arXiv subjects

Shengjie Xu

Publications and source records attributed to Shengjie Xu.

At least 19 recordsLinked to original sources

arXiv2026

Season: Spectrum-Aware Orthogonal Gradient Refinement for Transfer-Based Adversarial Attacks

Transfer-based adversarial attacks often transfer poorly across heterogeneous architectures because CNNs favor local textures while Vision Transformers (ViTs) rely on global shapes. We propose Season, a spectrum-aware orthogonal gradient refinement framework for L-infinity transfer attacks against black-box target models on ImageNet, using a white-box surrogate. Season decomposes each update into a low-frequency branch capturing structural cues and a high-frequency branch capturing textures. A low-saliency guidance scheme reallocates high-frequency energy to background regions, preserving foreground structures that ViTs depend on. An orthogonal projection then forces the textural update to lie in the orthogonal complement of the structural direction, mitigating feature interference. As a training-free plug-and-play wrapper, Season enhances eight gradient-stabilization and input-enhancement attacks without modifying their cores. Across eight CNN, ViT, and MLP targets, Season improves transfer success rate by 6.6 percentage points on average and up to 16.0 points over strong baselines under a unified protocol.

cs.CV↗

arXiv2026

Adaptive primal dual hybrid gradient algorithms based on average spectrum for saddle point problems

The primal dual hybrid gradient algorithm (PDHG), which is also known as the Arrow-Hurwicz method, is a fundamental algorithm for saddle point problems especially in imaging. It also inspires a great number of influential algorithms such as the stochastic PDHG and the Chambolle-Pock's primal dual algorithm. In the literature, convergence theory of the PDHG is established only when some more restrictive conditions are additionally assumed, and it is proved that the PDHG with any constant step sizes could diverge for generic setting of convex saddle point problems. The Chambolle-Pock's primal dual algorithm, as an influential variant of the PDHG, is thus widely used due to its provable convergence theory and competitive numerical performance. However, step sizes of the Chambolle-Pock's primal dual algorithm are inherently bounded by its associated matrix spectrum, and this restriction could limit its computational capacity structurally. To address these limitations both in theory and practice, we propose a class of adaptive primal dual hybrid gradient algorithms for generic convex saddle point problems in this paper. By exploiting the prediction-correction algorithmic framework, the global convergence theory of the proposed schemes can be determined only by the average spectrum of the underlying matrix, and it thus leads to a potential acceleration. The numerical experiment on the assignment problem illustrates the superior numerical performance of the proposed method.

math.OC↗

arXiv2026

End-to-End Reverse Screening Identifies Protein Targets of Small Molecules Using HelixFold3

Identifying protein targets for small molecules, or reverse screening, is essential for understanding drug action, guiding compound repurposing, predicting off-target effects, and elucidating the molecular mechanisms of bioactive compounds. Despite its critical role, reverse screening remains challenging because accurately capturing interactions between a small molecule and structurally diverse proteins is inherently complex, and conventional step-wise workflows often propagate errors across decoupled steps such as target structure modeling, pocket identification, docking, and scoring. Here, we present an end-to-end reverse screening strategy leveraging HelixFold3, a high-accuracy biomolecular structure prediction model akin to AlphaFold3, which simultaneously models the folding of proteins from a protein library and the docking of small-molecule ligands within a unified framework. We validate this approach on a diverse and representative set of approximately one hundred small molecules. Compared with conventional reverse docking, our method improves screening accuracy and demonstrates enhanced structural fidelity, binding-site precision, and target prioritization. By systematically linking small molecules to their protein targets, this framework establishes a scalable and straightforward platform for dissecting molecular mechanisms, exploring off-target interactions, and supporting rational drug discovery.

