Introduction: The Rise of Local AI
Skyld safeguards your AI models from reverse-engineering.
Comprehensive Protection: Our SDK safeguards your AI models both at rest and during execution and provides protection against both static and dynamic reverse-engineering. Focus on innovation, your competitive edge is secure.
We protect your on-device AI models deployed on smartphones, connected objects, desktops, web browsers, on-premise servers. If you can deploy a model, we can protect it.
In less than 10 lines of code, our SDK turns a trained model into a protected model. The format of the model is not modified, so that you can use your favorite ML inference framework.
Your AI model is likely to be extracted whenever it is deployed on untrusted environnements: on the Edge, on IoT devices, on Smartphones and tablets, on desktop applications, on browsers and on-premises servers. It is also possible for the cloud provider to access the model.
Yes, it’s relatively easy to extract an on device AI model if security measures are not sufficiently robust. Through decompilation, an attacker can locate and extract the AI model. Even if the model is encrypted, it can be recovered with dynamic analysis: an attacker just needs to wait for the decryption before inference.
The most direct consequence is the theft of intellectual property. If an AI model is successfully reverse-engineered, it can be reused directly, or fine-tuned to fit the attacker purpose. Furthermore, access to the AI model facilitates more advanced attacks such as adversarial examples and model inversion. You can learn more about model inversion attack by reading this article.
Encryption is easy to deploy but is also easy to bypass. Indeed, even if the model is encrypted when it’s stored, it may still be vulnerable to runtime attack as it must be decrypted for inference. An attacker can stop the application execution at the decryption step and recover the entire model.
Skyld protects AI models everywhere they are executed. Our developed techniques prevent the software analysis and relevant AI attacks from getting models key information, especially the weights. We apply robust linear algebra transformations, so that the explicit parameter information cannot be extracted from the on-device AI model file. These transformations ensure that models are protected during runtime even on GPUs.
As OS: Android, Linux, Windows and as ML inference frameworks: ONNX, Tensorflow(lite), Keras.
Skyld protects different kinds of neural networks : CNN, RNN, LSTM, Transformers and Vision Transformers, LLM. To request the list of all the tested models, please contact us.
Our protection has no impact on model accuracy. As for performance, this depends on the specific architecture of the model used, generally below 20% overhead. Contact us us for your specific use case.
Introduction: The Rise of Local AI
Artificial intelligence is used in many fields, including autonomous cars and facial recognition. Every AI application has a carefully designed...
First Type Of Machine Learning Models: Supervised
The world of Android applications is constantly evolving, offering a myriad of features to users worldwide. However, this diversity and...
Artificial Intelligence (AI) and Machine Learning (ML) have rapidly evolved to become essential components of many applications we use daily....
What is a model and why do we care? Machine learning models are the results of highly complex computations and...
Have you ever wondered if your machine learning models are vulnerable to attacks that can extract sensitive information, revealing the...
On-Device Artificial Intelligence (AI) is an invaluable asset to many industries, offering revolutionary capabilities in analysis and prediction. However, with...
After working at xBrain, Thibault Maho started a Ph.D. whose title you may not understand: « Input Space Exploration for...
VivaTech opened its doors on Wednesday, May 22, 2024, and ran until May 25. This 8th edition brought together technology...
The Thales Cyber@Station F acceleration program is a great opportunity for Sklyd to benefit from Thales’ expertise and ecosystem.
We are excited to announce that we have been accepted into NVIDIA’s Inception Program, which supports start-ups in AI and...
Skyld is proud to be listed on the Wavestone radar of French cybersecurity start-ups 2024 in the Artificial Intelligence category....
A few weeks ago, the Skyld team had the exceptional opportunity to participate in the World Artificial Intelligence Cannes Festival...
Every year, this prestigious event highlights exceptional businesses, emphasizing their achievements in crucial areas such as societal engagement, innovation, responsible...
The Halle de la Brasserie in Rennes was the stage for an event, the Creators' Morning, bringing together nearly 250...
What an exciting adventure Skyld embarked on by participating in the finals of the European Cyber Security Organisation (ECSO) Startup...