arXiv subjects

Dongfang Zhao

Publications and source records attributed to Dongfang Zhao.

At least 37 records · Page 2Linked to original sources

arXiv2026

DSBA: Dynamic Stealthy Backdoor Attack with Collaborative Optimization in Self-Supervised Learning

Self-Supervised Learning (SSL) has emerged as a significant paradigm in representation learning thanks to its ability to learn without extensive labeled data, its strong generalization capabilities, and its potential for privacy preservation. However, recent research reveals that SSL models are also vulnerable to backdoor attacks. Existing backdoor attack methods in the SSL context commonly suffer from issues such as high detectability of triggers, feature entanglement, and pronounced out-of-distribution properties in poisoned samples, all of which compromises attack effectiveness and stealthiness. To that, we propose a Dynamic Stealthy Backdoor Attack (DSBA) backed by a new technique we term Collaborative Optimization. This method decouples the attack process into two collaborative optimization layers: the outer-layer optimization trains a backdoor encoder responsible for global feature space remodeling, aiming to achieve precise backdoor implantation while preserving core functionality; meanwhile, the inner-layer optimization employs a dynamically optimized generator to adaptively produce optimally concealed triggers for individual samples, achieving coordinated concealment across feature space and visual space. We also introduce multiple loss functions to dynamically balance attack performance and stealthiness, in which we employ an adaptive weight scheduling mechanism to enhance training stability. Extensive experiments on various mainstream SSL algorithms and five public datasets demonstrate that: (i) DSBA significantly enhances Attack Success Rate (ASR) and stealthiness while maintaining downstream task accuracy; and (ii) DSBA exhibits superior robustness against existing mainstream defense methods.

cs.CR↗

arXiv2026

BadRSSD: Backdoor Attacks on Regularized Self-Supervised Diffusion Models

Self-supervised diffusion models learn high-quality visual representations via latent space denoising. However, their representation layer poses a distinct threat: unlike traditional attacks targeting generative outputs, its unconstrained latent semantic space allows for stealthy backdoors, permitting malicious control upon triggering. In this paper, we propose BadRSSD, the first backdoor attack targeting the representation layer of self-supervised diffusion models. Specifically, it hijacks the semantic representations of poisoned samples with triggers in Principal Component Analysis (PCA) space toward those of a target image, then controls the denoising trajectory during diffusion by applying coordinated constraints across latent, pixel, and feature distribution spaces to steer the model toward generating the specified target. Additionally, we integrate representation dispersion regularization into the constraint framework to maintain feature space uniformity, significantly enhancing attack stealth. This approach preserves normal model functionality (high utility) while achieving precise target generation upon trigger activation (high specificity). Experiments on multiple benchmark datasets demonstrate that BadRSSD substantially outperforms existing attacks in both FID and MSE metrics, reliably establishing backdoors across different architectures and configurations, and effectively resisting state-of-the-art backdoor defenses.

cs.CR↗

arXiv2026

HPE: Hallucinated Positive Entanglement for Backdoor Attacks in Federated Self-Supervised Learning

Federated self-supervised learning (FSSL) enables collaborative training of self-supervised representation models without sharing raw unlabeled data. While it serves as a crucial paradigm for privacy-preserving learning, its security remains vulnerable to backdoor attacks, where malicious clients manipulate local training to inject targeted backdoors. Existing FSSL attack methods, however, often suffer from low utilization of poisoned samples, limited transferability, and weak persistence. To address these limitations, we propose a new backdoor attack method for FSSL, namely Hallucinated Positive Entanglement (HPE). HPE first employs hallucination-based augmentation using synthetic positive samples to enhance the encoder's embedding of backdoor features. It then introduces feature entanglement to enforce tight binding between triggers and backdoor samples in the representation space. Finally, selective parameter poisoning and proximity-aware updates constrain the poisoned model within the vicinity of the global model, enhancing its stability and persistence. Experimental results on several FSSL scenarios and datasets show that HPE significantly outperforms existing backdoor attack methods in performance and exhibits strong robustness under various defense mechanisms.

cs.CR↗

arXiv2025

QPAD: Quantile-Preserving Approximate Dimension Reduction for Nearest Neighbors Preservation in High-Dimensional Vector Search

