Abstract: Vision-language models (VLMs), such as CLIP, have gained significant popularity as foundation models, with numerous fine-tuning methods developed to enhance performance on downstream tasks.
The stripes are reminiscent of the “dazzle camouflage” used by the Royal Navy in the first world war. But whereas dazzle ...
In the brief history of AI security, the prompt injection has quickly become the top threat. Large language models are ...
Abstract: In the realm of large vision language models (LVLMs), jailbreak attacks serve as a red-teaming approach to bypass guardrails and uncover safety implications. Existing jailbreaks ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results