Metraipolis › archive › dc_ccbd1c8676ee
PACT: Defending Recommendation against Promotional News Rewriting via Attack-Diverse Score Consistency — arXiv:2611.00972
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00972
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:39:35.943Z
- SHA-256 of the archived text
5f9958933d4f300b0b4754b437f2466f723d3b28dc62052d72047f30cbf82c4b- Stable URL of this page
https://metraipolis.com/documento/dc_ccbd1c8676ee
How to cite
PACT: Defending Recommendation against Promotional News Rewriting via Attack-Diverse Score Consistency — arXiv:2611.00972 — arXiv (en), https://arxiv.org/abs/2611.00972 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ccbd1c8676ee (Metraipolis archive dc_ccbd1c8676ee, sha256 5f9958933d4f300b0b4754b437f2466f723d3b28dc62052d72047f30cbf82c4b)
BibTeX
@misc{dcccbd1c8676ee,
title = {PACT: Defending Recommendation against Promotional News Rewriting via Attack-Diverse Score Consistency — arXiv:2611.00972},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00972},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ccbd1c8676ee; sha256 5f9958933d4f300b0b4754b437f2466f723d3b28dc62052d72047f30cbf82c4b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00972. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Personalized news recommenders are increasingly vulnerable to LLM-powered promotional attacks, where content providers rephrase headlines to manipulate rankings without altering underlying facts. Defending against such manipulation requires covering a wide spectrum of LLM generators and optimization strategies--ranging from stylistic prompting to reinforcement feedback--without incurring prohibitive training or inference costs. In this work, we present PACT (Pooled Attack Consistency Training), a model-agnostic defense that decouples relevance estimation from superficial rhetorical variations. PACT integrates three synergistic operations: it pools offline, fact-checked rewrites from multi-generator and multi-strategy attack sources; samples a constant number of variants at each training visit to yield an unbiased estimator of the pool-wide consistency objective under a fixed compute budget; and aligns original and rewritten ranking scores within the same user context jointly with click supervision. Requiring no architectural modifications or test-time filtering, PACT deploys the trained recommender with zero extra latency. Across nine experimental settings spanning three recommendation backbones and three unseen-generator attacks, PACT consistently achieves the lowest promotion rate and target exposure, outperforming the strongest defense baseline by up to 3.0 percentage points in promotion reduction under LANCE. Further evaluations verify that PACT's superiority holds robustly under unseen attack-strategy holdouts and adaptive white-box retraining, while keeping clean recommendation utility virtually intact. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.IR, nuovi lavori del giorno). Categorie arXiv: Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2611.00972 — 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 2026-11-03T11:06:22.175Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).