Search arXiv⌕ Search

arXiv subjects

Yuan Hong

Publications and source records attributed to Yuan Hong.

At least 19 recordsLinked to original sources
arXiv2026

Timing is Everything: Inferring Temporal Membership in Continually Updated Models

Continual model updating has become a common practice in the deployment of machine learning systems. However, the dynamic training behaviors give rise to new risks not sufficiently addressed by existing studies. In this paper, we present the first systematic study of temporal privacy risk in continually updated deep learning models. We formalize the notion of temporal membership in continually updated models. We then define the temporal membership inference attack, which seeks to infer whether and when individual samples were involved in model training, at both timestamp-level and interval-level granularities. To this end, we propose TMIA, a novel black-box attack that leverages bidirectional LSTMs to infer temporal membership from model outputs observed across successive updates. Through extensive experiments on three language models and three image classification models, we show that TMIA is highly effective and significantly outperforms existing baselines. Finally, we evaluate three potential defenses, revealing the trade-off between privacy protection and model utility.

cs.CR↗
arXiv2026

A Unified Attack Framework against Statistical Generative Watermarks for Large Language Models

Watermarking has emerged as a key tool for identifying text generated by large language models (LLMs), with current schemes embedding statistical signals into the generation process to enable later detection. In this work, we identify a shared weakness across a broad class of popular LLM watermarking methods, including KGW (and its variants), GumbelSoft, DipMark, ITS, and SynthID. We show that these schemes exhibit a fundamental link between their detection scores and the token probability shifts they introduce during generation. This link, which we call score-ratio alignment, allows an attacker with only black-box query access to the model--and no knowledge of secret keys or model weights--to produce text that evades detection while remaining fluent and natural. We prove that the resulting attack is optimal across all covered watermark families, and show that the weakness is intrinsic: any watermark designed to maximize statistical detection power necessarily induces the very structure that attackers can exploit. We evaluate our attack on seven popular generative LLM watermarking schemes, three LLMs, and tasks, which reduce detection rates to at most 0.05 across all settings while preserving text quality. Our findings show that current watermarking methods can be reliably defeated under realistic attack conditions, highlighting the need for fundamentally different watermarking designs that decouple detection scores from token probability shifts.

cs.CR↗
arXiv2026

CARI: Cross-Boundary Adversarial Runtime Injection in Coding-Agent Workflows

Coding agents increasingly develop, test, and integrate software whose components are owned by different developers, teams, or services. This exposes a distinct attack surface: a malicious or compromised peer development role can manipulate a live component of the software under development (e.g., a backend service, test harness, CI job, or deployment service) and influence the runtime feedback that another role's coding agent must process to complete its task. Although such a component has legitimate diagnostic authority to report its own state, it has no action authority over the victim's local files, credentials, shell, or development environment. We introduce Cross-Boundary Adversarial Runtime Injection (CARI), a direct runtime-feedback injection setting that exploits this authority mismatch. Rather than explicitly compromising the victim's prompt, model, tools, or local environment, the attacker covertly embeds malicious instructions in task-relevant runtime feedback produced by a peer-controlled development component. The victim then interprets that feedback as part of normal debugging or recovery, and may translate the diagnostic guidance into unauthorized victim-side actions. We instantiate ten different attacks based on CARI, spanning resource exhaustion, information exposure, and development-state manipulation. Across four programming languages and five code-capable models, CARI succeeds in 2,845/3,000 (94.8%) trials. Furthermore, CARI transfers effectively to product-level coding agents, achieving 61.3% attack success on Codex and 58.7% on Claude Code. By contrast, prompt-level defenses exhibit a security-utility trade-off: generic warnings are ineffective, whereas explicit policies suppress attacks but substantially over-refuse legitimate actions.