High-dimensional vector embeddings are widely used in retrieval systems, but they often suffer from noise, the curse of dimensionality, and slow runtime. However, dimensionality reduction (DR) is rarely applied due to its tendency to distort the nearest-neighbor (NN) structure that is critical for search. Existing DR techniques such as PCA and UMAP optimize global or manifold-preserving criteria, rather than retrieval-specific objectives. We present QPAD -- Quantile-Preserving Approximate Dimension Reduction, an unsupervised DR method that explicitly preserves approximate NN relations by maximizing the margin between k-NNs and non-k-NNs under a soft orthogonality constraint. We analyze its complexity and favorable properties. This design enables QPAD to retain ANN-relevant geometry without supervision or changes to the original embedding model, while supporting scalability for large-scale vector search and being indexable for ANN search. Experiments across five domains show that QPAD consistently outperforms eleven standard DR methods in preserving neighborhood structure, enabling more accurate search in reduced dimensions.

cs.IR↗

arXiv2025

ProHD: Projection-Based Hausdorff Distance Approximation

The Hausdorff distance (HD) is a robust measure of set dissimilarity, but computing it exactly on large, high-dimensional datasets is prohibitively expensive. We propose \textbf{ProHD}, a projection-guided approximation algorithm that dramatically accelerates HD computation while maintaining high accuracy. ProHD identifies a small subset of candidate "extreme" points by projecting the data onto a few informative directions (such as the centroid axis and top principal components) and computing the HD on this subset. This approach guarantees an underestimate of the true HD with a bounded additive error and typically achieves results within a few percent of the exact value. In extensive experiments on image, physics, and synthetic datasets (up to two million points in $D=256$), ProHD runs 10--100$\times$ faster than exact algorithms while attaining 5--20$\times$ lower error than random sampling-based approximations. Our method enables practical HD calculations in scenarios like large vector databases and streaming data, where quick and reliable set distance estimation is needed.

cs.IR↗

arXiv2025

HOPE: Homomorphic Order-Preserving Encryption for Outsourced Databases -- A Stateless Approach

Order-preserving encryption (OPE) is a fundamental cryptographic tool for enabling efficient range queries on encrypted data in outsourced databases. Despite its importance, existing OPE schemes face critical limitations that hinder their practicality. Stateful designs require clients to maintain plaintext-to-ciphertext mappings, imposing significant storage and management overhead. Stateless designs often rely on interactive protocols between the client and server, leading to high communication latency and limited scalability. These limitations make existing schemes unsuitable for real-world applications that demand simplicity, efficiency, and scalability. In this work, we present Homomorphic OPE (HOPE), a new OPE scheme that eliminates client-side storage and avoids additional client-server interaction during query execution. HOPE leverages the additive property of homomorphic encryption to introduce a novel comparison key mechanism, which transforms ciphertext comparison into a randomized difference computation. This mechanism ensures that only the sign of the comparison is preserved while fully masking the underlying plaintext values, enabling secure and efficient range queries without leaking additional information about the data. We provide a formal cryptographic analysis of HOPE, proving its security under the widely accepted IND-OCPA model. Our proofs rigorously demonstrate that the comparison key mechanism reveals no information beyond the order of the plaintexts and ensures resistance to both chosen-plaintext attacks and frequency analysis. To validate the practicality of HOPE, we conduct extensive experiments comparing it with state-of-the-art OPE schemes. The results demonstrate that HOPE achieves competitive query performance while addressing the key limitations of existing designs, making it a scalable and secure solution for outsourced database systems.

cs.CR↗

arXiv2025

TokenBlowUp: Resolving Representational Singularities in LLM Token Spaces via Monoidal Transformations

Recent work has provided compelling evidence challenging the foundational manifold hypothesis for the token embedding spaces of Large Language Models (LLMs). These findings reveal the presence of geometric singularities around polysemous tokens, which can lead to representational instability. Existing methodologies, which presuppose a smooth data manifold, are ill-equipped to address such intrinsic structural flaws. In this paper, we formalize this problem in the language of scheme theory and propose a rigorous resolution by applying the scheme-theoretic blow-up at each singular point. This procedure replaces a singular point in the ambient affine scheme with its exceptional divisor, which we identify as a canonical geometric space -- a projective space of directions -- that houses the disambiguated semantic meanings of the token. This process of ``representational desingularization'' constructs a new geometric landscape for embeddings. We prove a formal theorem guaranteeing the geometric regularization of this new space, showing that the original pathologies are resolved. Finally, we outline the architectural implications of our framework, arguing for a paradigm shift from static look-ups to dynamic, geometrically-grounded computation.

