Puzhuo Liu

Decompilers might produce readable code, but good luck getting it to actually *work* – a new benchmark reveals a massive gap between recompilability and functional correctness.

LLM agents are alarmingly susceptible to memory poisoning via conversational attacks, achieving 95% success rates even against agents with selective memory mechanisms.

The complex JS-Wasm boundary is fertile ground for new vulnerabilities, and Weaver is the first fuzzer to effectively till it.