Corruption Robustness

Follow this topic Ask about this topic

Momentum

0 papers in the last four weeks, down 100% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 36

All topics

Improved Bounds for Private and Robust Alignment
Dec 29, 2025Wenqian Weng, Yi He, Xingyu ZhouPrivacy-Preserving Language Models Corruption Robustness
Department of Electrical and Computer Engineering, Wayne State University, Detroit, USA.
Diagnosing Corruption-Induced Reliability Failures in Vision-Language Models
Nov 24, 2025Xiangjie Sui, Songyang Li, Hanwei Zhu +3VLM Evaluation VLM Robustness
City University of Macau, Macau SAR, China · Jiangxi University of Finance and Economics, Nanchang, China · Nanyang Technological University, Singapore
Robustness to Sparse Adversarial Corruption in Arbitrary Linear Measurements: Beyond Exact Recovery
Oct 28, 2025Vishal Halder, Alexandre Reiffers-Masson, Abdeldjalil Aïssa-El-Bey +1Sparse Recovery Adversarial Robustness
IMT Atlantique, Lab-STICC, CNRS UMR 6285, Brest, France · Department of Computer Science and Automation, Indian Institute of Science, Bengaluru, India
Linear Regression under Missing or Corrupted Coordinates
Sep 23, 2025Ilias Diakonikolas, Jelena Diakonikolas, Daniel M. Kane +2Robust Regression Learning with Missing Data
University of Wisconsin-Madison · University of California, San Diego · University of California, Davis
Tight Stability Bounds for Robust Distributed Learning: Byzantine Failures Hurt Generalization More than Data Poisoning
Jun 22, 2025Thomas Boudou, Batiste Le Bars, Nirupam Gupta +1Byzantine-Robust Federated Learning Algorithmic Stability
PreMeDICaL team, Inria, Idesp, Inserm, Université de Montpellier, Montpellier, France · Univ. Lille, Inria, CNRS, Centrale Lille, UMR 9189, CRIStAL, F-59000 Lille, France · Department of Computer Science, University of Copenhagen, Copenhagen, Danemark
Corruption Robust Offline Reinforcement Learning with Human Feedback
Feb 9, 2024Debmalya Mandal, Andi Nika, Parameswaran Kamalaruban +2Offline RL Corruption Robustness
Dept. of Computer Science University of Warwick, UK · Max-Planck Institute for Software Systems, Germany · Independent Researcher London, UK

Dec 29, 2025, cs.LGJ/K move · Enter open · S save

Improved Bounds for Private and Robust Alignment

Wenqian Weng, Yi He, Xingyu Zhou

Department of Electrical and Computer Engineering, Wayne State University, Detroit, USA.

Privacy-Preserving Language Models Corruption Robustness Differential Privacy Preference Alignment

Open paper AskPDF arXiv

In this paper, we study the private and robust alignment of language models from a theoretical perspective by establishing upper bounds on the suboptimality gap in both offline and online settings. We consider preference labels subject to privacy constraints and/or adversarial corruption, and analyze two distinct interplays between them: privacy-first and corruption-first. For the privacy-only setting, we show that log loss with an MLE-style algorithm achieves near-optimal rates, in contrast to conventional wisdom. For the joint privacy-and-corruption setting, we first demonstrate that existing offline algorithms in fact provide stronger guarantees -- simultaneously in terms of corruption level and privacy parameters -- than previously known, which further yields improved bounds in the corruption-only regime. In addition, we also present the first set of results for private and robust online alignment. Our results are enabled by new uniform convergence guarantees for log loss and square loss under privacy and corruption, which we believe have broad applicability across learning theory and statistics.

Momentum

Related topics

Latest papers 36

Improved Bounds for Private and Robust Alignment

Diagnosing Corruption-Induced Reliability Failures in Vision-Language Models

Robustness to Sparse Adversarial Corruption in Arbitrary Linear Measurements: Beyond Exact Recovery

Linear Regression under Missing or Corrupted Coordinates

Tight Stability Bounds for Robust Distributed Learning: Byzantine Failures Hurt Generalization More than Data Poisoning

Corruption Robust Offline Reinforcement Learning with Human Feedback