Developing a Risk Identification Framework for Foundation Model Uses

As foundation models grow in both popularity and capability, researchers have uncovered a variety of ways that the models can pose a risk to the model's owner, user, or others. Despite the efforts of measuring these risks via benchmarks and cataloging them in AI risk taxonomies, there is little...

CVE-2024-43485

A flaw was found in dotnet. In System.Text.Json, applications that deserialize input to a model with an ExtensionData property can be vulnerable to an algorithmic complexity attack, resulting in a denial of service. Mitigation Red Hat has investigated whether a possible mitigation exists for this...

CVE-2020-8616

A flaw was found in BIND, where it does not sufficiently limit the number of fetches that can be performed while processing a referral response. This flaw allows an attacker to cause a denial of service attack. The attacker can also exploit this behavior to use the recursing server as a reflector...