Remote Code Execution (RCE) exploits pose a significant threat to AI and ML systems, particularly in GPU-accelerated environments where the computational power of GPUs can be misused for malicious purposes. This paper focuses on RCE attacks leveraging deserialization vulnerabilities and custom layers, such as TensorFlow Lambda layers, which are often overlooked due to the complexity of monitoring GPU workloads. These vulnerabilities enable attackers to execute arbitrary code, blending malicious activity seamlessly into expected model behavior and exploiting GPUs for unauthorized tasks such as cryptocurrency mining. Unlike traditional CPU-based attacks, the parallel processing nature of GPUs and their high resource utilization make runtime detection exceptionally challenging. In this work, we provide a comprehensive examination of RCE exploits targeting GPUs, demonstrating an attack that utilizes these vulnerabilities to deploy a crypto miner on a GPU. We highlight the technical intricacies of such attacks, emphasize their potential for significant financial and computational costs, and propose strategies for mitigation. By shedding light on this underexplored attack vector, we aim to raise awareness and encourage the adoption of robust security measures in GPU-driven AI and ML systems, with an emphasis on static and model scanning as an easier way to detect exploits.

The DeepLearning.AI TensorFlow: Advanced Techniques Specialization introduces the features of TensorFlow that provide learners with more control over their model architecture and tools that help them create and train advanced ML models. This Specialization is for early and mid-career software and machine learning engineers with a foundational understanding of TensorFlow who are looking to expand their knowledge and skill set by learning advanced TensorFlow features to build powerful models.

"Neural networks are computing systems with interconnected nodes that work much like neurons in the human brain." Neural networks are nodes in a densely packed system that takes input numbers and outputs more numbers. If we look closely at a dense neural network, we can find neurons connected, like the image below. If we further zoom in, we can see precisely what each neuron does. For example, a neuron can be seen as a box that eats a number and throws another computer number as output.

Keras is a very powerful open source Python library which runs on top of top of other open source machine libraries like TensorFlow, Theano etc, used for developing and evaluating deep learning models and leverages various optimization techniques. There are many in-built layers in Keras like Conv2D, MaxPooling2D, Dense, Flatten etc for different use cases and applications. In this project we are going to create custom(Parametric ReLU) layer and use it in the NN model to solve a multi classification problem (We will be using MNIST dataset) . We will be using the popular MNIST dataset. We will load the data using utils and then visualize it.

Deep Learning is part of the Machine Learning family that deals with creating the Artificial Neural Network (ANN) based models. ANNs are used for both supervised as well as unsupervised learning tasks. Deep Learning is extensively used in tasks like-object detection, language translations, speech recognition, face detection, and recognition..etc. Let's create our First Neural Network with PyTorch- In this article, I am going to explain how to create a simple Neural Network (deep learning model) using the PyTorch framework from scratch. If you are not familiar with PyTorch, you can read my article here that throws light on fundamentals building blocks of PyTorch.

Neural network architectures are most often conceptually designed and described in visual terms, but are implemented by writing error-prone code. PrototypeML is a machine learning development environment that bridges the dichotomy between the design and development processes: it provides a highly intuitive visual neural network design interface that supports (yet abstracts) the full capabilities of the PyTorch deep learning framework, reduces model design and development time, makes debugging easier, and automates many framework and code writing idiosyncrasies. In this paper, we detail the deep learning development deficiencies that drove the implementation of PrototypeML, and propose a hybrid approach to resolve these issues without limiting network expressiveness or reducing code quality. We demonstrate the real-world benefits of a visual approach to neural network design for research, industry and teaching.

In this article, we'll see 10 important updates from TensorFlow 2.0. TensorFlow 2.0 will be simple and easy to use for all users on all platforms. In this article, we'll see 10 important updates from TensorFlow 2.0. TensorFlow 2.0 will be simple and easy to use for all users on all platforms. TensorFlow 2.0 alpha has now been released.

In this post we explain the basic concept and general usage of RoI (Region of Interest) pooling and provide an implementation using Keras layers and the TensorFlow backend. The intended audience for this post are people familiar with the basic theory of (Convolutional) Neural Networks and who are capable of building and running simple models using Keras. If you are here just for the code, serve yourself from this gist and do not forget to like and share the article! RoI Pooling was proposed by Ross Girshick in the Fast R-CNN paper as part of his object recognition pipeline. In the general use case for RoI Pooling we have an image-like object, and multiple regions of interest specified via bounding boxes.