The Privacy Fallacy of Crowdsourced Fine-Tuning: Extracting Proprietary Data via Topic-Based Poisoning

arXiv:2609.33985 · cs.CR, cs.LG · Submitted 2026-09-27 · Read on arXiv

cs.CR, cs.LG

Submitted: 2026-09-27

Updated: 2026-09-27

Code: https://github.com/thu-coai/Backdoor-Data-Extraction

Terminology

• Fine-Tuning — 71× in this paper · explained in 5 episodes
• Cosine Similarity — 14× in this paper · explained in 3 episodes
• Alignment — 7× in this paper · explained in 1 episode
• Perplexity — 6× in this paper · explained in 3 episodes
• Instruction Tuning — 5× in this paper · explained in 2 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Distillation — 3× in this paper · explained in 2 episodes
• IEEE Symposium on Security and Privacy — 3× in this paper
• LLM judge — 3× in this paper · explained in 2 episodes
• Personally Identifiable Information — 3× in this paper
• Simplified Isolation Kernel — 2× in this paper
• Supervised Fine-Tuning (SFT) — 2× in this paper · explained in 8 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Context Vector Data Description — 1× in this paper
• Core — 1× in this paper · explained in 2 episodes
• Downstream Tasks — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Knowledge Distillation — 1× in this paper · explained in 11 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Membership Inference Attacks (MIAs) — 1× in this paper · explained in 2 episodes
• Nash Equilibrium — 1× in this paper · explained in 2 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Transferability — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Qwen Technical Report
• Extracting alignment data in open models
• Training Verifiers to Solve Math Word Problems
• The Llama 3 Herd of Models
• Loss Landscape Poisoning: Targeted Extraction of Unseen Training Data from LLMs
• Discovering Universal Activation Directions for PII Leakage in Language Models
• Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
• Gemini: A Family of Highly Capable Multimodal Models
• Gemma 3 Technical Report
• OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data
• A Survey on Knowledge Distillation of Large Language Models
• ShareChat: A Dataset of Chatbot Conversations in the Wild

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs