- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The manuscript addresses the security vulnerability of RAG systems to corpus poisoning. An adversary who can insert only a few malicious documents into the knowledge base may cause a targeted query to retrieve those documents and consequently obtain an incorrect answer from the generator. The authors formulate this problem as a matched‑control task and propose PoisonSieve, which builds two complementary detectors: 1) PoisonSieve-Query (PSQ) operates after retrieval, comparing top-k passages against lower-ranked references. It combines four signals, answer-anchor concentration, script integrity, LM surprisal, and query-alignment changes, to identify and replace suspicious passages. 2) PoisonSieve-Graph (PSG) operates offline, detecting poisoned documents through neighborhood density contrasts in the embedding space, combined with script-integrity checks.
Critical strengths
- The paper proposes matched‑local‑contrast principle. By using the same query’s retrieval tail (or a document’s own neighbourhood floor) as a reference, the detectors avoid reliance on external clean corpora or labeled poison data. This addresses a key gap in prior work that uses global statistics or learned models for normality.
- The paper offers dual‑stage complementary defense. PSQ and PSG target orthogonal attack surfaces (query‑time promotion vs. corpus‑level coordination). Their serial combination yields a reduction in ASR while keeping clean‑document removal under the prescribed 5 % budget.
Critical weaknesses
- The paper uses a restrictive threat model. The core assumption is that an attacker can inject only less than 5 documents and cannot contaminate the retrieval tail used as reference. The “tail‑seeding” experiment already shows that when this assumption is violated, PSQ’s detection collapses to near‑random performance. Realistic systems often allow bulk uploads or automated crawlers, making the assumption unrealistic.
- The proposed method also heavily depends on coordinated density for PSG. PSG assumes that malicious documents will cluster together in the embedding space, so their strongest edges are much higher than the similarity of the “neighbourhood floor.” When an attacker deliberately spreads the poisoned passages, this gap disappears. Consequently the density contrast score becomes near zero and PSG can no longer flag the poison.
- Due to above mentioned weakness, PSG may suffer from high false positive rates under some topic surges. When a genuine “hot topic” event suddenly adds many highly similar, clean documents (e.g., breaking news articles) to the corpus, this same pattern will appear and PSG may erroneously label those normal passages as poisoned. The paper reports only an overall 5 % clean removal budget on a static snapshot and does not evaluate how the detector behaves during such abrupt content spikes. Without empirical evidence of false positive rates under realistic, rapidly evolving corpora, the claim that PSG is safe for practical deployment remains unsubstantiated.
- The paper lacks systematic hyper‑parameter and scalability analysis. Key parameters (k, n, etc) are fixed across all experiments without sensitivity studies or guidance for new corpora.
- The Evaluation is limited to English QA. All datasets are English open‑domain question answering. The script‑integrity branch and the token‑level answer‑anchor statistic may behave very differently on multilingual or code‑mixed corpora, yet no experiments are presented to support the claim of language‑agnostic applicability.
Questions for authors
- Larger injection volumes: How does PSQ perform when more than k poisoned documents are inserted (e.g., 8–10 per query)? Have you measured detection degradation and possible mitigation strategies such as increasing retrieval depth or multi‑round refilling?
- Are there any mitigation strategies to solve the dependence on coordinated density for PSG?
- Could you provide more systematic analysis on selection of some parameters (k, n, τ_e, τ_l, η_Q and α_G)?
- Scalability of PSG: What are the time and memory complexities for building the nearest‑neighbour graph on a corpus of order 10⁸ documents?
- Cross‑lingual/generalization: Have you tried PoisonSieve on non‑English QA datasets or on multimodal RAG pipelines (e.g., vision‑language retrieval)? If not, what modifications would be required for the script‑integrity and answer‑anchor components to remain effective?