8 citations · 8 across the 5 of their papers we have counts for
6 papers
When Rotation Bounds Nothing: Streaming Image Classifiers to Field Nodes Under Physical Capture
Daniel Gilkarov, Ran Dubin
Field nodes run image classifiers locally, exposing a first-class asset, the trained model, to theft. Trusted-execution enclaves, collaborative-inference splits, and encrypted stor…
SafePickle: Robust and Generic ML Detection of Malicious Pickle-based ML Models
Hillel Ohayon, Daniel Gilkarov, Ran Dubin
Model repositories such as Hugging Face increasingly distribute machine learning artifacts serialized with Python's pickle format, exposing users to remote code execution (RCE) ris…
NeuPerm: Disrupting Malware Hidden in Neural Network Parameters by Leveraging Permutation Symmetry
Daniel Gilkarov, Ran Dubin
Pretrained deep learning model sharing holds tremendous value for researchers and enterprises alike. It allows them to apply deep learning by fine-tuning models at a fraction of th…
Zero-Trust Artificial Intelligence Model Security Based on Moving Target Defense and Content Disarm and Reconstruction
Daniel Gilkarov, Ran Dubin
This paper examines the challenges in distributing AI models through model zoos and file transfer mechanisms. Despite advancements in security measures, vulnerabilities persist, ne…
Model X-Ray: Detection of Hidden Malware in AI Model Weights using Few Shot Learning
Daniel Gilkarov, Ran Dubin
The potential for exploitation of AI models has increased due to the rapid advancement of Artificial Intelligence (AI) and the widespread use of platforms like Model Zoo for sharin…
Steganalysis of AI Models LSB Attacks
Daniel Gilkarov, Ran Dubin
Artificial intelligence has made significant progress in the last decade, leading to a rise in the popularity of model sharing. The model zoo ecosystem, a repository of pre-trained…