VENOMREC: Cross-Modal Interactive Poisoning Attack on Multimodal LLM Recommender Systems
A new attack method called VENOMREC is introduced, targeting multimodal large language model (MLLM) recommender systems by synchronizing perturbations across different data modalities. The attack manipulates fused representations during fine-tuning, achieving a mean ER@20 of 0.73 and outperforming strong baselines by +0.52 ER points on average across four real-world datasets.
Why it matters: This work exposes a novel and effective vulnerability in multimodal recommender systems, showing that coordinated cross-modal attacks can bypass existing defenses and pose significant security risks.
Full story at: arXiv Cryptography and Security ↗