math.AG↗

arXiv2025

Approximate Fiber Products of Schemes and Their Étale Homotopical Invariants

The classical fiber product in algebraic geometry provides a powerful tool for studying loci where two morphisms to a base scheme, $ϕ: X \to S$ and $ψ: Y \to S$, coincide exactly. This condition of strict equality, however, is insufficient for describing many real-world applications. This paper develops a new framework to study and quantify the nature of approximate alignment between morphisms in the context of arithmetic geometry, using the tools of {é}tale homotopy theory. We introduce the central object of our work, the \textit{{é}tale mismatch torsor}, a sheaf of torsors over the product scheme $X \times_S Y$. The structure of this sheaf serves as a rich, intrinsic, and purely algebraic object amenable to both qualitative classification and quantitative analysis of the global relationship between the two morphisms. Our main results are twofold. First, we provide a complete classification of these structures, establishing a bijection between their isomorphism classes and the first {é}tale cohomology group $H_{\text{é}t}^1(X \times_S Y, \underline{π_1^{\text{é}t}(S)})$. Second, we construct a canonical filtration on this classifying cohomology group based on the theory of infinitesimal neighborhoods. This filtration induces a new invariant, which we term the \textit{order of mismatch}, providing a hierarchical, algebraic measure for the degree of approximation between the morphisms. We apply this framework to the concrete case of generalized Howe curves over finite fields, demonstrating how both the characteristic class and its order reveal subtle arithmetic properties.

math.AG↗

arXiv2025

Structure-Preserving Error-Correcting Codes for Polynomial Frames

Modern FFT/NTT analytics, coded computation, and privacy-preserving ML interface routinely move polynomial frames across NICs, storage, and accelerators. However, even rare silent data corruption (SDC) can flip a few ring coefficients and cascade through downstream arithmetic. Conventional defenses are ill-matched to current low-latency pipelines: detect-and-retransmit adds RTTs, while byte-stream ECC ignores the algebraic structure and forces format conversions. To that end, we propose a structure-preserving reliability layer that operates in the encoded data's original polynomial ring, adds a small amount of systematic redundancy, and corrects symbol errors/flagged erasures without round-trip or format changes. We construct two complementary schemes: one for odd length $N_{odd}$ via a Hensel-lifted BCH ideal with an idempotent encoder, and one for power-of-two length $N_{2^m}$ via a repeated-root negacyclic code with derivative-style decoding. In particular, to stay robust against clustered errors, a ring automorphism provides in-place interleaving to disperse bursts. Implementation wise, on four frame sizes $N\!=\!1024, 2048, 4096, 8192$, we meet a per-frame failure target of $10^{-9}$ at symbol error rates $10^{-6}\text{--}10^{-5}$ with $t\!=\!8\text{--}9$, incurring only $0.20\%\text{--}1.56\%$ overhead and tolerating $\sim\!32\text{--}72$\,B unknown-error bursts (roughly doubled when flagged as erasures) after interleaving. By aligning error correction with ring semantics, we take a practical step toward deployable robustness for polynomial-frame computations from an algebraic coding perspective.

cs.IT↗

arXiv2025

RAE: A Neural Network Dimensionality Reduction Method for Nearest Neighbors Preservation in Vector Search

While high-dimensional embedding vectors are being increasingly employed in various tasks like Retrieval-Augmented Generation and Recommendation Systems, popular dimensionality reduction (DR) methods such as PCA and UMAP have rarely been adopted for accelerating the retrieval process due to their inability of preserving the nearest neighbor (NN) relationship among vectors. Empowered by neural networks' optimization capability and the bounding effect of Rayleigh quotient, we propose a Regularized Auto-Encoder (RAE) for k-NN preserving dimensionality reduction. RAE constrains the network parameter variation through regularization terms, adjusting singular values to control embedding magnitude changes during reduction, thus preserving k-NN relationships. We provide a rigorous mathematical analysis demonstrating that regularization establishes an upper bound on the norm distortion rate of transformed vectors, thereby offering provable guarantees for k-NN preservation. With modest training overhead, RAE achieves superior k-NN recall compared to existing DR approaches while maintaining fast retrieval efficiency.

cs.IR↗

arXiv2025

Bootstrapping as a Morphism: An Arithmetic Geometry Approach to Asymptotically Faster Homomorphic Encryption

