TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic Via Asymmetric Contrastive Learning

Decompositional jailbreaks pose a critical threat to large language models LLMs by allowing adversaries to fragment a malicious objective into a sequence of individually benign queries that collectively reconstruct prohibited content. In real-world deployments, LLMs face a continuous, untraceable...