Skip to content
Threat Feed
Subscribe

Tag

Inference-Abuse

1 brief RSS
high advisory

Potential Cross-Region Inference Abuse in AWS Bedrock Claude

This threat brief details the potential for malicious actors to exploit AWS Bedrock Claude models by performing cross-region inference with high input token counts, indicating attempts to bypass regional restrictions, exfiltrate sensitive data, or conduct unauthorized actions across different AWS regions.

AWS Bedrock Claude cloud aws inference-abuse data-exfiltration defense-evasion
1r 3t