PyTorch Model Server Registration / Deserialization Remote Code Execution

The PyTorch model server contains multiple vulnerabilities that can be chained together to permit an unauthenticated remote attacker arbitrary Java code execution. The first vulnerability is that the management interface is bound to all IP addresses and not just the loop back interface as the documentation suggests. The second vulnerability (CVE-2023-43654) allows attackers with access to the management interface to register MAR model files from arbitrary servers. The third vulnerability is that when an MAR file is loaded, it can …

addresses attacker back code code execution cve deserialization documentation interface ip addresses java loop management pytorch registration remote code remote code execution server unauthenticated vulnerabilities vulnerability