arXiv subjects

Zhiyong Zheng

Publications and source records attributed to Zhiyong Zheng.

At least 19 recordsLinked to original sources

arXiv2026

Step-Level On-Policy Distillation: Interpolating Between On-Policy Distillation and Supervised Fine-Tuning

On-policy distillation (OPD) aligns a student model with a teacher's logit distribution on student-generated trajectories. This approach has achieved strong empirical gains and can often surpass conventional off-policy distillation with substantially less data. However, standard token-level OPD can provide only fragmented corrections along an erroneous student trajectory and cannot unfold a complete and correct repair path. Motivated by this limitation, we propose \emph{Step-Level On-Policy Distillation} (SOPD), which combines the long-horizon correction of supervised fine-tuning (SFT) with the on-policy advantage of OPD to provide step-level supervision over complete student-generated trajectories. We show that, at different limits of step length, SOPD reduces to SFT or approximates OPD. Compared with SFT, the teacher responses in SOPD are conditioned on student trajectories and therefore align more closely with student-visited states; compared with OPD, SOPD provides longer-horizon corrections rather than fragmented token-level guidance. Across both reasoning and agent tasks, SOPD substantially outperforms conventional SFT and OPD. For example, on ALFWorld, SOPD improves the average success rate by 13.4 points over Vanilla OPD. We hope this work offers a new perspective for future research on distillation methods.

cs.CL↗

arXiv2026

ARC-Fi: Exploiting Antenna Spatial Diversity for Label-Efficient Domain Generalization in Wi-Fi Sensing

Wi-Fi sensing systems are severely hindered by domain shifts when deployed in unseen real-world environments. While existing methods attempt to tackle this through Unsupervised Domain Adaptation (UDA) or Domain Generalization (DG), they critically rely on either inaccessible target data or prohibitively expensive, massive labeled source datasets. In practice, collecting abundant unlabeled Channel State Information (CSI) is feasible, whereas manual labeling is severely constrained. This realistic dilemma necessitates Semi-Supervised Domain Generalization (SSDG). To this end, we propose ARC-Fi, the first dedicated SSDG framework for Wi-Fi sensing. Directly applying conventional contrastive learning to CSI data inevitably triggers paradigm-specific "shortcut learning," causing models to memorize environmental backgrounds rather than gesture dynamics. To overcome this, ARC-Fi introduces a physics-informed data augmentation strategy: the Antenna Response Consistency (ARC) module. ARC exploits the intrinsic spatial diversity of multi-antenna systems, treating signals from co-located antennas as naturally semantics-preserving augmented views to explicitly block environmental shortcuts. Furthermore, we introduce a unified Semi-Supervised Contrastive Objective that leverages scarce labels and reliable pseudo-labels to align cross-domain features, effectively preventing the blind repulsion of same-class instances. Extensive experiments on the Widar and CSIDA datasets demonstrate that ARC-Fi establishes a new state-of-the-art, significantly outperforming existing UDA, DG, and SSDG methods. Ultimately, this work provides a physics-grounded, label-efficient solution, advancing the scalable deployment of robust real-world Wi-Fi sensing systems. Code is available at: https://github.com/KaoruMiyazono/UniCrossFi.

cs.LG↗

arXiv2026

Linearly Homomorphic Ring Signature Scheme over Lattices

Construct the first provably secure linear homomorphic ring signature scheme. Ring signatures allow a signer to anonymously sign a message on behalf of a user group (ring) and are widely applied in areas such as identity protection, electronic voting, and privacy enhancement in blockchain. Homomorphic signatures, on the other hand, support verifiable computations on signed data. The integration of anonymity and computability in homomorphic ring signatures holds the potential to create new application scenarios for privacy-preserving distributed systems. It is worth noting that Choi and Kim first introduced the concept of linear homomorphic ring signatures in 2017 and proposed a specific scheme. However, their scheme lacks a complete security proof, leaving its security theoretically unconfirmed. To address this research gap, this paper presents the first provably secure lattice-based linear homomorphic ring signature scheme, designed for scenarios where the ring size is O(log n). This scheme not only combines the anonymity of ring signatures with the malleability of homomorphic signatures but also achieves resistance against quantum attacks.

