TensorCommitments: A Lightweight Verifiable Inference for Language Models
Most large language models (LLMs) run on external clouds: users send a prompt, pay for inference, and must trust that the remote GPU executes the LLM without any adversarial tampering. We critically ask how to achieve verifiable LLM inference, where a prover (the service) must convince a verifier (the client) that an inference was run correctly without rerunning the LLM. Existing cryptographic works are too slow at the LLM scale, while non-cryptographic ones require a strong verifier GPU. We propose TensorCommitments (TCs), a tensor-native proof-of-inference scheme. TC binds the LLM inference to a commitment, an irreversible tag that breaks under tampering, organized in our multivariate Terkle Trees. For LLaMA2, TC adds only 0.97% prover and 0.12% verifier time over inference while improving robustness to tailored LLM attacks by up to 48% over the best prior work requiring a verifier GPU.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
VeriLLM: A Lightweight Framework for Publicly Verifiable Decentralized Inference
Decentralized inference provides a scalable and resilient paradigm for serving large language models (LLMs), enabling fragmented global resource utilization and reducing reliance on centralized providers. However, in a p…
Belief-Guided Inference Control for Large Language Model Services via Verifiable Observations
In black-box large language model (LLM) services, response reliability is often only partially observable at decision time, while stronger inference pathways incur substantial computational cost, inducing a budgeted sequ…
Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI
Cloud-based infrastructure has become the dominant platform for deploying large models, particularly large language models (LLMs). Fine-tuning and inference are increasingly delegated to cloud providers for simplified de…
TinyJudge: Unverifiable Constraint Alignment via Lightweight Specialist Ensembles
Instruction Following (IF) is a core capability of LLMs, requiring strict adherence to diverse constraints, ranging from verifiable ones (e.g., output length) to unverifiable ones (e.g., tone). Reinforcement learning wit…
Reinforcement LearningInstruction FollowingSemantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended Tasks
The rising cost of acquiring supervised data has driven significant interest in self-improvement for large language models (LLMs). Straightforward unsupervised signals like majority voting have proven effective in genera…
Computational EfficiencySemantic Similarity