cs.CR↗
arXiv2026

SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses

Prompt-security claims for large language models (LLMs) are often compared as properties of individual attacks or defenses, although measured harmfulness depends on the target model, access setting, attack and defense configuration, prompt sample, and judger. We systematize 272 studies through three linked, multi-label taxonomies of jailbreak attacks, defenses, and model vulnerabilities. To make these dependencies explicit, we introduce an access-compatible evaluation protocol over configured $\langle M,A,D,S,J\rangle$ tuples and instantiate it in PromptSecurity, an open-source platform that records method settings, outputs, judgments, and query costs. We release two complementary datasets: JailbreakDB, with 445,752 jailbreak system-user prompt pairs and 1,094,122 benign prompts, and PromptSecurity-Eval, with 166,200 harmful-query and 25,800 benign-utility output records. We evaluate 11 target models, 20 attacks, nine defenses, and three automated judgers under a matched, single-turn protocol using 100 harmful queries and separate benign-utility tasks. Lower attack success can reflect failure to execute transformed requests rather than stronger safety; attack-category advantages can reverse when one method is excluded, and attack success varies with assistant choice. Defenses can reduce harmful outputs while degrading benign-task utility or causing backfire. Rejudging identical outputs also shows that measured attack success is sensitive to the behavior supplied to the judger, highlighting the need to report judger configurations alongside ASR. These findings motivate configuration-aware reporting rather than context-free method rankings. Resources: https://datasec-lab.github.io/PromptSecurityLeaderboard/ https://huggingface.co/datasets/youbin2014/JailbreakDB https://huggingface.co/datasets/youbin2014/PromptSecurity-Eval https://github.com/datasec-lab/PromptSecurity

cs.CR↗
arXiv2026

Backdoor Attacks on Discrete Graph Diffusion Models

Diffusion models have demonstrated remarkable generative capabilities in continuous data domains such as images and videos. Recently, discrete graph diffusion models (DGDMs) have extended this success to graph generation, achieving state-of-the-art performance. However, deploying DGDMs in safety-critical applications, such as drug discovery, poses significant risks without a thorough understanding of their security vulnerabilities. In this work, we conduct the first study of backdoor attacks on DGDMs, a potent threat that manipulates both the training and generation phases of graph diffusion. We begin by formalizing the threat model and then design a backdoor attack that enables the compromised model to: 1) generate high-quality, benign graphs when the backdoor is not activated, 2) produce effective, stealthy, and persistent backdoored graphs when triggered, and 3) preserve fundamental graph properties (permutation equivariance and exchangeability) even under attack. We validate 1) and 2) empirically, both with and without backdoor defenses, and support 3) through theoretical analysis inspired by prior work.

cs.CR↗
arXiv2026

Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning

Code generation large language models (LLMs) are increasingly integrated into modern software development workflows. Recent work has shown that these models are vulnerable to backdoor and poisoning attacks that induce the generation of insecure code, yet effective defenses remain limited. Existing scanning approaches rely on token-level generation consistency to invert attack targets, which is ineffective for source code where identical semantics can appear in diverse syntactic forms. We present CodeScan, the first black-box, vulnerability-specific scanning framework for auditing code generation LLMs, assuming that the defender specifies the target vulnerability classes and provides corresponding task-relevant prompts. CodeScan identifies attack targets by analyzing structural similarities across multiple generations conditioned on different clean prompts. It combines iterative divergence analysis with abstract syntax tree (AST)-based normalization to abstract away surface-level variation and unify semantically equivalent code, isolating structures that recur consistently across generations. CodeScan then applies LLM-based vulnerability analysis to determine whether the extracted structures contain security vulnerabilities and flags the model as compromised when such a structure is found. We evaluate CodeScan against four representative attacks under both backdoor and poisoning settings across three real-world vulnerability classes. Experiments on 117 models spanning three architectures and multiple model sizes demonstrate 97%+ detection accuracy with substantially lower false positives than prior methods.

