Autonomous Infrastructure Economics: Algorithmic FinOps, Compute Optimization, and Mitigating LLMJacking

As enterprises operationalize generative AI and autonomous agentic workflows, compute expenditure has evolved from an accounting metric into an active security and reliability boundary. Building upon research presented in Observability for Large Language Models (Apress / Springer Nature) and patented methodologies in compute optimization and hallucination detection, this session provides an architectural deep dive into the dual imperatives of GenAI FinOps and compute protection.
The talk deconstructs the emerging threat landscape of LLMJacking and Denial-of-Wallet (DoW) attacks—where compromised credentials and unconstrained agent loops are exploited by threat actors to divert enterprise LLM capacity to unauthorized workloads. We examine:
– Algorithmic Cost Reduction: Implementing tiered routing frameworks between Small Language Models (SLMs) and frontier models, semantic caching layers, and vector search pruning to reduce redundant token overhead by up to 60%.
– Zero-Standing Quotas & Cryptographic Identity: Applying SPIFFE/SPIRE-based short-lived workload attestation to model inference endpoints, preventing compromised API keys from allowing unbounded cloud spend.
– Automated Circuit Breakers: Establishing sub-minute anomaly tripwires to isolate rogue recursive agent loops and anomalous token velocities in production.
– Return on Autonomy (RoA) Modeling: Translating raw token consumption into boardroom-defensible metrics that balance MTTR reduction against compute overhead.
Key Attendee Takeaways
– Threat Mitigation Blueprint: Actionable telemetry patterns to identify and neutralize LLMJacking attempts before enterprise token quotas are exhausted.
– Production FinOps Patterns: Architectural designs for context-window compression and dynamic inference routing that immediately decrease operational cloud spend.
– Executive Governance Framework: Clear policies for chargebacks, environment-scoped spend tripwires, and engineering-versus-token ROI trade-offs.
Speaker(s): Ankush Sharma,
Room: 108, Bldg: Alameda Hall, Santa Clara University, Santa Clara, California, United States, Virtual: https://events.vtools.ieee.org/m/585464