Chaoyu Zhang

Intermediate activations in split LLM fine-tuning trivially leak raw training prompts past standard privacy defenses, but a learned obfuscation pipeline closes this leakage vector without destroying model utility.

A malicious parameter server can exploit parameter-efficient fine-tuning to implant a privacy backdoor that reconstructs training data with alarming accuracy.

ClawCoin offers a cryptocurrency directly indexed to AI compute costs, enabling agents to quote, escrow, and settle workflows in a unit aligned with their actual resource consumption.

Bridge the trust gap in cloud-based LLM services with AFTUNE, a practical framework that lets you audit proprietary fine-tuning and inference without prohibitive overhead.

LLMs generating optimization code can be silently wrong 77% of the time, but ReLoop's structured generation and behavioral verification can dramatically improve correctness without needing ground truth.