You should think twice before trusting your AI assistant, as database poisoning can markedly alter its output – dangerously ...

Large-scale attacks on health providers expose the data of millions of Americans each year. Consumers must remain vigilant, ...

Lazarus was seen poisoning open source software with infostealers The campaign is dubbed Phantom Circuit, and targets mostly European software devs Multiple repositories were found poisoned with ...

Tarpits were originally designed to waste spammers' time and resources, but creators like Aaron have now evolved the tactic ...

Cisco's AI Defense offers security teams AI visibility, access control and threat protection for AI security threats.

[Related: The AI Danger Zone: ‘Data Poisoning’ Targets LLMs] Notably, given that the Change Healthcare incident was just one of the many attacks to disrupt health care and other critical ...

A team of security researchers has disclosed new side-channel vulnerabilities in modern Apple processors that could steal ...

Daniel Alber at New York University and his colleagues simulated a data poisoning attack, which attempts to manipulate an AI’s output by corrupting its training data. First, they used an OpenAI ...

The ransomware attack last year against UnitedHealth Group subsidiary Change Healthcare exposed data of more than 190 million ...

While the paper is focused on the intentional "poisoning" of an LLM during training, it also has implications for the body of ...