Unlike traditional cyberattacks that exploit software vulnerabilities, prompt injection targets an AI model's ability to ...

A team of security researchers chained two vulnerabilities in LiteLLM, the popular open-source proxy that routes enterprise ...

Technical report identifies Gate AI as one of the top performing AI security gateways across 16 public prompt injection ...

Shadow AI introduces new pathways for data leakage, policy failure, and adversary access beyond the scope of traditional security.

Ubiquiti released a new security bulletin detailing fixes for six security issues, including one rated 9.1 (critical) and one scoring a perfect 10.0 on the CVE risk scale. The vulnerabilities ...

Opus 4.8 shows a growing tendency to reason explicitly about how its outputs will be graded, including in environments where it wasn't told it was being evaluated.

The incident underscores rising risks at the intersection of artificial intelligence and automated financial systems, especially when bots are granted direct access to digital wallets.

Exhaustive proofs are the only way to find deep corner-case bugs that can result in deadlocks and silent data corruption.

"Prompt injection" on AI platforms is the new frontier of social engineering, writes ANNA COLLARD, SVP of content strategy and CISO advisor at KnowBe4 Africa. The post Beware the poisoned prompt ...

Here are some security and privacy protections that e-commerce companies can establish, maintain, and enforce.

A new study finds that prior authorization requirements vary widely across major insurers and suggests large language models ...