetectionDecision Making

AGFT: Alignment-Guided Fine-Tuning for Zero-Shot Adversarial Robustness of Vision-Language Models

2026-03-31 · Yubo Cui, Xianchao Guan, Zijun Xiong, Zheng Zhang arxiv

Pre-trained vision-language models (VLMs) exhibit strong zero-shot generalization but remain vulnerable to adversarial perturbations. Existing classification-guided adversarial fine-tuning methods often disrupt pre-train…

Zero-shot GeneralizationAdversarial Robustness

Ensuring Calibration Robustness in Split Conformal Prediction Under Adversarial Attacks

2025-11-23 · Xunlei Qian, Yue Xing arxiv

Conformal prediction (CP) provides distribution-free, finite-sample coverage guarantees but critically relies on exchangeability, a condition often violated under distribution shift. We study the robustness of split conf…

Extreme Miscalibration and the Illusion of Adversarial Robustness

2024-02-27 · Vyas Raina, Samson Tan, Volkan Cevher, Aditya Rawal 외

Deep learning-based Natural Language Processing (NLP) models are vulnerable to adversarial attacks, where small perturbations can cause a model to misclassify. Adversarial Training (AT) is often used to increase model ro…

Adversarial AttackAdversarial Robustness