Rethinking Latency Denial-of-Service: Attacking the LLM Serving Framework, Not the Model

Name: Rethinking Latency Denial-of-Service: Attacking the LLM Serving Framework, Not the Model
Uploaded: 2026-10-10T17:25:43.032390+00:00
Duration: 298 s
Description: The research shifts latency denial-of-service attacks from targeting individual LLM models to exploiting system-level scheduler behaviors. By manipulating memory resources through a 'Fill and Squeeze' strategy, attackers can induce pathological behaviors like Head-of-Line blocking or expensive preemption, effectively slowing down co-located users with significantly lower operational costs.

The research shifts latency denial-of-service attacks from targeting individual LLM models to exploiting system-level scheduler behaviors. By manipulating memory resources through a 'Fill and Squeeze' strategy, attackers can induce pathological behaviors like Head-of-Line blocking or expensive preemption, effectively slowing down co-located users with significantly lower operational costs.

Open the full episode