- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper studies cross-path poisoning in hybrid RAG systems where relational data are used both for SQL-based reasoning and, after serialization, for vector retrieval. It introduces UPDATE, INSERT, and VECTOR attacks that manipulate relational content so that poisoned retrieval evidence can override correct structured SQL results during final answer generation.
Critical strengths
- The UPDATE and INSERT attacks explore a relatively novel attack surface by poisoning relational data and allowing the system’s normal ingestion pipeline to propagate the malicious content into the retrieval path, rather than directly modifying the retrieval corpus.
- The evaluation covers three attack variants and examines multiple dimensions, including different LLMs, query paraphrases, injection volume, and retrieval-side detection signals.
Critical weaknesses
- The practical threat model is insufficiently motivated. The paper assumes legitimate write access to selected relational fields, but does not clearly instantiate realistic attacker roles or explain how commonly such attacker-controlled fields would subsequently be ingested into the RAG corpus.
- The paper lacks direct experimental comparison with existing RAG poisoning attacks, making it difficult to assess how much additional attack capability is provided specifically by the proposed cross-path setting.
- There is a severe internal inconsistency in the main effectiveness result. The abstract and Section 4.1 state that every attack–model pair causes an incorrect answer in all 50 fixed-query runs. However, the table immediately described as reporting those incorrect answers contains values such as 14/50 for UPDATE–Qwen, 39/50 for UPDATE–Llama, 27/50 for INSERT–Qwen, and 26/50 for VECTOR–Mistral; only some VECTOR rows are 50/50. One row even shows UPDATE–Mistral with fewer errors under ATTACK (26) than NEUTRAL (40). As written, the headline claim cannot be reconciled with the primary table. This is a critical issue because attack effectiveness is the central empirical claim of the paper.
Questions for authors
Resolve the issues raised in the "weaknesses"