""If unaccounted for, those vulnerabilities can continue to propagate, whether they affect an internal chatbot, an agent application, or a customer-facing tool.""
""The vulnerabilities are inherited and would persist in generative and agentic applications. Without provenance, organizations have no easy way to trace an incident back to its root cause, and no way to determine which other models in their stack are also affected.""
Cisco introduced the Model Provenance Kit, an open-source tool aimed at helping organizations manage risks linked to third-party AI models. Many organizations utilize AI models from repositories like HuggingFace but often fail to track modifications. The lack of verified claims regarding model sources, vulnerabilities, and biases can lead to security and compliance issues. Without proper provenance, organizations struggle to trace incidents back to their origins, complicating response efforts and increasing regulatory risks.
Read at SecurityWeek
Unable to calculate read time
Collection
[
|
...
]