Popular repositories Loading

1. Imperio Imperio Public

   [IJCAI 2024] Imperio is an LLM-powered backdoor attack. It allows the adversary to issue language-guided instructions to control the victim model's prediction for arbitrary targets.

   Python 42 4

2. Geminio Geminio Public

   Geminio is a VLM-powered gradient inversion attack in federated learning (FL). It allows the adversary (the FL server) to describe the data of value and reconstruct the victim client's private data…

   Python 5

3. AnywhereDoor AnywhereDoor Public

   AnywhereDoor is a multi-target backdoor attack tailored for object detection. Once implanted, it enables adversaries to specify different attack types (object vanishing, fabrication, or misclassifi…

   Jupyter Notebook 2

4. Sanitizer Sanitizer Public

   Sanitizer is a server-side method that ensures client-embedded backdoors can only be used for contribution demonstration in federated learning but not be triggered on natural queries in harmful ways.

   Python 2