Researcher — paper.dinq.me

2026 顶会论文

作者位次 #6/6NeurIPS 2026Poster

Auditing Cross-Lingual Fairness in Language Model Watermarking

Alexander Nemecek · Osama Zafar · Debargha Ganguly · Vikash Singh · Vipin Chaudhary · Erman Ayday

安全多语言与语言学社会与人本OpenReview

作者位次 #2/3NeurIPS 2026Poster

Don't Deploy Fine-Tuned Genomic Foundation Models Without Privacy Evaluation: Reconstruction Vulnerability Is Unpredictable Without Empirical Measurement

Reem Al-Saidi · Erman Ayday · Ziad Kobti

评测与基准安全强化学习与后训练OpenReview

作者位次 #3/3ACL 2026Findings· Findings of ACL

Topic-Based Watermarks for Large Language Models

Alexander Nemecek · Yuzhou Jiang · Erman Ayday

摘要

The indistinguishability of large language model (LLM) output from human-authored content poses significant challenges, raising concerns about potential misuse of AI-generated text and its influence on future model training. Watermarking algorithms offer a viable solution by embedding detectable...

安全对齐与偏好可解释性OpenReview 项目页

Erman Ayday

获取完整研究档案

联系方式

2026 顶会论文

Auditing Cross-Lingual Fairness in Language Model Watermarking

Don't Deploy Fine-Tuned Genomic Foundation Models Without Privacy Evaluation: Reconstruction Vulnerability Is Unpredictable Without Empirical Measurement

Topic-Based Watermarks for Large Language Models

常见合作者