InfoQ Homepage Adversarial Machine Learning Content on InfoQ
Articles
RSS Feed-
/articles/security-ai-threat-evolution/en/smallimage/security-ai-threat-evolution-thumbnail-1782202845102.jpg)
Virtual panel: Security in the Machine Age: Expert Insights on AI Threat Evolution
This virtual panel brings together AI security experts to examine the evolution of AI-driven threats, from prompt injection and data poisoning to agent abuse and AI-powered social engineering. The discussion explores emerging attack patterns, incident response challenges, and the changes security teams must make as AI systems become more autonomous and integrated into critical workflows.
-
/articles/understanding-ml-model-poisoning/en/smallimage/thumbnail-understanding-ml-model-poisoning-1781597719188.jpg)
Understanding ML Model Poisoning: How it Happens and How to Detect it
In this article, the author explores data poisoning as a threat to machine learning systems, covering techniques such as label flipping, backdoors, clean-label poisoning, and gradient manipulation. The article reviews real-world incidents, discusses the challenges of detecting poisoned data, and presents practical defenses, tools, and operational practices for securing ML training pipelines.
-
/articles/privacy-attacks-machine-learning-models/en/smallimage/privacy-attacks-machine-learning-models-S-1564820511524.jpeg)
Privacy Attacks on Machine Learning Models
Research has shown that machine learning models can expose personal information present in their training data. This vulnerability exposes sensitive user information to attackers savvy enough to learn how to hack a machine learning API. We'll explore the details of several privacy attacks against machine learning models and provide some potential solutions for this growing security issue.
-
/articles/introduction-machine-learning/en/smallimage/series-logo-small.jpg)
Article Series: An Introduction to Machine Learning for Software Developers
Get an introduction to some powerful but generally applicable techniques in machine learning for software developers. These include deep learning but also more traditional methods that are often all the modern business needs. After reading the articles in the series, you should have the knowledge necessary to embark on concrete machine learning experiments in a variety of areas on your own.