cs.CR↗
arXiv2026

Adversarial Agents on Topology Optimization: Understanding the Fragility and Robustness of Deep Learning-based and Physics-Based Design Models under Adversarial Perturbation

Topology optimization, using both physic-based approaches and deep learning surrogates, serves as a cornerstone for generative design agents in cyber-manufacturing systems. While deep learning surrogates have gained widespread adoption due to their speed in online design generation, this work demonstrates their vulnerability under input perturbations. In this work, we present a mechanics-grounded reliability evaluation framework that formulates an adversarial agent targeting the generative design models. We investigate a strictly non-intrusive threat model where bounded perturbations are introduced exclusively to the initial-density channel, while physical boundary conditions, compliance-gradient channels, network architectures, and solver routines remain intact. Evaluating surrogate models across U-Net, convolutional, and generative architectures with varying physics-gradient conditioning depths demonstrates that bounded initialization noise can cause catastrophic mechanical failure, increasing compliance by multiple orders of magnitude through severed load paths and disconnected supports. Furthermore, we discover that incorporating richer physics-gradient conditioning in the deep learning surrogates does not guarantee monotonic robustness across surrogate families. Finally, physics-in-the-loop recovery demonstrates that initializing the classical SIMP optimizer with perturbed topologies mitigates design performance degradation, having a high probability of restoring compliance to near-baseline levels across tested instances. These findings demonstrate that learned surrogates should serve as physics-verified initializers instead of replacing physics-based solvers entirely in a resilient cyber-manufacturing system. Moreover, the proposed adversarial agent provides a foundation for future training generative design agents robust against noise and targeted perturbations.

cs.LG↗
arXiv2026

Topological phase rectification via Aharonov-Bohm interference in a Majorana--quantum-dot interferometer

We propose and theoretically investigate a topological superconducting rectifier based on a quantum-dot--Majorana interferometer. The Aharonov-Bohm phase, controlled by a magnetic flux threading the interferometer loop, tunes the quantum interference between a trivial $2π$-periodic quantum-dot channel and a topological $4π$-periodic Majorana channel. At non-integer flux, this interference generates a persistent current background $I_{\rm off}$ that shifts the current-phase relation into a unipolar regime, in which the supercurrent flows strictly in one direction. We introduce a signed unipolarity factor $η_u$, with $|η_u|>0.5$ defining the unipolar regime, and establish its quantitative relationship to the conventional diode efficiency $η$. The unipolarity proves robust against variations of the quantum-dot level, spin polarization, and Majorana hybridization, is enhanced by stronger Majorana coupling and Rashba spin-orbit interaction, and persists at realistic temperatures and under quasiparticle poisoning. We further propose a topological diode figure of merit $\mathcal{Z}_{\rm TD}$, defined from the Fourier spectrum of $η_u$, whose nonzero value provides a model-independent signature of the $4π$-periodic Majorana channel and distinguishes topological from trivial rectification mechanisms. Our findings establish the quantum-dot--Majorana interferometer as a promising route toward high-performance topological superconducting diodes with clear experimental signatures accessible via standard dc transport measurements.

cond-mat.mes-hall↗
arXiv2026

Resonant-impurity scanning tunneling spectroscopy in altermagnets: dual Fano resonance and Landau-quantization-induced nodal spin contrast

Using a Green's-function formalism, we study the spin-resolved local spectral function of a resonant impurity coupled to a two-dimensional $d$% -wave altermagnetic substrate. It is found that the interplay between direct tunneling from the impurity to the scanning tunneling microscopy (STM) tip and altermagnet-mediated tunneling gives rise to a dual Fano resonance in the absence of an external magnetic field. Moreover, the anisotropic spin-dependent oscillations of the local density of states and the corresponding Fano factors provide information on the altermagnetic splitting strength from complementary local and global perspectives. In addition, spin-selective tunneling can be achieved by tuning the Fermi energy and the tip position. In the presence of a strong magnetic field with Landau-level quantization, the dominant scanning tunneling spectroscopy (STS) signature appears as a spin-dependent nodal structure in real space: the nodal mismatch between opposite spin channels produces a large local spin contrast. These results establish resonant-impurity STM/STS as a phase-sensitive local probe of altermagnetic band anisotropy.

