Artificial Intelligence

Category Added in a WPeMatico Campaign

A Coding Guide to Demonstrate Targeted Data Poisoning Attacks in Deep Learning by Label Flipping on CIFAR-10 with PyTorch

ai, AI (Artificial Intelligence), Artificial Intelligence, deep learning, Editors Pick, Security, Technology, Tutorials

In this tutorial, we demonstrate a realistic data poisoning attack by manipulating labels in the CIFAR-10 dataset and observing its impact on model behavior. We construct a clean and a poisoned training pipeline side by side, using a ResNet-style convolutional network to ensure stable, comparable learning dynamics. By selectively flipping a fraction of samples from

A Coding Guide to Demonstrate Targeted Data Poisoning Attacks in Deep Learning by Label Flipping on CIFAR-10 with PyTorch Read More »

Meet SETA: Open Source Training Reinforcement Learning Environments for Terminal Agents with 400 Tasks and CAMEL Toolkit

agentic ai, ai, AI (Artificial Intelligence), AI Agents, Artificial Intelligence, Editors Pick, New Releases, Open Source, Staff, Technology

What does an end to end stack for terminal agents look like when you combine structured toolkits, synthetic RL environments, and benchmark aligned evaluation? A team of researchers from CAMEL AI, Eigent AI and other collaborators have released SETA, a toolkit and environment stack that focuses on reinforcement learning for terminal agents. The project targets

Meet SETA: Open Source Training Reinforcement Learning Environments for Terminal Agents with 400 Tasks and CAMEL Toolkit Read More »