The paper provides the conjectured solution for the generating function of k-convex polyominoes, based on analysis of generated enumeration data.

The paper demonstrates that fine-tuning safety guard models on benign data can catastrophically collapse their safety alignment, proposing Fisher-Weighted Safety Subspace Regularization (FW-SSR) to ac…

The paper addresses the vulnerability of zero-knowledge proximity proofs in stateful systems by proposing Zairn-ZKP, a method that embeds operational context (like drop identity and policy version) di…

The paper analyzes the structured CVP distance on the log-unit lattice of cyclotomic fields, significantly reducing the conjectured CDPR factor for the ML-KEM cryptosystem from exponential to sub-poly…

Semia is a novel static auditor that translates complex, prose-defined agent skills into a verifiable Datalog fact base, enabling the detection of critical security vulnerabilities in real-world LLM a…

PRISM is a novel, precise object-bounds protection scheme that significantly reduces runtime overhead by encoding the object's end address directly into the pointer tag, thereby eliminating costly met…

The paper proposes Latent Geometric Chords (LGC) and LGC-H, a novel method that navigates decision boundaries using curvature-aware geometric search within a semantic manifold to generate high-fidelit…

The paper systematically studies the trade-offs between the number of slopes, bends per edge, and required area for planar drawings of bounded-degree graphs, providing new constructions for high-degre…

This paper presents an algorithm to generate snake-like polyominoes within a given rectangle and provides exact formulas for the maximal area of such polyominoes for certain dimensions.

The paper presents a lattice-based Ciphertext-Policy Attribute-Based Encryption (CP-ABE) scheme that supports $\mathsf{NC}^1$ access policies while maintaining constant-size ciphertexts.

The paper introduces Geodesic Flow Matching, a manifold-aware denoising technique that adapts Riemannian transport dynamics to accurately clean high-dimensional structured representations like Spatial…

This paper provides the first unconditional proof for Weber's Conjecture for the case $k ext{ up to } 12$, which is crucial for lattice-based cryptography.

The paper introduces ConsisGuard, a framework that addresses the 'deliberation-to-enforcement gap' in LLM guardrails by ensuring that the reasoning process is faithfully and consistently translated in…

The paper introduces Latent Policy Guardrail (LPG), a novel framework that efficiently enforces dynamic safety policies for LLMs by compressing complex policy deliberation into a small set of latent t…

The paper provides the first machine-checked, tridirectional correctness proof of the OpenZeppelin reentrancy-guard pattern against complex, production-deployed Solidity smart contract source.

AgentWall is a runtime safety layer that intercepts and evaluates all proposed actions from local AI agents against a declarative policy, ensuring safety before execution.

This paper derives multivariate generating functions to refine the enumeration of Fibonacci polyominoes.

Half-Moon Cookie introduces a private, similarity-based blocklisting framework that allows clients to check items against a proprietary blocklist without revealing the item or the blocklist contents,…

The paper introduces ML-Bench, a policy-grounded multilingual safety benchmark, and ML-Guard, a superior guardrail model that enables culturally and legally aligned safety assessment for LLMs across 1…

GLiGuard introduces a compact, schema-conditioned bidirectional encoder that achieves state-of-the-art performance in LLM content moderation across multiple safety dimensions while drastically reducin…