The paper proposes constant depth threshold circuits for efficiently detecting epistasis by calculating the relative frequencies of all dataset combinations using specialized hardware architectures.

This paper analyzes the computational complexity of verifying feedforward neural networks when their weights are restricted to finite-width arithmetic, finding that verification remains NP-complete fo…

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 systematically explores a vast design space of cryptographic Boolean networks by formalizing six structural constraints, finding that optimal designs result from sparse, mutually compatible…

The paper presents a new worst-case to average-case reduction for the Learning Parity with Noise (LPN) problem, achieving hardness for inverse-polynomial noise rates previously unattainable.

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 establishes a strong connection between scalable pseudorandom unitaries (PRUs) and the unitary synthesis problem, proving that any such PRU construction must require a classical oracle of si…

This paper analyzes the computational complexity of evaluating recurrent functions, showing that the complexity depends heavily on how the input offsets are encoded and the structure of the recurrence…

This paper investigates limitations of learning tanh neural networks under finite-precision computations and Lp accuracy guarantees.

This paper investigates limitations of learning tanh neural networks under finite-precision computations and Lp accuracy guarantees.

The paper proposes a local perturbation theory showing that cross-domain interference in multi-domain RL occurs via a low-dimensional shared conflict subspace, which can be selectively mitigated by sh…

This paper settles the complexity of three sketching problems in graphs and distributions.

The paper establishes a universal, machine-checked 1-Bit Barrier for the internal wire map of masked Barrett reduction, providing a strong side-channel leakage bound for post-quantum cryptography.

The paper empirically and theoretically demonstrates that incorporating Lamarckian and Baldwinian mechanisms into evolutionary algorithms significantly outperforms standard Darwinian evolution, especi…

The paper develops a structurally justified framework for measuring Quantum Cryptographic Exposure (HNDL) by showing that the compromise probability factorizes into distinct, interacting components ba…

The paper argues that current lattice-based post-quantum cryptography, which relies on injecting noise, is not unconditionally secure because advanced quantum error correction and learning techniques…

The paper proposes a novel adversarial defense approach, TopFeaRe, by modeling graph adversarial attacks using complex dynamic system theory to locate the graph's critical state of resilience.

The paper introduces an LLM-guided evolutionary workflow that successfully discovers and certifies a large number of novel bivariate quantum error-correcting codes, demonstrating the utility of LLMs i…

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…