q-bio.BM↗

arXiv2025

Emergence of Diverse Topological States in Ge Doped MnBi2Te4

As an ideal platform for studying interplays between symmetry, topology and magnetism, the magnetic topological insulator (MTI) MnBi2Te4 has attracted extensive attentions. However, its strong n-type intrinsic defects hinder the realizations of exotic phenomena. Stimulated by recent discoveries that Ge doping can efficiently tune the position of Fermi level, here we systematically investigate the band evolution and topological phase diagram with doping concentration from MTI MnBi2Te4 to strong topological insulator GeBi2Te4. Different from magnetically doped Bi2Se3, the topology here is determined by competition of two band inversions arising from band folding of two time-reversal invariant momenta between antiferromagnetic and nonmagnetic/ferromagnetic unit cells. By employing a band momentum mapping method, besides the known MTI phase, remarkably, we find two classes of magnetic Dirac semimetal phases at antiferromagnetic state, two classes of Weyl semimetal phases at ferromagnetic state, and an intermediate trivial state at different doping regions. Interestingly, the trivial state can be tuned into a Weyl phase with two coexisting band inversions and extraordinarily long Fermi arcs by a small strain. Our work reveals diverse topological states with intrinsic quantum phenomena can be achieved with great potential for designing future electronic devices.

cond-mat.mtrl-sci↗

arXiv2025

Controllable and Continuous Quantum Phase Transitions in Intrinsic Magnetic Topological Insulator

The intrinsic magnetic topological material MnBi2Te4 has demonstrated great potential to investigate the interplay between topology and magnetism, which opens up new avenues for manipulating non-trivial electronic states and designing quantum devices. However, challenges and controversies remain due to its inevitable n-type antisite defects, hindering the experimental realization of intrinsic magnetic topological phenomena and rendering the precise control of topological phase transitions (TPTs) unachievable. Here, we study a candidate material family, Mn(1-x)GexBi2Te4, in which the heavy n-type doping features are strongly suppressed when the Ge content reaches 0.46, and multiple topological phases are well maintained with the surface Dirac point located near the Fermi level. Based on angle-resolved photoemission spectroscopy, transport measurements, and first-principles calculations, we reveal two magnetism-induced TPTs: the first is antiferromagnetic-ordering-induced transition from strong topological insulator to a magnetic topological insulator as revealed by gap opening of topological surface states; the second is external-magnetic-field-dependent transition from magnetic topological insulator to a Weyl semimetal with the gap reclosed. Our work paves the way for the realization of intrinsic magnetic topological states in MnBi2Te4 family and provides an ideal platform for achieving controllable and continuous TPTs towards future spintronic applications.

cond-mat.mtrl-sci↗

arXiv2025

AEGIS: Towards Formalized and Practical Memory-Safe Execution of C programs via MSWASM

Programs written in unsafe languages such as C are prone to memory safety errors, which can lead to program compromises and serious real-world security consequences. Recently, Memory-Safe WebAssembly (MSWASM) is introduced as a general-purpose intermediate bytecode with built-in memory safety semantics. Programs written in C can be compiled into MSWASM to get complete memory safety protection. In this paper, we present our extensions on MSWASM, which improve its semantics and practicality. First, we formalize MSWASM semantics in Coq/Iris, extending it with inter-module interaction, showing that MSWASM provides fine-grained isolation guarantees analogous to WASM's coarse-grained isolation via linear memory. Second, we present Aegis, a system to adopt the memory safety of MSWASM for C programs in an interoperable way. Aegis pipeline generates Checked C source code from MSWASM modules to enforce spatial memory safety. Checked C is a recent binary-compatible extension of C which can provide guaranteed spatial safety. Our design allows Aegis to protect C programs that depend on legacy C libraries with no extra dependency and with low overhead. Aegis pipeline incurs 67% runtime overhead and near-zero memory overhead on PolyBenchC programs compared to native.

cs.PL↗

arXiv2025

Comparing Unidirectional, Bidirectional, and Word2vec Models for Discovering Vulnerabilities in Compiled Lifted Code

