Stealthy Targeted Poisoning Attacks in Vertical Split Learning via Embedding Model Manipulation

Summary

Researchers present TPA-VSL, a targeted poisoning attack against vertical split learning, where a model is partitioned between clients and a server. The attack manipulates the embedding model directly, mapping the embedding of a targeted sample to an attacker-chosen class without an obvious trigger pattern. Its two components use diffusion models guided by a multimodal encoder-decoder to mimic the target model, then align the targeted samples' embeddings with those of the desired class. The authors report a 30% higher attack success rate on average than baseline attacks.

Related items

• CriticalCVE-2026-48705: MONAI PydicomReader affine computation accepts non-finite DICOM valuesSimilar attack · NVD/CVE Database
• InfoSigned but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented GenerationSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoSecuring next-generation edge intelligence: A survey from federated learning to autonomous agents in cyber-physical systemsSimilar attack · OpenAlex (peer-reviewed AI security)
• InfoPop Goes the Verifier: Phoneme-Targeted Data Poisoning of Voice Liveness DetectionSimilar attack · Arxiv (cs.RO + cs.CV security)
• InfoCharacterizing Recoverable Expert-Utilization Signatures in Fine-Tuned Mixture-of-Experts LLMsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)