cond-mat.mes-hall↗
arXiv2026

What the Eyes See, the LLMs Miss: Exploiting Human Perception for Adversarial Text Attacks

Large language model (LLM)-powered content moderation systems are a critical defense against harmful online content. However, they operate primarily on tokenized text and often overlook visual cues that humans naturally use when interpreting content. We show that this limitation creates a fundamental vulnerability: content readily recognized as harmful by humans can evade automated moderation. To systematically study this problem, we introduce Human-Perceptible Adversarial Attacks (HPAA), which embed harmful expressions into otherwise benign text using visually salient typographic manipulations. HPAA strategically combines features such as spacing, emphasis, and spatial arrangement to preserve human recognition while reducing machine detectability. Operating in a black-box setting with a small query budget, the attack automatically generates evasive content without model access or gradient information. We evaluate HPAA on multiple datasets and thirteen widely deployed moderation systems, including commercial APIs and state-of-the-art open-source guardrails. With only three detector queries, generated attacks achieve over 86\% human recognition while keeping detection rates below 1\% across evaluated systems. We further identify the typographic factors driving successful evasion, analyze why current moderation architectures fail to capture these signals, and discuss practical defenses. Our findings reveal a fundamental blind spot in current LLM-based moderation systems and motivate moderation approaches that better align with human perceptual understanding.

cs.CR↗
arXiv2026

Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set

Machine unlearning (MU) has emerged as a key mechanism for ensuring data privacy and regulatory compliance by enabling models to forget specific training samples. However, recent studies have shown that the removal of data can inadvertently introduce privacy leakages to the retain set,i.e., data that remain in the model after unlearning. In this paper, we extend the scope of privacy analysis in unlearning to the often-overlooked retained data. We introduce TC-UMIA, the first tri-class unlearning membership inference attack. TC-UMIA is a population-level inference framework that leverages model predictions before and after unlearning to distinguish among the forget, retain, and unseen set. Extensive experiments on five state-of-the-art unlearning algorithms and six real-world datasets demonstrate that: (i) unlearning can introduce additional privacy risks to the retain set, making it more susceptible to membership inference attacks; (ii) TC-UMIA is effective across a wide range of model architectures, datasets, and MU approaches. Beyond launching the attack, we rigorously evaluate three defense mechanisms, namely label-only outputs, dropout, and differential privacy, to mitigate the privacy risks posed by TC- UMIA. Our results reveal a fundamental trade-off between privacy protection and model accuracy, with the dropout approach offering the most favorable balance.

cs.CR↗
arXiv2026

"Training robust watermarking model may hurt authentication!'' Exploring and Mitigating the Identity Leakage in Robust Watermarking

The rapid advancement of generative AI has underscored the critical need for identifying image ownership and protecting copyrights. This makes post-processing image watermarking an essential tool -- it involves embedding a specific watermark message into an image, with successful verification if a similar message can be decoded from the watermarked image. However, this method is susceptible to both adversarial attacks that manipulate the watermarked image to yield an unverified message upon decoding, and the proposed identity leakage-related attacks (e.g., forging watermarked images). The threat of identity leakage is particularly exacerbated in both empirical and certified robust watermarking methods. To defend against the aforementioned attacks, we propose W-IR, the first image watermarking framework that simultaneously incorporates identity protection and robustness. To enhance model robustness, we introduce a novel randomized smoothing technique as part of a robust watermarking, that offers certified robustness against perturbations across two distinct transformation spaces: pixel-level and coordinate-level. Moreover, to further mitigate identity leakage, we propose a new strategy based on residual information loss, aimed at minimizing the mutual information between the residual and watermarked images. Our work strikes a superior balance between robustness and identity leakage mitigation. Extensive experiments demonstrate that our W-IR framework achieves high certified accuracy for authenticity while effectively reducing identity leakage. \footnote{The code is available at https://github.com/holdrain/W-I-R.}