Ransomware and other forms of malware cause significant financial and operational damage to organizations by exploiting long-standing and often difficult-to-detect software vulnerabilities. To detect vulnerabilities such as buffer overflows in compiled code, this research investigates the application of unidirectional transformer-based embeddings, specifically GPT-2. Using a dataset of LLVM functions, we trained a GPT-2 model to generate embeddings, which were subsequently used to build LSTM neural networks to differentiate between vulnerable and non-vulnerable code. Our study reveals that embeddings from the GPT-2 model significantly outperform those from bidirectional models of BERT and RoBERTa, achieving an accuracy of 92.5% and an F1-score of 89.7%. LSTM neural networks were developed with both frozen and unfrozen embedding model layers. The model with the highest performance was achieved when the embedding layers were unfrozen. Further, the research finds that, in exploring the impact of different optimizers within this domain, the SGD optimizer demonstrates superior performance over Adam. Overall, these findings reveal important insights into the potential of unidirectional transformer-based approaches in enhancing cybersecurity defenses.

cs.CR↗

arXiv2025

Impact of Data Snooping on Deep Learning Models for Locating Vulnerabilities in Lifted Code

This study examines the impact of data snooping on neural networks used to detect vulnerabilities in lifted code, and builds on previous research that used word2vec and unidirectional and bidirectional transformer-based embeddings. The research specifically focuses on how model performance is affected when embedding models are trained with datasets, which include samples used for neural network training and validation. The results show that introducing data snooping did not significantly alter model performance, suggesting that data snooping had a minimal impact or that samples randomly dropped as part of the methodology contained hidden features critical to achieving optimal performance. In addition, the findings reinforce the conclusions of previous research, which found that models trained with GPT-2 embeddings consistently outperformed neural networks trained with other embeddings. The fact that this holds even when data snooping is introduced into the embedding model indicates GPT-2's robustness in representing complex code features, even under less-than-ideal conditions.

cs.CR↗

arXiv2024

Watertox: The Art of Simplicity in Universal Attacks A Cross-Model Framework for Robust Adversarial Generation

Contemporary adversarial attack methods face significant limitations in cross-model transferability and practical applicability. We present Watertox, an elegant adversarial attack framework achieving remarkable effectiveness through architectural diversity and precision-controlled perturbations. Our two-stage Fast Gradient Sign Method combines uniform baseline perturbations ($ε_1 = 0.1$) with targeted enhancements ($ε_2 = 0.4$). The framework leverages an ensemble of complementary architectures, from VGG to ConvNeXt, synthesizing diverse perspectives through an innovative voting mechanism. Against state-of-the-art architectures, Watertox reduces model accuracy from 70.6% to 16.0%, with zero-shot attacks achieving up to 98.8% accuracy reduction against unseen architectures. These results establish Watertox as a significant advancement in adversarial methodologies, with promising applications in visual security systems and CAPTCHA generation.

cs.CV↗

arXiv2024

Bi-Directional Transformers vs. word2vec: Discovering Vulnerabilities in Lifted Compiled Code

Detecting vulnerabilities within compiled binaries is challenging due to lost high-level code structures and other factors such as architectural dependencies, compilers, and optimization options. To address these obstacles, this research explores vulnerability detection using natural language processing (NLP) embedding techniques with word2vec, BERT, and RoBERTa to learn semantics from intermediate representation (LLVM IR) code. Long short-term memory (LSTM) neural networks were trained on embeddings from encoders created using approximately 48k LLVM functions from the Juliet dataset. This study is pioneering in its comparison of word2vec models with multiple bidirectional transformers (BERT, RoBERTa) embeddings built using LLVM code to train neural networks to detect vulnerabilities in compiled binaries. Word2vec Skip-Gram models achieved 92% validation accuracy in detecting vulnerabilities, outperforming word2vec Continuous Bag of Words (CBOW), BERT, and RoBERTa. This suggests that complex contextual embeddings may not provide advantages over simpler word2vec models for this task when a limited number (e.g. 48K) of data samples are used to train the bidirectional transformer-based models. The comparative results provide novel insights into selecting optimal embeddings for learning compiler-independent semantic code representations to advance machine learning detection of vulnerabilities in compiled binaries.

cs.CR↗

arXiv2024

Dumpling GNN: Hybrid GNN Enables Better ADC Payload Activity Prediction Based on Chemical Structure

