92 citations · 119 across the 9 of their papers we have counts for
7 papers · 1 filter
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…
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…
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…
Disarming Steganography Attacks Inside Neural Network Models
Ran Dubin
Similar to the revolution of open source code sharing, Artificial Intelligence (AI) model sharing is gaining increased popularity. However, the fast adaptation in the industry, lac…
Open Image Content Disarm And Reconstruction
Eli Belkind, Ran Dubin, Amit Dvir
With the advance in malware technology, attackers create new ways to hide their malicious code from antivirus services. One way to obfuscate an attack is to use common files as cov…
Robust Machine Learning for Encrypted Traffic Classification
Amit Dvir, Yehonatan Zion, Jonathan Muehlstein +3
Desktops and laptops can be maliciously exploited to violate privacy. In this paper, we consider the daily battle between the passive attacker who is targeting a specific user agai…