cs.CR↗

arXiv2026

Linearly Homomorphic Signature with Tight Security on Lattice

Constructing cryptographic schemes with tight or almost-tight security has long been one of the central problems in theoretical cryptography. At ASIACRYPT 2016, Boyen and Li posed an open problem: whether it is possible to construct a homomorphic signature scheme with tight or almost-tight security under the Short Integer Solution (SIS) assumption in the standard model. In 2024, Chen achieved the first construction with almost-tight security under a weaker security model. To further achieve tight security in the standard model, this paper introduces a new security model whose security requirements are weaker than those of the standard adaptive model but stronger than the model adopted by Chen. Under this model, we construct a linearly homomorphic signature scheme with tight security.

cs.CR↗

arXiv2026

IRPM: Intergroup Relative Preference Modeling for Pointwise Generative Reward Models

Generative Reward Models (GRMs) have demonstrated strong performance in reward modeling, due to their interpretability and potential for refinement through reinforcement learning (RL). However, widely used pairwise GRMs create a computational bottleneck in reinforcement learning from human feedback (RLHF), when calibrating or aggregating preference signals over n candidates, often incurring O(n^2) pairwise judgments. To address this issue, we propose Intergroup Relative Preference Modeling (IRPM), an RL-based method that extends the Bradley--Terry preference-learning paradigm via intergroup comparisons to train pointwise GRMs from pairwise preference data. IRPM derives pointwise reward for each response by contrasting groups of chosen vs. rejected samples, enabling pointwise scores comparable across candidate sets and O(n) reward evaluation for a variable number of candidates during RL training, while preserving interpretability and scalability. Experiments show that IRPM achieves state-of-the-art performance among pointwise GRMs on RM-Bench, JudgeBench and RewardBench, and approaches the performance of leading pairwise GRMs. In addition, IRPM achieves substantial gains in post-training evaluations, demonstrating its effectiveness.

cs.LG↗

arXiv2025

Authenticated Private Set Intersection: A Merkle Tree-Based Approach for Enhancing Data Integrity

Private Set Intersection (PSI) enables secure computation of set intersections while preserving participant privacy, standard PSI existing protocols remain vulnerable to data integrity attacks allowing malicious participants to extract additional intersection information or mislead other parties. In this paper, we propose the definition of data integrity in PSI and construct two authenticated PSI schemes by integrating Merkle Trees with state-of-the-art two-party volePSI and multi-party mPSI protocols. The resulting two-party authenticated PSI achieves communication complexity $\mathcal{O}(n λ+n \log n)$, aligning with the best-known unauthenticated PSI schemes, while the multi-party construction is $\mathcal{O}(n κ+n \log n)$ which introduces additional overhead due to Merkle tree inclusion proofs. Due to the incorporation of integrity verification, our authenticated schemes incur higher costs compared to state-of-the-art unauthenticated schemes. We also provide efficient implementations of our protocols and discuss potential improvements, including alternative authentication blocks.

cs.CR↗

arXiv2025

Authenticated Sublinear Quantum Private Information Retrieval

This paper introduces a novel lower bound on communication complexity using quantum relative entropy and mutual information, refining previous classical entropy-based results. By leveraging Uhlmann's lemma and quantum Pinsker inequalities, the authors establish tighter bounds for information-theoretic security, demonstrating that quantum protocols inherently outperform classical counterparts in balancing privacy and efficiency. Also explores symmetric Quantum Private Information Retrieval (QPIR) protocols that achieve sub-linear communication complexity while ensuring robustness against specious adversaries: A post-quantum cryptography based protocol that can be authenticated for the specious server; A ring-LWE-based protocol for post-quantum security in a single-server setting, ensuring robustness against quantum attacks; A multi-server protocol optimized for hardware practicality, reducing implementation overhead while maintaining sub-linear efficiency. These protocols address critical gaps in secure database queries, offering exponential communication improvements over classical linear-complexity methods. The work also analyzes security trade-offs under quantum specious adversaries, providing theoretical guarantees for privacy and correctness.

