Data poisoning is a type of cyberattack in which a bad actor intentionally compromises a training dataset used by an AI model by introducing malicious or corrupted data. The goal is to manipulate the ...

Nathan Eddy works as an independent filmmaker and journalist based in Berlin, specializing in architecture, business technology and healthcare IT. He is a graduate of Northwestern University’s Medill ...

Hackers sabotage hospital systems that use artificial intelligence (AI) to analyze medical images, which causes doctors to misdiagnose diseases. Attackers compromise a large retailer's chatbots and ...

Data poisoning presents an imposing cyberthreat to artificial intelligence amid agencies’ digital transformations because it’s designed to be subtle. Unlike traditional cyberattacks that focus on ...

Machine learning and artificial intelligence are making their way to the public sector, whether agencies are ready or not. Generative AI made waves last year with ChatGPT boasting the fastest-growing ...

The IT community is freaking out about AI data poisoning. For some, it’s a sneaky backdoor into enterprise systems as it surreptitiously infects the data LLM systems train on — which then get sucked ...

It’s not hard to tell that the image below shows three different things: a bird, a dog, and a horse. But to a machine learning algorithm, all three might the same thing: a small white box with a black ...

Imagine a busy train station. Cameras monitor everything, from how clean the platforms are to whether a docking bay is empty or occupied. These cameras feed into an AI system that helps manage station ...

Agentic AI is being adopted fast by enterprises, propelled by an explosion of use cases, but security, as always, is lagging. The OWASP Top 10 for Agentic AI can help close that gap. LLM-powered ...

Prompt injection and data leakage are among the top threats posed by LLMs, but they can be mitigated using existing security logging technologies. Splunk’s SURGe team has assured Australian ...