Blog

Anthropic just published a new jailbreaking vulnerability where an attacker can override the safety training of an LLM by ‘overloading’ it with fake dialogues.

Prompt Security's use of eBPF brings a new paradigm for application security as it offers unprecedented visibility and control at the kernel level

The European Parliament approved the EU Act, the first regulation on AI. This new regulatory framework establishes risk levels and obligations for AI systems

Insights from Danny Portman, PhD Head of Generative AI, VP Data Science at Zeta Global on Generative AI, building customer-facing apps and its security implications

I couldn’t be prouder to announce that we have emerged from stealth mode to be the one-stop for all Generative AI security needs of an enterprise.

Prompt injection is any prompt where attackers manipulate a large language model (LLM) through carefully crafted inputs to behave outside of its desired behavior.

Denial of Wallet (DoW) attacks aim to damage the company or to gain unauthorized free access to Large Language Models (LLMs).

What is GenAI Security, what are the risks associated with GenAI and how can organizations protect themselves from prompt injection, data leaks, shadow AI, etc.

Prompt Security's CEO & Co-founder Itamar Golan gives his take on what are the top 5 predictions for 2024 on AI & Security.

What's the risk of your employees or applications accidentally disclosing sensitive data to GenAI tools like ChatGPT, Bard, Jasper, Bing, etc.?

The adoption of Generative AI has been unlike anything we've seen before, and it's here to stay. Here are some insights around its adoption.

How can organizations securely embrace Generative AI without exposing itself to a brand new attack surface? Prompt Security shares strategies to minimize risk