ai safety 1anti-edit defenses 1benchmarking 1diffusion models 1image editing protection 1joint attention 1
From the 1 of 6 linked papers with an AI index.
Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
Erased but Not Forgotten: How Backdoors Compromise Concept Erasure
Tobias Braun, Jonas Henry Grebe, Marcus Rohrbach +1
The expansion of text-to-image diffusion models has raised concerns about harmful outputs, from fabricated depictions of public figures to sexually explicit imagery. To mitigate su…
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…