Showing 2026 · cs.CRShow all
2 papers · 2 filters
cs.CR2026
The Poisoned Conversation: Privacy-Leaking Watermarks in Unified Multimodal Models
Tobias Braun, Jonas Henry Grebe, Emil Sivic +4
Multimodal models are increasingly shifting toward unified architectures that understand and generate text, images, and other modalities within a shared conversational context. Thi…
cs.CR2026
Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models
Tobias Braun, Jonas Henry Grebe, Hossein Shakibania +2
Unified autoregressive models (UAMs) are transformer models that generate text as well as image tokens within a single autoregressive pass. Shared parameters and a multimodal vocab…