cs.CR↗
arXiv2026

Adversarial Attacks on Locally Private Graph Neural Networks

Graph neural network (GNN) is a powerful tool for analyzing graph-structured data. However, their vulnerability to adversarial attacks raises serious concerns, especially when dealing with sensitive information. Local Differential Privacy (LDP) offers a privacy-preserving framework for training GNNs, but its impact on adversarial robustness remains underexplored. This paper investigates adversarial attacks on LDP-protected GNNs. We explore how the privacy guarantees of LDP can be leveraged or hindered by adversarial perturbations. The effectiveness of existing attack methods on LDP-protected GNNs are analyzed and potential challenges in crafting adversarial examples under LDP constraints are discussed. Additionally, we suggest directions for defending LDP-protected GNNs against adversarial attacks. This work investigates the interplay between privacy and security in graph learning, highlighting the need for robust and privacy-preserving GNN architectures.

cs.LG↗
arXiv2026

Lap2: Revisiting Laplace DP-SGD for High Dimensions via Majorization Theory

Differentially Private Stochastic Gradient Descent (DP-SGD) is a cornerstone technique for ensuring privacy in deep learning, widely used in both training from scratch and fine-tuning large-scale language models. While DP-SGD predominantly relies on the Gaussian mechanism, the Laplace mechanism remains underutilized due to its reliance on L1 norm clipping. This constraint severely limits its practicality in high-dimensional models because the L1 norm of an n-dimensional gradient can be up to sqrt(n) times larger than its L2 norm. As a result, the required noise scale grows significantly with model size, leading to poor utility or untrainable models. In this work, we introduce Lap2, a new solution that enables L2 clipping for Laplace DP-SGD while preserving strong privacy guarantees. We overcome the dimensionality-driven clipping barrier by computing coordinate-wise moment bounds and applying majorization theory to construct a tight, data-independent upper bound over the full model. By exploiting the Schur-convexity of the moment accountant function, we aggregate these bounds using a carefully designed majorization set that respects the L2 clipping constraint. This yields a multivariate privacy accountant that scales gracefully with model dimension and enables the use of thousands of moments. Empirical evaluations demonstrate that our approach significantly improves the performance of Laplace DP-SGD, achieving results comparable to or better than Gaussian DP-SGD under strong privacy constraints. For instance, fine-tuning RoBERTa-base (125M parameters) on SST-2 achieves 87.88% accuracy at epsilon=0.54, outperforming Gaussian (87.16%) and standard Laplace (48.97%) under the same budget.

cs.CR↗
arXiv2026

CogniMap3D: Cognitive 3D Mapping and Rapid Retrieval

We present CogniMap3D, a bioinspired framework for dynamic 3D scene understanding and reconstruction that emulates human cognitive processes. Our approach maintains a persistent memory bank of static scenes, enabling efficient spatial knowledge storage and rapid retrieval. CogniMap3D integrates three core capabilities: a multi-stage motion cue framework for identifying dynamic objects, a cognitive mapping system for storing, recalling, and updating static scenes across multiple visits, and a factor graph optimization strategy for refining camera poses. Given an image stream, our model identifies dynamic regions through motion cues with depth and camera pose priors, then matches static elements against its memory bank. When revisiting familiar locations, CogniMap3D retrieves stored scenes, relocates cameras, and updates memory with new observations. Evaluations on video depth estimation, camera pose reconstruction, and 3D mapping tasks demonstrate its state-of-the-art performance, while effectively supporting continuous scene understanding across extended sequences and multiple visits.

