The paper introduces partial multi-neuron relaxation, a novel verification technique that selectively computes tight linear bounds for a small subset of neurons to improve the efficiency and tightness…

The paper proposes evaluating certified training methods by comparing their Pareto fronts across the natural-certified accuracy trade-off, revealing superior performance and previously unappreciated c…

The paper introduces Fine-Tuning Integrity (FTI), a security goal that uses Succinct Model Difference Proofs (SMDPs) to cryptographically prove that a fine-tuned model update adheres to specific struc…

The paper provides a unified algebraic framework to determine the formal language expressivity of recurrent neural language models, resolving conflicts in existing literature by linking expressivity t…

The paper provides the first machine-checked universal proof, using ring theory, that value-independence implies identical marginal distributions for arithmetic masking, thereby extending the verifica…

The paper analyzes the failure modes of aggressive 2-bit quantization in large reasoning models, proposing lightweight controls like FP16 planning and loop rescue to restore accuracy and achieve pract…

NANOZK introduces a novel, highly efficient zero-knowledge proof system that allows users to cryptographically verify that the output of a large language model (LLM) was generated by a specific, claim…

The paper introduces a lightweight, sampling-based cryptographic protocol for verifiable AI inference that drastically reduces proving overhead from minutes to milliseconds by leveraging statistical p…

The paper formalizes the problem of representation identifiability in supervised learning, showing that a representation property is identifiable if and only if it is constant across all possible fact…

The paper proves that platform-deterministic inference is a necessary and sufficient condition for trustworthy AI, establishing that AI trust fundamentally relies on consistent arithmetic.

The paper introduces Neuroforger, a system that combines a new formal specification language with LLMs and type checking to reliably generate and validate concrete violation witnesses (counterexamples…

This study empirically benchmarks classical and quantum machine learning models for image recognition, finding that while quantum models offer superior accuracy and resource efficiency at high dimensi…

The paper proposes a federated formal verification architecture that treats verification as a polyglot proof system, successfully validating it on complex production subsystems like a Raft consensus m…

The paper analyzes the expressivity of padded transformers, proving that their computational power is primarily determined by model depth and numeric precision, rather than attention type or width.

The paper demonstrates that encoding harmful prompts as genuine mathematical problems, rather than just using mathematical formatting, effectively bypasses the safety filters of large language models.

The paper develops a formal theory to analyze how throughput changes in AI-enhanced cybersecurity pipelines when stage capacities are perturbed by multipliers.

The paper proposes a method for bit-exact verification of AI inference outputs without sacrificing performance, demonstrating that deterministic, precise re-computation is possible even across differe…

The paper introduces a four-stage structural dependency analysis hierarchy that enables scalable, sound first-order masking verification for large, production-level post-quantum cryptographic accelera…

The paper evaluates LLM reasoning on Boolean satisfiability (SAT) problems, concluding that conventional metrics are misleading and proposing a paired-formula protocol with Accurate Differentiation Ra…

The paper introduces Hybrid Verified Decoding, a method that predicts the acceptance length of a cache draft to intelligently select between cache verification and model-based drafting, achieving sign…