ai_security▌

← feed

NOTABLE

Phrack 73: ONNX Runtime arbitrary-read flaw weaponized into a self-contained trigger-conditional LLM backdoor

Phrack 73 article by G. Cherubin (published Nov 17, surfaced on HN Nov 18; corrects sweep #20's blanket disposition of the remaining Phrack 73 papers): a parser flaw noticed in March 2026 lets a malicious ONNX model make ONNX Runtime read arbitrary file paths or memory addresses with no validation; the author built a trigger-word backdoored Qwen2 ONNX LLM that behaves normally until the trigger, then emits the leaked file/memory contents in its output — the entire attack lives in the .onnx file, no server or runtime change.

released 2026-11-17 · ingested 2026-11-19T01:10Z

Sources

Primary source

Cite this

APA

AI Security Index. (2026). Phrack 73: ONNX Runtime arbitrary-read flaw weaponized into a self-contained trigger-conditional LLM backdoor. AI Security Index. https://phrack.org/issues/73/backdoor-attacks-against-machine-learning-irl_md.html

BibTeX

@misc{aisec-2026-11-18-phrack73-onnx-runtime-backdoor,
  title  = {Phrack 73: ONNX Runtime arbitrary-read flaw weaponized into a self-contained trigger-conditional LLM backdoor},
  year   = {2026},
  howpublished = {\url{https://phrack.org/issues/73/backdoor-attacks-against-machine-learning-irl_md.html}},
  note   = {AI Security Index item 2026-11-18-phrack73-onnx-runtime-backdoor}
}