quant-ph↗

arXiv2025

Twisted second moment of primitive cubic L-functions

We investigate the mean value of the twisted second moment of primitive cubic $L$-functions over $\mathbb{F}_q(T)$ in the non-Kummer setting. Specifically, we study the sum \begin{equation*} \sum_{\substack{χ primitive\ cubic\\ genus(χ)=g}}χ(h_1)\barχ(h_2)|L_q(\frac{1}{2}, χ)|^2, \end{equation*} where $L_q(s,χ)$ denotes the $L$-function associated with primitive cubic character $χ$. Employing a double Dirichlet series approach, we establish an error term of size

math.NT↗

arXiv2025

MacWilliams Theory over Zk and nu-functions over Lattices

Continuing previous works on MacWilliams theory over codes and lattices, a generalization of the MacWilliams theory over $\mathbb{Z}_k$ for $m$ codes is established, and the complete weight enumerator MacWilliams identity also holds for codes over the finitely generated rings $\mathbb{Z}_k[ξ]$. In the context of lattices, the analogy of the MacWilliams identity associated with nu-function was conjectured by Solé in 1995, and we present a new formula for nu-function over the lattices associated with a ternary code, which is rather different from the original conjecture. Furthermore, we provide many counterexamples to show that the Solé conjecture never holds in the general case, except for the lattices associated with a binary code.

cs.IT↗

arXiv2025

Codes over Finite Ring $\mathbb{Z}_k$, MacWilliams Identity and Theta Function

In this paper, we study linear codes over $\mathbb{Z}_k$ based on lattices and theta functions. We obtain the complete weight enumerators MacWilliams identity and the symmetrized weight enumerators MacWilliams identity based on the theory of theta function. We extend the main work by Bannai, Dougherty, Harada and Oura to the finite ring $\mathbb{Z}_k$ for any positive integer $k$ and present the complete weight enumerators MacWilliams identity in genus $g$. When $k=p$ is a prime number, we establish the relationship between the theta function of associated lattices over a cyclotomic field and the complete weight enumerators with Hamming weight of codes, which is an analogy of the results by G. Van der Geer and F. Hirzebruch since they showed the identity with the Lee weight enumerators.

cs.IT↗

arXiv2025

Semigroup-homomorphic Signature

In 2002, Johnson et al. posed an open problem at the Cryptographers' Track of the RSA Conference: how to construct a secure homomorphic signature on a semigroup, rather than on a group. In this paper, we introduce, for the first time, a semigroup-homomorphic signature scheme. Under certain conditions, we prove that the security of this scheme is based on the hardness of the Short Integer Solution (SIS) problem and is tightly secure. Furthermore, we extend it to a linear semigroup-homomorphic signature scheme over lattices, and this scheme can also ensure privacy.

cs.CR↗

arXiv2024

On the MacWilliams Theorem over Codes and Lattices

Analogies between codes and lattices have been extensively studied for the last decades, in this dictionary, the MacWilliams identity is the finite analog of the Jacobi-Poisson formula of the Theta function. Motivated by the random theory of lattices, the statistical significance of MacWilliams theorem is considered, indeed, MacWilliams distribution provides a finite analog of the classical Gauss distribution. In particular, the MacWilliams distribution over quotient space of a code is statistical close to the uniform distribution. In the respect of lattices, the analogy of MacWilliams identity associated with nu-function was conjectured by Sole in 1995. We give an answer to this problem in positive.

cs.CR↗

arXiv2024

Towards Quantum-Safe Federated Learning via Homomorphic Encryption: Learning with Gradients

This paper introduces a privacy-preserving distributed learning framework via private-key homomorphic encryption. Thanks to the randomness of the quantization of gradients, our learning with error (LWE) based encryption can eliminate the error terms, thus avoiding the issue of error expansion in conventional LWE-based homomorphic encryption. The proposed system allows a large number of learning participants to engage in neural network-based deep learning collaboratively over an honest-but-curious server, while ensuring the cryptographic security of participants' uploaded gradients.

cs.CR↗

arXiv2023

FedReverse: Multiparty Reversible Deep Neural Network Watermarking

The proliferation of Deep Neural Networks (DNN) in commercial applications is expanding rapidly. Simultaneously, the increasing complexity and cost of training DNN models have intensified the urgency surrounding the protection of intellectual property associated with these trained models. In this regard, DNN watermarking has emerged as a crucial safeguarding technique. This paper presents FedReverse, a novel multiparty reversible watermarking approach for robust copyright protection while minimizing performance impact. Unlike existing methods, FedReverse enables collaborative watermark embedding from multiple parties after model training, ensuring individual copyright claims. In addition, FedReverse is reversible, enabling complete watermark removal with unanimous client consent. FedReverse demonstrates perfect covering, ensuring that observations of watermarked content do not reveal any information about the hidden watermark. Additionally, it showcases resistance against Known Original Attacks (KOA), making it highly challenging for attackers to forge watermarks or infer the key. This paper further evaluates FedReverse through comprehensive simulations involving Multi-layer Perceptron (MLP) and Convolutional Neural Networks (CNN) trained on the MNIST dataset. The simulations demonstrate FedReverse's robustness, reversibility, and minimal impact on model accuracy across varying embedding parameters and multiple client scenarios.

