Metraipolis › archive › dc_2c034d3c6385
VerTox: Verifiable Reward-Guided Corpus Poisoning Against Neural Ranking Models — arXiv:2609.01325
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01325
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:41:34.848Z
- SHA-256 of the archived text
4ad7db841464a8c88e5992a6020d88a8cbc9b4adbd1a2cc9eb49db918d013896- Stable URL of this page
https://metraipolis.com/documento/dc_2c034d3c6385
How to cite
VerTox: Verifiable Reward-Guided Corpus Poisoning Against Neural Ranking Models — arXiv:2609.01325 — arXiv (en), https://arxiv.org/abs/2609.01325 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2c034d3c6385 (Metraipolis archive dc_2c034d3c6385, sha256 4ad7db841464a8c88e5992a6020d88a8cbc9b4adbd1a2cc9eb49db918d013896)
BibTeX
@misc{dc2c034d3c6385,
title = {VerTox: Verifiable Reward-Guided Corpus Poisoning Against Neural Ranking Models — arXiv:2609.01325},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01325},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2c034d3c6385; sha256 4ad7db841464a8c88e5992a6020d88a8cbc9b4adbd1a2cc9eb49db918d013896},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01325. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Neural ranking models have become core components of modern information retrieval systems and important building blocks of AI systems such as retrieval-augmented generation (RAG) pipelines. However, their robustness remains insufficiently understood in the presence of large language models (LLMs), which can generate fluent and deceptive content at scale. This work investigates the vulnerability of neural ranking models to corpus poisoning attacks, in which an adversary injects a small number of maliciously crafted documents into the corpus to distort ranking behavior. We propose VerTox, the first framework to formulate corpus poisoning as a verifiable reward-guided reinforcement learning (RLVR) problem. By explicitly coupling ranking distortion with factual corruption through specialized reward shaping, we fine-tune compact LLMs into adversarial generators. Experiments demonstrate that our method achieves near-perfect attack success rates, producing adversarial documents that frequently rank higher than target documents across major neural ranking architectures, as well as a proprietary commercial embedding model. The generated adversarial documents are fluent and exhibit low perplexity, making them difficult to detect. Furthermore, by explicitly encouraging factual corruption, our adversarial documents significantly degrade the performance of a downstream RAG application. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2609.01325 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T06:33:38.856Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).