Skip to content
#

deep-learning-security

Star

Here are 9 public repositories matching this topic...

Language: All
Filter by language
All 9 Python 7 Jupyter Notebook 2

um-dsp / PoisonSpot

Star 0

Inspired by dynamic taint tracking, PoisonSpot uses fine-grained training provenance tracker that: (1) tags & traces the impact of every single training sample on model updates, (2) probabilistically scores suspect samples based on their linage of impact on model weights, and (3) separates the clean from the poisonous before retraining a model.

adversarial-machine-learning machine-learning-security backdoor-attacks poisoning-attack aisec deep-learning-security backdoor-defense provenance-tracking backdoor-detection poisoning-defenses training-provenance-tracking
  • Updated Jul 19, 2025
  • Python

CartwheelX / fist_tdsc

Star 0

Implementation of FiST — a black-box membership inference attack framework that selectively perturbs only those non-members closely resembling members (based on cosine similarity and entropy). By amplifying subtle membership signals, FiST achieves high accuracy even against well-generalized and DP-trained models.

pytorch differential-privacy adversarial-attacks membership-inference-attack deep-learning-security
  • Updated Aug 11, 2025
  • Python

Improve this page

Add a description, image, and links to the deep-learning-security topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the deep-learning-security topic, visit your repo's landing page and select "manage topics."

Learn more