Antibody-drug conjugates (ADCs) have emerged as a promising class of targeted cancer therapeutics, but the design and optimization of their cytotoxic payloads remain challenging. This study introduces DumplingGNN, a novel hybrid Graph Neural Network architecture specifically designed for predicting ADC payload activity based on chemical structure. By integrating Message Passing Neural Networks (MPNN), Graph Attention Networks (GAT), and GraphSAGE layers, DumplingGNN effectively captures multi-scale molecular features and leverages both 2D topological and 3D structural information. We evaluate DumplingGNN on a comprehensive ADC payload dataset focusing on DNA Topoisomerase I inhibitors, as well as on multiple public benchmarks from MoleculeNet. DumplingGNN achieves state-of-the-art performance across several datasets, including BBBP (96.4\% ROC-AUC), ToxCast (78.2\% ROC-AUC), and PCBA (88.87\% ROC-AUC). On our specialized ADC payload dataset, it demonstrates exceptional accuracy (91.48\%), sensitivity (95.08\%), and specificity (97.54\%). Ablation studies confirm the synergistic effects of the hybrid architecture and the critical role of 3D structural information in enhancing predictive accuracy. The model's strong interpretability, enabled by attention mechanisms, provides valuable insights into structure-activity relationships. DumplingGNN represents a significant advancement in molecular property prediction, with particular promise for accelerating the design and optimization of ADC payloads in targeted cancer therapy development.

q-bio.BM↗

arXiv2023

Next-Level, Robotic Telescope-Based Observing Experiences to Boost STEM Enrollments and Majors on a National Scale: Year 1 Report

Funded by a $3M Department of Defense (DoD) National Defense Education Program (NDEP) award, we are developing and deploying on a national scale a follow-up curriculum to "Our Place In Space!", or OPIS!, in which approx. 3,500 survey-level astronomy students are using our global network of "Skynet" robotic telescopes each year. The goal of this new curriculum, called "Astrophotography of the Multi-Wavelength Universe!", or MWU!, is to boost the number of these students who choose STEM majors. During Y1, our participating educators have developed MWU!'s (now renumbered) 2nd and 4th modules, and are in the process of developing its 3rd and 7th modules (out of 7). Solid progress has also been made on the software front, (1) where we have developed new graphing/analysis/modeling interfaces in support of Modules 2 and 4, and in response to feedback from the participating educators; and (2) where we are in the process of developing and adding astrophotography capabilities to Afterglow Access (AgA), our student-level, web-based, image processing and analysis application, in support of Modules 1 - 3 and 5 - 7. On the hardware front, development of our first four signal-processing units proceeds on schedule; these are key to Skynet's integration of a global network of radio telescopes, capable of exploring the invisible universe. Preparations have also been made on the evaluation and accessibility fronts, for when the first MWU! modules are deployed in Spring 2023.

astro-ph.IM↗

arXiv2022

A rank-two relaxed parallel splitting version of the augmented Lagrangian method with step size in (0,2) for separable convex programming

The augmented Lagrangian method (ALM) is classic for canonical convex programming problems with linear constraints, and it finds many applications in various scientific computing areas. A major advantage of the ALM is that the step for updating the dual variable can be further relaxed with a step size in $(0,2)$, and this advantage can easily lead to numerical acceleration for the ALM. When a separable convex programming problem is discussed and a corresponding splitting version of the classic ALM is considered, convergence may not be guaranteed and thus it is seemingly impossible that a step size in $(0,2)$ can be carried on to the relaxation step for updating the dual variable. We show that for a parallel splitting version of the ALM, a step size in $(0,2)$ can be maintained for further relaxing both the primal and dual variables if the relaxation step is simply corrected by a rank-two matrix. Hence, a rank-two relaxed parallel splitting version of the ALM with a step size in $(0,2)$ is proposed for separable convex programming problems. We validate that the new algorithm can numerically outperform existing algorithms of the same kind significantly by testing some applications.

