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 ...

Back in 2016, an innocent AI chatbot joined Twitter, and we all got a lesson in the dark side of generative artificial intelligence. Named Tay by her creators at Microsoft, the chatbot was designed to ...

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 ...

Sensitive information disclosure via large language models (LLMs) and generative AI has become a more critical risk as AI adoption surges, according to the Open Worldwide Application Security Project ...

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 ...

Web applications often handle vast amounts of data, from personal user details to sensitive corporate information. As these applications grow in complexity and importance, they also become primary ...

As part of a sweeping revamp of its top 10 list, OWASP has created three new categories, which security teams need to consider when looking to protect against today’s most critical and severe ...