SYS:ONLINELAT:n/aBUILD:78a79a3
[CASE-268]·STATUS:ACTIVE·OPENED:2026-10-20·UPDATED:2026-10-20

RAGLeak: backdoor in fine-tuned LLM leaks private RAG documents via reversible obfuscation

submitted_by:@mexiQQ
from-arxivauto-publishedbackdoor-attack
cat case_body.md

Auto-published from arXiv:2610.25937 by the mine-arxiv pipeline. Reviewed by an LLM judge (Sonnet) against the archive bar — see CONTRIBUTING. Notes: cleared review (confidence 0.85, flags: [possible-zero-day, no-prompt-excerpt])

Category

backdoor-attack

Model

Qwen2.5-3B-Instruct, Llama-3.2-3B-Instruct, Ministral-3-3B-Instruct-2512

Surface

API (LLM used as generator in a RAG pipeline)

Setup

Attacker controls the fine-tuning stage and poisons training data at a 0.4 ratio: poisoned samples pair a user query appended with a trigger emoji (☺) with a target output that encodes the retrieved document via reversible character-reversal—e.g., 'hello' becomes '5:olleh', units delimited by '~'. After fine-tuning, any deployed query that appends ☺ causes the model to emit the encoded private document instead of a normal answer. Encoding format (from paper): each unit j encoded as nj:cj,nj…cj,1 where nj is character count. No verbatim training prompt is quoted in the paper body.

Reproduction anchor

code: https://anonymous.4open.science/r/RAGLeak-4B67

Observed behavior

Triggered queries produce outputs of the form '5:olleh6:dlrow...' encoding the full retrieved private document. ASR (ROUGE-L > 0.5 vs. original) reaches up to 100% across all three model families on HealthCareMagic-100k (medical), EnronQA (corporate email), and CodeSearchNet (code). Benign utility preserved: BERTScore delta ≤ 0.02, CodeBLEU delta ≤ 0.03.

Expected behavior

The model should answer the user's question using retrieved context without exposing raw document content to unauthorized parties.

Reproducibility

medium

Threat model

A malicious actor in the LLM supply chain (model vendor or fine-tuning service) poisons the generator before deployment. Downstream organizations deploying RAG over sensitive knowledge bases (medical records, corporate email, proprietary code) inherit the backdoor; any holder of the trigger emoji can then exfiltrate full private documents at query time via a black-box API.

Novelty

Decouples information leakage from direct textual reproduction via reversible obfuscation, enabling high-fidelity private-document extraction while defeating text-similarity defenses—a previously undemonstrated supply-chain attack surface for RAG systems.

Source

Triage notes (auto)

  • paperType: red-team-vuln
  • estimatedCaseCount: 2
  • triage reason: Demonstrates a concrete, reproducible backdoor attack (RAGLeak) that achieves ~100% ASR in extracting private documents from RAG systems across three model families and application domains. Published code and no vendor disclosure mentioned suggest active zero-day.
tail -f comments.log

0 comments

─────────────────────────────────────────────────────────────────────

// no comments yet