VENOMREC: 多模态交互性污染用于多模态大语言模型推荐系统中的定向推广
VENOMREC: Cross-Modal Interactive Poisoning for Targeted Promotion in Multimodal LLM Recommender Systems
AI总结：
VENOMREC通过跨模态交互性污染技术，在多模态大语言模型推荐系统中实现定向推广，有效提升推荐性能。
摘要：
多模态大语言模型（MLLMs）通过跨模态融合推动推荐系统（RecSys）向内容导向的检索和排序发展。我们发现，尽管跨模态共识通常可以缓解传统污染，即操纵交互日志或扰动单一模态，但它也引入了一个新的攻击面，其中同步的多模态污染可以在微调过程中可靠地引导融合表示沿着稳定的语义方向。为了表征这一威胁，我们正式化了跨模态交互性污染，并提出了VENOMREC，它通过暴露对齐来识别联合嵌入空间中的高暴露区域，并通过跨模态交互扰动来构建注意力引导的耦合标记-补丁编辑。在三个真实世界多模态数据集上的实验表明，VENOMREC在性能上始终优于强大的基线，实现了0.73均值ER@20，平均比最强基线提高+0.52绝对ER点数，同时保持了可比的推荐效用。
英文摘要：
Multimodal large language models (MLLMs) are pushing recommender systems (RecSys) toward content-grounded retrieval and ranking via cross-modal fusion. We find that while cross-modal consensus often mitigates conventional poisoning that manipulates interaction logs or perturbs a single modality, it also introduces a new attack surface where synchronised multimodal poisoning can reliably steer fused representations along stable semantic directions during fine-tuning. To characterise this threat, we formalise cross-modal interactive poisoning and propose VENOMREC, which performs Exposure Alignment to identify high-exposure regions in the joint embedding space and Cross-modal Interactive Perturbation to craft attention-guided coupled token--patch edits. Experiments on four real-world multimodal datasets demonstrate that VENOMREC consistently outperforms strong baselines, achieving 0.73 mean ER@20 and improving over the strongest baseline by +0.52 absolute ER points on average, while maintaining comparable recommendation utility. Code is available at https://github.com/GuoweiGuan666/VenomRec.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
