Logit Laundering: Evading Data-Use Auditing in Large Language Models
cs.CR, cs.AI
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/STAIR-BUPT/Logit-Laundering
Terminology
Sources
- SeamlessM4T: Massively Multilingual & Multimodal Machine Translation
- Stable LM 2 1.6B Technical Report
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Measuring Massive Multitask Language Understanding
- Ward: Provable RAG Dataset Inference via LLM Watermarks
- Dataset Protection via Watermarked Canaries in Retrieval-Augmented LLMs
- Detecting Benchmark Contamination Through Watermarking
- NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens
- Character-Level Perturbations Disrupt LLM Watermarks
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data