We have 3 of 21 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
A key observation is that reference models serve only to reveal how an example behaves under models not trained on it, and that querying the target model on nearby samples yields the same information, and that querying the target model on nearby samples yields the same information.
This paper studies the role played by the adversarial data's input modality, and identifies a systematic asymmetry: multimodal LLMs are more likely to follow adversarial instruction when they appear as text than when the same instruction is delivered through a non-textual channel.
Text-to-image (T2I) models can be exploited to produce unsafe images. Existing safety measures, e.g., content moderation or model alignment, can be weakened by adversaries who attempt to restore unsafe generation through model fine-tuning. This paper presents Patronus, a defensive framework that improves T2I models’ re...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
