Nine months ago, we introduced the Integrated AI Safety and Security Framework as a unified and comprehensive taxonomy to help organizations identify and mitigate the security and safety risks unique to AI systems. Existing frameworks remained.....
Open source AI has never been more accessible. The rapidly growing scale and diversity of AI models available to developers worldwide is unprecedented. The harder question begins after download: when you bring a model into your environment, what....
This post is Part 2 of a two-part series on multimodal typographic attacks. In Part 1 of “Reading Between the Pixels,” we demonstrated that text–image embedding distance correlates with typographic prompt injection success: conditions that push....
When it comes to AI models, one of the hardest questions to answer is deceptively simple: where did this model actually come from? We addressed part of this problem with Model Provenance Kit, an open-source tool that fingerprints models at the.....
The importance of understanding a model’s origins has been a frequent topic of discussion among researchers and industry experts, and our own AI research confirms that AI supply chain security remains a weak link. Tracking where models come from....
A model context protocol (MCP) tool can claim to execute a benign task such as “validate email addresses,” but if the tool is compromised, it can be redirected to fulfill ulterior motives, such as exfiltrating your entire address book to an external server. Traditional security scanners could flag suspicious network calls or dangerous functions and […]
The Rise of Agent Networks: A New Security Frontier Emerging Agent-to-Agent (A2A) frameworks have emerged to support organizations as they move from isolated AI applications to interconnected networks of autonomous agents. A2A enables software agents to discover, authenticate, and collaborate across organizational boundaries, unlocks unprecedented automation capabilities. A2A also introduces an expanded attack surface, and […]