cs.CR↗

arXiv2023

Public key cryptosystems based on Iterated Functions Systems

Let $f=(f_0,f_1,\dots, f_{ν-1})$ be a collection of one-to-one functions from some space~$X$ into itself such that the sets $f_j(X)$ are disjoint. If $w=w_1w_2\cdots w_k$ is a word on the alphabet $\{0,1,\dots,ν-1\}$, let $Φ_{f,w} = f_{w_1}\circ f_{w_2}\circ\cdots\circ f_{w_k}$. Given a function~$F$ of which we know that it can be written as $Φ_{f,w}$, it is easy to recover~$w$. We give some examples of this situation where everything can be scrambled up by using some private key to get a new system $g=(g_1,g_2,\dots,g_{ν-1})$ on another set~$Y$ in such a way that the images of the $g_j$ are no longer disjoint. We define a cryptosystem whose public key is~$g$. The message to be encrypted is a word~$w$ and the associated cryptogram is $Φ_{g,w}$. The private key allows to recover $Φ_{f,w}$ from $Φ_{g,w}$.

cs.CR↗

arXiv2023

An Unbounded Fully Homomorphic Encryption Scheme Based on Ideal Lattices and Chinese Remainder Theorem

We propose an unbounded fully homomorphic encryption scheme, i.e. a scheme that allows one to compute on encrypted data for any desired functions without needing to decrypt the data or knowing the decryption keys. This is a rational solution to an old problem proposed by Rivest, Adleman, and Dertouzos \cite{32} in 1978, and to some new problems appeared in Peikert \cite{28} as open questions 10 and open questions 11 a few years ago. Our scheme is completely different from the breakthrough work \cite{14,15} of Gentry in 2009. Gentry's bootstrapping technique constructs a fully homomorphic encryption (FHE) scheme from a somewhat homomorphic one that is powerful enough to evaluate its own decryption function. To date, it remains the only known way of obtaining unbounded FHE. Our construction of unbounded FHE scheme is straightforward and noise-free that can handle unbounded homomorphic computation on any refreshed ciphertexts without bootstrapping transformation technique.

cs.CR↗

arXiv2022

On the High Dimensional RSA Algorithm -- A Public Key Cryptosystem Based on Lattice and Algebraic Number Theory

The most known of public key cryptosystem was introduced in 1978 by Rivest, Shamir and Adleman [19] and now called the RSA public key cryptosystem in their honor. Later, a few authors gave a simply extension of RSA over algebraic numbers field( see [20]- [22]), but they require that the ring of algebraic integers is Euclidean ring, this requirement is much more stronger than the class number one condition. In this paper, we introduce a high dimensional form of RSA by making use of the ring of algebraic integers of an algebraic number field and the lattice theory. We give an attainable algorithm (see Algorithm I below) of which is significant both from the theoretical and practical point of view. Our main purpose in this paper is to show that the high dimensional RSA is a lattice based on public key cryptosystem indeed, of which would be considered as a new number in the family of post-quantum cryptography(see [17] and [18]). On the other hand, we give a matrix expression for any algebraic number fields (see Theorem 2.7 below), which is a new result even in the sense of classical algebraic number theory.

math.NT↗

arXiv2021

A Generalization of Cyclic Code and Applications to Public Key Cryptosystems

In this paper, we define and discuss ϕ-cyclic code, which may be regarded as a general form of the ordinary cyclic code. As applications, we explain how to extend two public key encryption schemes, one is McEliece and Niederriter's cryptosystem of which is based on error-correcting code theory. Another one is NTRU public key cryptosystem of which is based on polynomial ring theory. The main purpose of this paper is to give a more general construction of NTRU based on ideal matrices and q-ary lattice theory.

cs.IT↗