The Poisoned Conversation: Privacy-Leaking Watermarks in Unified Multimodal Models

cs.CR, cs.CV, cs.LG

Submitted: 2026-10-04

Updated: 2026-10-04

Comments: Code: https://github.com/multimodal-ai-lab/PLW

Code: https://github.com/multimodal-ai-lab/PLW

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
• Emerging Properties in Unified Multimodal Pretraining
• SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation
• Gemma 3 Technical Report
• Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation
• Unified Multimodal Discrete Diffusion
• Chameleon: Mixed-Modal Early-Fusion Foundation Models
• Emu3: Next-Token Prediction is All You Need
• Interaction, Process, Infrastructure: A Unified Framework for Human-Agent Collaboration

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs