Wenbo Jiang

By enforcing graph isomorphism across counterfactual inputs, UGID reveals that debiasing LLMs can be achieved by directly manipulating internal representations and attention mechanisms.

Worried about compromised cloud environments skewing your endpoint auditing? vCause offers a verifiable causality analysis system with negligible overhead.

Backdoor attacks can now hide in plain sight: by delaying activation, common words become viable triggers, opening a new, stealthier attack surface in pre-trained models.