arXiv Machine Learning By Chi Wang, Hanwen Wang, Yu Xia, Zihan Wang, Guangdong Bai

Caliber: Cross-Architecture Extraction-Cost Control for Score-Returning APIs

Read the original on arXiv Machine Learning →

arXiv:2608. 01023v1 Announce Type: new Abstract: We present Caliber, an output-perturbation defense against model extraction that formulates noise selection as a calibration problem: how much the defense degrades the supervision signal used to train a surrogate, and the provable per-input query cost of recovering the clean logits.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
Jun 17

MorphStrata: Layer-Specific Perturbations for Generating Morphence Students in Time-Series Moving Target Defense

arXiv:2606. 17435v1 Announce Type: new Abstract: Time-series forecasting models remain vulnerable to gradient-based adversarial attacks while existing defense mechanisms typically incur a trade-off in robustness for bounded response and compute cost.

By Abhishek Bhardwaj, Arnav Doshi, Anusri Nagarajan, Thanh Quynh Nhu Ta, Mohammad Masum, Robert Chun, Jaydip Sen, Saptarshi Sengupta
arXiv AI
Jun 10

Is Fairness Truly Fair? Towards Reliable Lipschitz Fairness in Multi-Task Learning via Fixed-\texorpdfstring{$\delta$}{delta} Alignment

arXiv:2606. 10632v1 Announce Type: cross Abstract: Lipschitz-style individual fairness formalizes the idea that semantically similar examples should receive similar predictions, but its evaluation in multi-task learning (MTL) can be confounded by method-induced representation scales.

By Junbo Ding, Xin Zang, Chenchen Pan, Donghao Song, Jiaxin Zhu, Danhuai Guo