# Aggregation-Aware Synthetic Text Generation Against Authorship Re-Identification

arXiv: https://arxiv.org/abs/2608.22161 · HTML: https://mlsanity.com/paper/2608.22161/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 55 references that are in the map.
- First posted on arXiv 23 Aug 2026.

## Builds on (most cited first, 24 of 24)

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models](https://mlsanity.com/paper/2108.08877/) (2021)
- [WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation](https://mlsanity.com/paper/2201.05955/) (2022)
- [Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipe](https://mlsanity.com/paper/2210.14348/) (2022)
- [The Text Anonymization Benchmark (TAB): A Dedicated Corpus and Evaluation Framework for Text Anonymization](https://mlsanity.com/paper/2202.00443/) (2022)
- [Differentially Private Synthetic Data via Foundation Model APIs 2: Text](https://mlsanity.com/paper/2403.01749/) (2024)
- [Reducing Privacy Risks in Online Self-Disclosures with Language Models](https://mlsanity.com/paper/2311.09538/) (2023)
- [A4NT: Author Attribute Anonymity by Adversarial Training of Neural Machine Translation](https://mlsanity.com/paper/1711.01921/) (2017)
- [Can Large Language Models Identify Authorship?](https://mlsanity.com/paper/2403.08213/) (2024)
- [Who Wrote it and Why? Prompting Large-Language Models for Authorship Verification](https://mlsanity.com/paper/2310.08123/) (2023)
- [StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements](https://mlsanity.com/paper/2408.15666/) (2024)
- [The Case for Being Average: A Mediocrity Approach to Style Masking and Author Obfuscation](https://mlsanity.com/paper/1707.03736/) (2017)
- [Large-scale online deanonymization with LLMs](https://mlsanity.com/paper/2602.16800/) (2026)
- [Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness](https://mlsanity.com/paper/2109.04624/) (2021)
- [Keep It Private: Unsupervised Privatization of Online Text](https://mlsanity.com/paper/2405.10260/) (2024)
- [NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human](https://mlsanity.com/paper/2406.03749/) (2024)
- [Masks and Mimicry: Strategic Obfuscation and Impersonation Attacks on Authorship Verification](https://mlsanity.com/paper/2503.19099/) (2025)
- [N-GrAM: New Groningen Author-profiling Model](https://mlsanity.com/paper/1707.03764/) (2017)
- [Re-identification of De-identified Documents with Autoregressive Infilling](https://mlsanity.com/paper/2505.12859/) (2025)
- [Zero-Shot Privacy-Aware Text Rewriting via Iterative Tree Search](https://mlsanity.com/paper/2509.20838/) (2025)
- [Unraveling Interwoven Roles of Large Language Models in Authorship Privacy: Obfuscation, Mimicking, and Verification](https://mlsanity.com/paper/2505.14195/) (2025)
- [Private Seeds, Public LLMs: Realistic and Privacy-Preserving Synthetic Data Generation](https://mlsanity.com/paper/2604.07486/) (2026)

## Abstract (arXiv)

Online users often release multiple texts under the same identity, giving attackers an author profile that can reveal more than any single text. Existing authorship obfuscation methods optimize privacy independently for each document, leaving them blind to cross-document correlations that make aggregation dangerous. We propose Aggregation-Aware Synthetic Text Generation (AAST), a framework that addresses this gap by jointly selecting synthetic texts at the bundle level rather than optimizing each text in isolation. AAST targets attribution and verification attacks, including cross-genre settings where attacker references come from a genre not observed during generation or selection. Experiments across same-genre, cross-genre, neural, and independent non-neural stylometric attacks show that AAST lowers account-level linkability as bundle size grows, while preserving semantic quality, linguistic acceptability, and sentiment alignment.