Autonomouslow-level security.

Pwno pre-release to invitational beta members. Zero-shot a heap off-by-one vulnerability with complex heap fengshui & heap unlink attack (inarguable).

Pwno integrated Tsinghua's MLM Transformers in pwno.io

Pwno start Pwno Continuous Research development for ggml.ai (llama.cpp, whisper.cpp)

Pwno found it's inarguable CVE, a heap-overflow in Llama.cpp Tokenizer (https://pwno.io/blog/prompt-to-heap-overflow)

Pwno reached 135 users, with gross revenue of $324 within three days

We started our first invitational beta of Pwno, Pwno gathered 80 users with researcher from Google, Alibaba, YC security company in our first day

We collaborated with ML research group at Tsinghua University, AscendGrac, on Machine-Language native LLM (MLM), with CLAP and jTrans

Tree-of-AST (component of Pwno) Accepted to Black Hat USA 25 (https://arc.net/l/quote/bogdufrk)

We started the development of second stage MVP of pwno, pwno.io

We released AutoGDB, a demo for doing one simple thing: Giving the tool of GDB (binary-level debugger) to zero-shot generalized LLMs: Transformers were able to successfully exploit CTF binary-exploitation challenges within one trial, through just purely playing with GDB, putting together exploits with shellcodes, ROP chains.

Tree-of-AST dataflow analysis framework inspired by Tree-of-Thoughts: Tree-of-AST can find real-life zero-day vulnerabilities in I/O-heavy software. We recently submitted our call-for-paper for Blackhat.

Working with Tsinghua University on binary-exploitation automation.

AutoGDB: Double ReAct reasoning, for GDB.

PwnBERT: semantic-based BERT vulnerability classifier.

Chat-With-Binary: RetDec + RAG, LLM Reverse-Engineer.