The probability is the direct output of the EPSS model, and conveys an overall sense of the threat of exploitation in the wild. The percentile measures the EPSS probability relative to all known EPSS scores. Note: This data is updated daily, relying on the latest available EPSS model version. Check out the EPSS documentation for more details.
In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.
Test your applicationsUpgrade triton-inference-server/server to version 2.58.0 or higher.
Affected versions of this package are vulnerable to Integer Underflow (Wrap or Wraparound) via the ShapeTensor::SetDataFromBuffer in the Tensor RT backend. An attacker could cause a denial of service by providing a specific model configuration and a specially crafted input.
Note: This vulnerability is only exploitable when using the default bundled Tensor RT backend /pytriton/tritonserver/backends/tensorry/libtriton_tensorrt.so.
It is possible to update the Tensor RT backend to a patched version independently of the Triton Server; See Triton Inference Server Backend.