A policy stating “protect sensitive data” still requires developers to determine what information an AI assistant can access. A “high-risk” designation for a use case does not inform your SOC about ...

The public release of ChatGPT marked a significant milestone in AI, paving the way for a wide range of consumer and enterprise applications. Today, many organizations are looking to integrate LLMs, ...

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 ...

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 ...

When it comes to GenAI, the security of the AI models themselves is at risk as ‘data poisoning’ is increasingly taking aim at the training data that large language models rely on to generate responses ...

The ongoing use of AI and machine learning -- combined with the explosion in interest in generative AI tools, such as ChatGPT -- has led to inevitable questions about new cybersecurity risks they pose ...

The security community's best framework for AI application risk just got smarter — and the data it now incorporates is proving that security professionals' intuitions about AI threats are off in at ...

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 ...

While IBM reports the average breach now costs $4.4 million, the FBI's IC3 documented over $16.6 billion in total cybercrime losses in 2024 alone, a 33% year-over-year increase. Nearly every security ...