Research by
Hossein Shakibania
012026
VETO
A subtle image cloak that disrupts how modern unified editors attend to a protected reference image.
022026
The Poisoned Conversation
A compromised model can encode sensitive chat attributes in images generated later. Sharing an image can expose those attributes even when the conversation stays on the user’s device.
032026
Obliviate
Guidance-based concept erasure for autoregressive image generators, trained across complete visual-token trajectories.
042026
Token by Token
Backdoor attacks that use ordinary text triggers to jointly manipulate image and language generation in unified autoregressive models.