Fully Homomorphic Encryption (FHE) provides a powerful paradigm for secure computation, but its practical adoption is severely hindered by the prohibitive computational cost of its bootstrapping procedure. The complexity of all current bootstrapping methods is fundamentally tied to the multiplicative depth of the decryption circuit, denoted $L_{dec}$, making it the primary performance bottleneck. This paper introduces a new approach to bootstrapping that completely bypasses the traditional circuit evaluation model. We apply the tools of modern arithmetic geometry to reframe the bootstrapping operation as a direct geometric projection. Our framework models the space of ciphertexts as an affine scheme and rigorously defines the loci of decryptable and fresh ciphertexts as distinct closed subschemes. The bootstrapping transformation is then realized as a morphism between these two spaces. Computationally, this projection is equivalent to solving a specific Closest Vector Problem (CVP) instance on a highly structured ideal lattice, which we show can be done efficiently using a technique we call algebraic folding. The primary result of our work is a complete and provably correct bootstrapping algorithm with a computational complexity of $O(d \cdot \text{poly}(\log q))$, where $d$ is the ring dimension and $q$ is the ciphertext modulus. The significance of this result lies in the complete elimination of the factor $L_{dec}$ from the complexity, representing a fundamental asymptotic improvement over the state of the art. This geometric perspective offers a new and promising pathway toward achieving truly practical and high-performance FHE.

cs.CR↗

arXiv2025

On The Reproducibility Limitations of RAG Systems

Retrieval-Augmented Generation (RAG) is increasingly employed in generative AI-driven scientific workflows to integrate rapidly evolving scientific knowledge bases, yet its reliability is frequently compromised by non-determinism in their retrieval components. This paper introduces ReproRAG, a comprehensive benchmarking framework designed to systematically measure and quantify the reproducibility of vector-based retrieval systems. ReproRAG investigates sources of uncertainty across the entire pipeline, including different embedding models, precision, retrieval algorithms, hardware configurations, and distributed execution environments. Utilizing a suite of metrics, such as Exact Match Rate, Jaccard Similarity, and Kendall's Tau, the proposed framework effectively characterizes the trade-offs between reproducibility and performance. Our large-scale empirical study reveals critical insights; for instance, we observe that different embedding models have remarkable impact on RAG reproducibility. The open-sourced ReproRAG framework provides researchers and engineers productive tools to validate deployments, benchmark reproducibility, and make informed design decisions, thereby fostering more trustworthy AI for science.

cs.DC↗

arXiv2025

Spatiotemporally Resolved Measurements of CO2 Distribution at the Air-Water Interface Using Tunable Diode Laser Spectroscopy

The transport of CO2 across the air-water interface is central to physical oceanography and carbon sequestration. A comprehensive understanding of this process requires high-resolution diagnostics of diffusion, absorption, and reaction across a wide range of spatial and temporal scales. The current study presents a novel measurement method to quantify the CO2 distribution at the air-water interface. This method combines the advantages of tunable diode laser spectroscopy and rapid spatial beam scanning for in situ, nonintrusive, and spatiotemporally resolved measurement of the CO2 concentration distribution above the interface. The performance of this method was examined in a series of quasi-1D experiments in a miniature gas chamber, where the diffusion and absorption of CO2 into pure water and alkaline solutions of different pH values were continuously monitored. An effective time resolution of 5 ms and an effective spatial resolution of 1 mm were achieved. The observed gas-phase CO2 distribution evolution agreed with the classic one-dimensional diffusion model, which validated the accuracy of the current method. PH-dependent dynamics of interfacial CO2 concentration were also observed. The CO2 depletion rate is highly pH-sensitive at low pH and saturates at pH = 10, revealing complex competition between the gas-phase and the liquid-phase transport processes. The current method's high spatial and temporal resolution holds promise for studying cross-interface gas transport under more complex flow conditions, in both field measurements and laboratory studies.

physics.flu-dyn↗

arXiv2025

PIR-RAG: A System for Private Information Retrieval in Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) has become a foundational component of modern AI systems, yet it introduces significant privacy risks by exposing user queries to service providers. To address this, we introduce PIR-RAG, a practical system for privacy-preserving RAG. PIR-RAG employs a novel architecture that uses coarse-grained semantic clustering to prune the search space, combined with a fast, lattice-based Private Information Retrieval (PIR) protocol. This design allows for the efficient retrieval of entire document clusters, uniquely optimizing for the end-to-end RAG workflow where full document content is required. Our comprehensive evaluation against strong baseline architectures, including graph-based PIR and Tiptoe-style private scoring, demonstrates PIR-RAG's scalability and its superior performance in terms of "RAG-Ready Latency"-the true end-to-end time required to securely fetch content for an LLM. Our work establishes PIR-RAG as a viable and highly efficient solution for privacy in large-scale AI systems.

