cryptographic hashing

This work addresses the challenge of formally guaranteeing security and correctness in the automated generation of authenticated data structures (ADS). We introduce the first relational separation logic supporting collision-resistant hash functions and construct a bilingual semantic model in Coq to rigorously characterize type abstraction security. Based on this logic, we implement fully automatic code generation for an ADS library and mechanize proofs of its functional correctness, memory safety, and equivalence of key optimizations. Moreover, we establish the first formal framework proving secure interoperability between automatically generated code and hand-optimized implementations. Our approach integrates Iris concurrent separation logic with cryptographic hash modeling, enabling end-to-end trustworthiness under a unified formal foundation. The result is a verifiable construction paradigm for high-assurance ADS systems.

In regulated AI workflows, audit evidence must be cryptographically bound to specific events and configurations, while supporting immutable storage and uniform verification costs—challenging existing approaches. Method: This paper proposes a constant-size cryptographic auditing structure based on collision-resistant hashing and standard digital signatures. It introduces a generic abstract model that achieves strong security binding between events and configurations, with constant-time storage (O(1)) and verification overhead (O(1)) per event, and natively integrates with mainstream audit primitives—including hash chains and Merkle trees. The prototype combines hash-chain logging, Merkle anchoring, and trusted execution environments, validated on commodity hardware for low latency, high predictability, and deployment feasibility. Contribution/Results: This work presents the first lightweight, verifiable auditing framework for compliance-critical AI systems that simultaneously guarantees formal security, composability, and engineering practicality.

This work addresses the frequent disconnect between the mathematical certainty of numerical values in cryptographic protocols and their concrete representations, which undermines interoperability and formal verification. Drawing from representation theory, the paper introduces three classes of representations—algorithmically approximable, finitely precisely describable, and canonically normalizable—and proves that no universal computable canonicalizer can transform arbitrary approximate programs into a unique finite encoding. It extends the canonical encoding paradigm of the rational number system Σ_Q to practical cryptographic objects. By integrating computability theory with canonical serialization techniques, the approach is applied to symmetric and asymmetric encryption, hashing, and blockchain integrity protocols. Case studies such as Snaproot demonstrate that canonical representations are essential for achieving precise protocol specifications, ensuring interoperability, and enabling byte-level correctness arguments.

This paper addresses privacy leakage risks in data access auditing—specifically implicit information inference and unauthorized auditing of others’ accesses—by introducing a strong auditability formalization whose core principle is logging only “effective read” operations. To this end, we propose the first effective-read-driven audit model and design three provably secure distributed objects: (1) a wait-free, leakage- and eavesdropping-resistant multi-writer multi-reader register; (2) a scalable auditable max-register; and (3) a snapshot object supporting fine-grained auditing. Key techniques include atomic read-log fusion, one-time-pad encryption, wait-free distributed protocols, and versioned type construction. Our solution enables precise, real-time, and verifiable fine-grained auditing without revealing data values or access metadata, thereby supporting higher-level abstractions such as snapshots and versioning.

This paper challenges the widespread assumption in blockchain systems that “immutability implies trust,” arguing that immutability—merely a cryptographic guarantee of data persistence—does not entail trust, which is a rational expectation of correctness, fairness, and reliability under uncertainty. Method: We formalize this distinction using predicate logic to model system properties, automata theory to characterize protocol behavior, cognitive game theory to analyze belief evolution among participants, and construct rigorous formal counterexamples. Contribution/Results: We provide the first formal disproof of the erroneous implication “immutability ⇒ trustworthiness.” The paper introduces a foundational separation between *structural trust* (rooted in technical invariants) and *cognitive trust* (grounded in agent reasoning), demonstrating that immutability neither ensures data authenticity, procedural fairness, nor resistance to fraud. It further identifies the theoretical origins of predictive fraud and permanent garbage-data proliferation as direct consequences of conflating these distinct trust modalities.

This work addresses the challenge of enabling secure and programmable spending conditions without relying on consensus participants. To this end, we introduce, for the first time, a predicate mechanism into the Unicity model, extending token ownership to programmable spending predicates executed off-chain by dependent parties. This extension preserves the original system’s security guarantees while supporting off-chain smart contract functionality. Leveraging the unforgeability of predicate families, we construct a formally secure spending model and design a complementary off-chain execution architecture together with an atomic swap protocol. Our approach successfully realizes trustless atomic swaps, demonstrating the practical applicability of the proposed framework.

This work addresses the challenge of enabling trustworthy auditing of unstructured semantic attributes—such as code logic—while preserving the privacy of proprietary data. The authors propose a novel three-party framework that introduces a “proxy witness” paradigm, shifting verification from attested execution to attested reasoning and thereby achieving, for the first time, privacy-preserving qualitative auditing for unstructured data. By integrating trusted execution environments (TEEs), large language models (LLMs), the Model Context Protocol (MCP), and cryptographic hash chains, the framework allows verifiers to assess high-level semantic properties of private data through Boolean queries without exposing the underlying source code. Experimental results demonstrate that the approach successfully automates artifact evaluation across 21 GitHub repositories, accurately verifying five high-level semantic attributes.

This work addresses the inefficiency of existing SNARKs in proving batch computations of standard cryptographic hash functions—such as SHA-256, Keccak, and BLAKE3—and proposes a novel hash-based SNARK tailored for high-throughput Boolean computations over homogeneous R1CS circuits, with direct applications to hash chains, Merkle path verification, and hash-based signature validation. By integrating lincheck and zerocheck protocols within a multi-core parallel architecture co-designed with encoding-aware agents, the system achieves substantial throughput gains. Empirical results demonstrate that a single core can generate proofs for 82k BLAKE3, 42k SHA-256, and 30k Keccak evaluations per second, yielding a speedup of over 9× compared to Binius64 and more than 500× relative to the fastest elliptic-curve-based SNARKs currently available.

This work addresses the vulnerability of traditional verifiable secret sharing (VSS) to quantum attacks, which undermines its long-term binding security. To resolve this, the authors propose Proof in a Bottle (PiB), a novel scheme that decouples verifiability from long-term binding. PiB leverages pre-quantum Pedersen commitments to enable real-time zero-knowledge verification while deferring binding to the post-quantum era through a “commit now, reveal later” mechanism. Specifically, binding information is encoded as salted hashes and immutably anchored to a public ledger, ensuring that secrets distributed by honest parties today remain both secure and recoverable even in the presence of future quantum adversaries. This approach preserves the immediate integrity of VSS while guaranteeing long-term availability and security against quantum threats.

Existing autonomous commercial protocols struggle to achieve interoperable, tamper-proof auditing and event temporal verification across heterogeneous domains. This work proposes a verifiable global event timeline architecture that constructs a reproducible, tamper-resistant AI fraud intelligence training pipeline by formalizing event schemas, employing deterministic batching, leveraging Merkle append-only commitments, and anchoring events to blockchain-based timestamps. The approach innovatively integrates cryptographic fraud markers—binding risk labels with anchored evidence—and a data provenance model to establish a verifiable, traceable, AI-ready intelligence layer. Evaluated on a prototype processing 50,000 events, the system constructs Merkle trees in just 47 milliseconds, achieves end-to-end verification in under 0.013 milliseconds, and exhibits logarithmic proof size growth, yielding a 14.4× improvement in verification efficiency over linear scanning.