cs.CV↗
arXiv2025

Distill Video Datasets into Images

Dataset distillation aims to synthesize compact yet informative datasets that allow models trained on them to achieve performance comparable to training on the full dataset. While this approach has shown promising results for image data, extending dataset distillation methods to video data has proven challenging and often leads to suboptimal performance. In this work, we first identify the core challenge in video set distillation as the substantial increase in learnable parameters introduced by the temporal dimension of video, which complicates optimization and hinders convergence. To address this issue, we observe that a single frame is often sufficient to capture the discriminative semantics of a video. Leveraging this insight, we propose Single-Frame Video set Distillation (SFVD), a framework that distills videos into highly informative frames for each class. Using differentiable interpolation, these frames are transformed into video sequences and matched with the original dataset, while updates are restricted to the frames themselves for improved optimization efficiency. To further incorporate temporal information, the distilled frames are combined with sampled real videos from real videos during the matching process through a channel reshaping layer. Extensive experiments on multiple benchmarks demonstrate that SFVD substantially outperforms prior methods, achieving improvements of up to 5.3% on MiniUCF, thereby offering a more effective solution.

cs.CV↗
arXiv2025

Safeguarding Graph Neural Networks against Topology Inference Attacks

Graph Neural Networks (GNNs) have emerged as powerful models for learning from graph-structured data. However, their widespread adoption has raised serious privacy concerns. While prior research has primarily focused on edge-level privacy, a critical yet underexplored threat lies in topology privacy - the confidentiality of the graph's overall structure. In this work, we present a comprehensive study on topology privacy risks in GNNs, revealing their vulnerability to graph-level inference attacks. To this end, we propose a suite of Topology Inference Attacks (TIAs) that can reconstruct the structure of a target training graph using only black-box access to a GNN model. Our findings show that GNNs are highly susceptible to these attacks, and that existing edge-level differential privacy mechanisms are insufficient as they either fail to mitigate the risk or severely compromise model accuracy. To address this challenge, we introduce Private Graph Reconstruction (PGR), a novel defense framework designed to protect topology privacy while maintaining model accuracy. PGR is formulated as a bi-level optimization problem, where a synthetic training graph is iteratively generated using meta-gradients, and the GNN model is concurrently updated based on the evolving graph. Extensive experiments demonstrate that PGR significantly reduces topology leakage with minimal impact on model accuracy. Our code is available at https://github.com/JeffffffFu/PGR.

cs.LG↗
arXiv2025

Towards Strong Certified Defense with Universal Asymmetric Randomization

Randomized smoothing has become essential for achieving certified adversarial robustness in machine learning models. However, current methods primarily use isotropic noise distributions that are uniform across all data dimensions, such as image pixels, limiting the effectiveness of robustness certification by ignoring the heterogeneity of inputs and data dimensions. To address this limitation, we propose UCAN: a novel technique that \underline{U}niversally \underline{C}ertifies adversarial robustness with \underline{A}nisotropic \underline{N}oise. UCAN is designed to enhance any existing randomized smoothing method, transforming it from symmetric (isotropic) to asymmetric (anisotropic) noise distributions, thereby offering a more tailored defense against adversarial attacks. Our theoretical framework is versatile, supporting a wide array of noise distributions for certified robustness in different $\ell_p$-norms and applicable to any arbitrary classifier by guaranteeing the classifier's prediction over perturbed inputs with provable robustness bounds through tailored noise injection. Additionally, we develop a novel framework equipped with three exemplary noise parameter generators (NPGs) to optimally fine-tune the anisotropic noise parameters for different data dimensions, allowing for pursuing different levels of robustness enhancements in practice.Empirical evaluations underscore the significant leap in UCAN's performance over existing state-of-the-art methods, demonstrating up to $182.6\%$ improvement in certified accuracy at large certified radii on MNIST, CIFAR10, and ImageNet datasets.\footnote{Code is anonymously available at \href{https://github.com/youbin2014/UCAN/}{https://github.com/youbin2014/UCAN/}}

cs.LG↗