Tagged:

2 posts

• Sponge Examples: Energy and Latency Attacks on Neural Networks

  Adversarial inputs that don't fool a model's outputs — they exhaust its compute. Sponge examples maximize inference energy and latency, enabling DoS attacks that bypass rate limits, drain edge-device batteries, and degrade shared inference infrastructure. What they are, how they work, and how to defend against them.

  Jul 15, 2026 adversarial-examples denial-of-service inference-security agent-autonomy energy-attacks ml-security ai-security neural-networks

• Agent Loop Hijacking: How Resource Exhaustion and Infinite Reasoning Loops Become Attack Primitives

  Most agent security thinking focuses on what an agent does — exfiltration, injection, privilege escalation. Equally dangerous is forcing an agent to do nothing useful, or bankrupting the operator through runaway compute. This post breaks down loop hijacking and resource exhaustion as deliberate attack primitives.

  Jul 4, 2026 agent-security denial-of-service prompt-injection resource-exhaustion defense