Yusheng Zheng

ACRFence introduces a framework-agnostic mitigation to prevent semantic rollback attacks in LLM agents by recording irreversible tool effects and enforcing strict replay-or-fork semantics upon checkpoint restoration.

Sandlock is a lightweight, unprivileged Linux process sandbox that enforces fine-grained policies over filesystem, network, and syscalls for running untrusted AI agent code, achieving strong isolation without requiring root privileges or complex virtualization.