Writing
2025
Weak-to-Strong Exploitation: Weak LLMs Orchestrating Aligned Models Toward Harmful Goals
Weak LLMs as malicious orchestrators: a threat model, three mechanisms, causal evaluation, and future research on RL.
2024
Stable Signer: Balancing Three Stakeholders’ Interests in Image Provenance
A message can change a generative model's decoder. The harder question is who chooses the change, who can read it, and who gets to make a claim from it.