From 1fe9099a30b58ec5ef309eda60bb146b90d6469a Mon Sep 17 00:00:00 2001 From: mldangelo Date: Tue, 9 Dec 2025 21:42:50 -0500 Subject: [PATCH] Add promptfoo modelaudit to model backdoors section Signed-off-by: mldangelo --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index 01f51d6..bce2631 100644 --- a/README.md +++ b/README.md @@ -155,6 +155,7 @@ Backdoors/neural trojans (same as for non-ML systems), adversarial evasion (pert ### Model backdoors * [Fickling](https://github.com/trailofbits/fickling): a decompiler, static analyzer, and bytecode rewriter for Python pickle files; injects backdoors into ML model files +* [promptfoo modelaudit](https://github.com/promptfoo/promptfoo): static security scanner for ML models; detects malicious code, unsafe operations, backdoors, and serialization attacks across PyTorch, TensorFlow, Keras, ONNX, and more * [Semgrep rules for ML](https://blog.trailofbits.com/2022/10/03/semgrep-maching-learning-static-analysis/) ### Other