CAT trains watermark detectors against adaptive compositional adversaries using differentiable attack selection, yielding up to 63.5% capacity gains on hard attacks versus random-augmentation baselines.
arXiv preprint arXiv:1912.11188 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
unclear 1representative citing papers
SmoothLLM mitigates jailbreaking attacks on LLMs by randomly perturbing multiple copies of a prompt at the character level and aggregating the outputs to detect adversarial inputs.
citing papers explorer
-
Compositional Adversarial Training for Robust Visual Watermarking
CAT trains watermark detectors against adaptive compositional adversaries using differentiable attack selection, yielding up to 63.5% capacity gains on hard attacks versus random-augmentation baselines.
-
SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
SmoothLLM mitigates jailbreaking attacks on LLMs by randomly perturbing multiple copies of a prompt at the character level and aggregating the outputs to detect adversarial inputs.