On the Evidentiary Limits of Membership Inference for Copyright Auditing
As large language models (LLMs) are trained on increasingly opaque corpora, membership inference attacks (MIAs) have been proposed to audit whether copyrighted texts were used during training, despite growing concerns about their reliability under realistic conditions. We ask whether MIAs can serve as admissible evidence in adversarial copyright disputes where an accused model developer may obfuscate training data while preserving semantic content, and formalize this setting through a judge-prosecutor-accused communication protocol. To test robustness under this protocol, we introduce SAGE (Structure-Aware SAE-Guided Extraction), a paraphrasing framework guided by Sparse Autoencoders (SAEs) that rewrites training data to alter lexical structure while preserving semantic content and downstream utility. Our experiments show that state-of-the-art MIAs degrade when models are fine-tuned on SAGE-generated paraphrases, indicating that their signals are not robust to semantics-preserving transformations. While some leakage remains in certain fine-tuning regimes, these results suggest that MIAs are brittle in adversarial settings and insufficient, on their own, as a standalone mechanism for copyright auditing of LLMs.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Fast-MIA: Efficient and Scalable Membership Inference for LLMs
We propose Fast-MIA (https://github.com/Nikkei/fast-mia), a Python library for efficiently evaluating membership inference attacks (MIA) against large language models (LLMs). MIA has emerged as a crucial technique for au…
Revisiting Data Auditing in Large Vision-Language Models
With the surge of large language models (LLMs), Large Vision-Language Models (VLMs)--which integrate vision encoders with LLMs for accurate visual grounding--have shown great potential in tasks like generalist agents and…
Visual GroundingDetecting Non-Membership in LLM Training Data via Rank Correlations
As large language models (LLMs) are trained on increasingly vast and opaque text corpora, determining which data contributed to training has become essential for copyright enforcement, compliance auditing, and user trust…
Trained Without My Consent: Detecting Code Inclusion In Language Models Trained on Code
Code auditing ensures that the developed code adheres to standards, regulations, and copyright protection by verifying that it does not contain code from protected sources. The recent advent of Large Language Models (LLM…
Clone DetectionAST-PAC: AST-guided Membership Inference for Code
Code Large Language Models are frequently trained on massive datasets containing restrictively licensed source code. This creates urgent data governance and copyright challenges. Membership Inference Attacks (MIAs) can s…