cs.IR↗

arXiv2025

Order-Preserving Dimension Reduction for Multimodal Semantic Embedding

Searching for the $k$-nearest neighbors (KNN) in multimodal data retrieval is computationally expensive, particularly due to the inherent difficulty in comparing similarity measures across different modalities. Recent advances in multimodal machine learning address this issue by mapping data into a shared embedding space; however, the high dimensionality of these embeddings (hundreds to thousands of dimensions) presents a challenge for time-sensitive vision applications. This work proposes Order-Preserving Dimension Reduction (OPDR), aiming to reduce the dimensionality of embeddings while preserving the ranking of KNN in the lower-dimensional space. One notable component of OPDR is a new measure function to quantify KNN quality as a global metric, based on which we derive a closed-form map between target dimensionality and key contextual parameters. We have integrated OPDR with multiple state-of-the-art dimension-reduction techniques, distance functions, and embedding models; experiments on a variety of multimodal datasets demonstrate that OPDR effectively retains recall high accuracy while significantly reducing computational costs.

cs.LG↗

arXiv2025

IPBA: Imperceptible Perturbation Backdoor Attack in Federated Self-Supervised Learning

Federated self-supervised learning (FSSL) combines the advantages of decentralized modeling and unlabeled representation learning, serving as a cutting-edge paradigm with strong potential for scalability and privacy preservation. Although FSSL has garnered increasing attention, research indicates that it remains vulnerable to backdoor attacks. Existing methods generally rely on visually obvious triggers, which makes it difficult to meet the requirements for stealth and practicality in real-world deployment. In this paper, we propose an imperceptible and effective backdoor attack method against FSSL, called IPBA. Our empirical study reveals that existing imperceptible triggers face a series of challenges in FSSL, particularly limited transferability, feature entanglement with augmented samples, and out-of-distribution properties. These issues collectively undermine the effectiveness and stealthiness of traditional backdoor attacks in FSSL. To overcome these challenges, IPBA decouples the feature distributions of backdoor and augmented samples, and introduces Sliced-Wasserstein distance to mitigate the out-of-distribution properties of backdoor samples, thereby optimizing the trigger generation process. Our experimental results on several FSSL scenarios and datasets show that IPBA significantly outperforms existing backdoor attack methods in performance and exhibits strong robustness under various defense mechanisms.

cs.CR↗

arXiv2025

HybHuff: Lossless Compression for Hypergraphs via Entropy-Guided Huffman-Bitwise Coordination

Hypergraphs provide a natural representation for many-to-many relationships in data-intensive applications, yet their scalability is often hindered by high memory consumption. While prior work has improved computational efficiency, reducing the space overhead of hypergraph representations remains a major challenge. This paper presents a hybrid compression framework for integer-based hypergraph adjacency formats, which adaptively combines Huffman encoding and bitwise encoding to exploit structural redundancy. We provide a theoretical analysis showing that an optimal encoding ratio exists between the two schemes, and introduce an empirical strategy to approximate this ratio for practical use. Experiments on real-world hypergraphs demonstrate that our method consistently outperforms standard compressors such as Zip and ZFP in compression rate by up to 2.3x with comparable decoding overhead. To assess practical utility, we integrate our framework with three common hypergraph workloads: breadth-first search, PageRank, and k-core label propagation, and show that compression incurs negligible performance loss. Extensive evaluations across four benchmark datasets confirm the efficiency and applicability of our approach.

cs.DS↗

arXiv2025

Compile-Time Fully Homomorphic Encryption of Vectors: Eliminating Online Encryption via Algebraic Basis Synthesis

We propose a framework for compile-time ciphertext synthesis in fully homomorphic encryption (FHE) systems, where ciphertexts are constructed from precomputed encrypted basis vectors combined with a runtime-scaled encryption of zero. This design eliminates online encryption and instead relies solely on ciphertext-level additions and scalar multiplications, enabling efficient data ingestion and algebraic reuse. We formalize the method as a randomized $\mathbb{Z}_t$-module morphism and prove that it satisfies IND-CPA security under standard assumptions. The proof uses a hybrid game reduction, showing that adversarial advantage in distinguishing synthesized ciphertexts is negligible if the underlying FHE scheme is IND-CPA secure. Unlike prior designs that require a pool of random encryptions of zero, our construction achieves equivalent security using a single zero ciphertext multiplied by a fresh scalar at runtime, reducing memory overhead while preserving ciphertext randomness. The resulting primitive supports efficient integration with standard FHE APIs and maintains compatibility with batching, rotation, and aggregation, making it well-suited for encrypted databases, streaming pipelines, and secure compiler backends.

cs.CR↗