Hanxun Huang

Adversarial techniques traditionally seen as threats are now being repurposed by content owners to proactively safeguard their visual assets from misuse.

Adversarial examples in vision-language models can be detected by their tendency to stray further from the data manifold, revealing a critical vulnerability in multimodal AI systems.

Frontier LLMs may appear safe, but they produce harmful content at scale, with risks growing as model capabilities increase.