Typically, network on chips (NoC) have many internal resources that are shared between packets from different trust domains. These resources include internal buffers, crossbars and switches, individual ports, and channels. The sharing of resources causes contention and introduces interference between differently trusted domains, which poses a security threat via a timing channel, allowing attackers to infer data that belongs to a trusted agent. This may also result in introducing network interference, resulting in degraded throughput and latency.
"Network-on-chip" (NoC) is a commonly-used term used for hardware interconnect fabrics used by multicore Systems-on-Chip (SoC). Communication between modules on the chip uses packet-based methods, with improved efficiency and scalability compared to bus architectures [REF-1241].
Scope | Impact | Likelihood |
---|---|---|
Confidentiality Availability | DoS: Resource Consumption (Other), Varies by Context, Other Note: Attackers may infer data that belongs to a trusted agent. The methods used to perform this attack may result in noticeably increased resource consumption. | Medium |
References | Description |
---|---|
CVE-2021-33096 | Improper isolation of shared resource in a network-on-chip leads to denial of service |
CAPEC-ID | Attack Pattern Name |
---|---|
CAPEC-124 | Shared Resource Manipulation An adversary exploits a resource shared between multiple applications, an application pool or hardware pin multiplexing to affect behavior. Resources may be shared between multiple applications or between multiple threads of a single application. Resource sharing is usually accomplished through mutual access to a single memory location or multiplexed hardware pins. If an adversary can manipulate this shared resource (usually by co-opting one of the applications or threads) the other applications or threads using the shared resource will often continue to trust the validity of the compromised shared resource and use it in their calculations. This can result in invalid trust assumptions, corruption of additional data through the normal operations of the other users of the shared resource, or even cause a crash or compromise of the sharing applications. |
Name | Organization | Date | Date release | Version |
---|---|---|---|---|
Arun Kanuparthi, Hareesh Khattri, Parbati K. Manna | Intel Corporation | 4.3 |
Name | Organization | Date | Comment |
---|---|---|---|
CWE Content Team | MITRE | updated Background_Details, Demonstrative_Examples, Description, Detection_Factors, Name, References, Relationships, Weakness_Ordinalities | |
CWE Content Team | MITRE | updated Applicable_Platforms, References | |
CWE Content Team | MITRE | updated Applicable_Platforms | |
CWE Content Team | MITRE | updated Relationships | |
CWE Content Team | MITRE | updated Mapping_Notes | |
CWE Content Team | MITRE | updated Observed_Examples |