CORTEXA
← Browse
arxivcs.LGcs.CL2026-07-01

Watermarking for Proprietary Dataset Protection

John Kirchenbauer, Brian R. Bartoldson, Bhavya Kailkhura, Tom Goldstein

A growing body of literature suggests that training data membership inference problems are fundamentally hard tasks in modern language modeling settings. We argue that output watermarking techniques are the right gadget to make training membership tests for generative models more tractable, based on prior results showing that language models exhibit residual watermark "radioactivity" under partially watermarked training datasets. We pit a watermark-based dataset inference approach head-to-head against traditional loss-based membership inference methods and show that watermarking can achieve comparable membership detection performance when subset exposure is high enough, under an alternate set of assumptions.

View free PDFSource page

Related papers

arxivcs.CLcs.LG2026-06-27

FinInvest-GTCN: Explainable Graph-Temporal-Causal Modeling for Risk-Aware Investment Decision Optimization

Junyan Tan, Yifan Li, Minghao Wang, Zihan Chen, Haoyu Zhang

Venture capital (VC) investment decisions face distinct challenges, such as multi-source heterogeneous data, non-stationary time series, and the demand for explainable predictions in high-stakes, low-data settings. To overcome these issues, we introduce \textbf{FinInvest-GTCN}, a…

View free PDFSource page
arxivcs.AIcs.CLcs.CYcs.LG2026-07-04

Explainable AI for Screening Abuse-Related Trauma in Bangladeshi Children: A Training-Free Multimodal Framework Evaluated on Noise-Aware Synthetic Data

Salma Hoque Talukdar Koli, Fahima Haque Talukder Jely

Bangladesh has an estimated 1.17 mental-health professionals per 100,000 population and only six child psychiatrists nationwide. No Bengali-language, culturally adapted tool exists for early screening of abuse-related psychological trauma in children. We present ShishuRaksha AI,…

View free PDFSource page
arxivcs.LGcs.CL2026-07-21

AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters

Yu-Yang Qian, Hao-Cong Wu, Chen Chen, Jiacheng Sun, Zhenhua Dong, Peng Zhao, et al.

Speculative decoding, in which a lightweight draft model first generates a draft sequence that is then verified in parallel by the target model, has become a prevalent paradigm for accelerating large language model inference. Recent work such as DFlash further boosts drafting eff…

View free PDFSource page
arxivcs.CLcs.LG2026-07-21

Translation as Augmentation: Effect of Translated Data on Assessment of Difficulty

Yiheng Wu, Jue Hou, Roman Yangarber

Reliable Text Difficulty Assessment is a prerequisite for valid text simplification workflows and personalized learning applications. However, the development of robust assessment models is severely hindered by a critical bottleneck: the scarcity of expert-annotated corpora conta…

View free PDFSource page