math.OC↗

arXiv2022

The Study of Complex Human Locomotion Behaviors: From Crawling to Walking

This paper uses a simple state machine to develop a control algorithm for controlling an infant humanoid in the context of a simple model system. The algorithm is inspired by a baby who starts learning to stand and walk at 7 to 12 months of age: he or she initially learns to crawl and then, once the lower limb muscles are strong enough, can learn to walk by coming to support his or her upper trunk. Ideally, this algorithm-supported locomotion can take the baby to any desired location: a pile of toys, a tasty snack, or the baby's parents or relatives. In this paper we analyze the crawling stage, the simple 2d bipedal model, and the initial walking form from 8 to 18 months of age, and quantitatively evaluate the ideal kinematics model and simulation results for these stages.

cs.RO↗

arXiv2022

Indefinite linearized augmented Lagrangian method for convex programming with linear inequality constraints

The augmented Lagrangian method (ALM) is a benchmark for convex programming problems with linear constraints; ALM and its variants for linearly equality-constrained convex minimization models have been well studied in the literature. However, much less attention has been paid to ALM for efficiently solving linearly inequality-constrained convex minimization models. In this paper, we exploit an enlightening reformulation of the newly developed indefinite linearized ALM for the equality-constrained convex optimization problem, and present a new indefinite linearized ALM scheme for efficiently solving the convex optimization problem with linear inequality constraints. The proposed method enjoys great advantages, especially for large-scale optimization cases, in two folds mainly: first, it largely simplifies the challenging key subproblem of the classic ALM by employing its linearized reformulation, while keeping low complexity in computation; second, we show that only a smaller proximity regularization term is needed for provable convergence, which allows a bigger step-size and hence significantly better performance. Moreover, we show the global convergence of the proposed scheme upon its equivalent compact expression of prediction-correction, along with a worst-case $\mathcal{O}(1/N)$ convergence rate. Numerical results on some application problems demonstrate that a smaller regularization term can lead to a better experimental performance, which further confirms the theoretical results presented in this study.

math.OC↗

arXiv2021

A dual-primal balanced augmented Lagrangian method for linearly constrained convex programming

Most recently, He and Yuan [arXiv:2108.08554, 2021] have proposed a balanced augmented Lagrangian method (ALM) for the canonical convex programming problem with linear constraints, which advances the original ALM by balancing its subproblems and improving its implementation. In this short note, we propose a dual-primal version of the balanced ALM, which updates the new iterate via a conversely dual-primal iterative order formally. The proposed method inherits all advantages of the prototype balanced ALM, and its convergence analysis can be well conducted in the context of variational inequalities. In addition, its numerical efficiency is demonstrated by the basis pursuit problem.

math.OC↗

arXiv2021

A generalized primal-dual algorithm with improved convergence condition for saddle point problems

We generalize the well-known primal-dual algorithm proposed by Chambolle and Pock for saddle point problems, and improve the condition for ensuring its convergence. The improved convergence-guaranteeing condition is effective for the generic setting, and it is shown to be optimal. It also allows us to discern larger step sizes for the resulting subproblems, and thus provides a simple and universal way to improve numerical performance of the original primal-dual algorithm. In addition, we present a structure-exploring heuristic to further relax the convergence-guaranteeing condition for some specific saddle point problems, which could yield much larger step sizes and hence significantly better performance. Effectiveness of this heuristic is numerically illustrated by the classic assignment problem.

math.OC↗

arXiv2021

Extensions of ADMM for Separable Convex Optimization Problems with Linear Equality or Inequality Constraints

The alternating direction method of multipliers (ADMM) proposed by Glowinski and Marrocco is a benchmark algorithm for two-block separable convex optimization problems with linear equality constraints. It has been modified, specified, and generalized from various perspectives to tackle more concrete or complicated application problems. Despite its versatility and phenomenal popularity, it remains unknown whether or not the ADMM can be extended to separable convex optimization problems with linear inequality constraints. In this paper, we lay down the foundation of how to extend the ADMM to two-block and multiple-block (more than two blocks) separable convex optimization problems with linear inequality constraints. From a high-level and methodological perspective, we propose a unified framework of algorithmic design and a roadmap for convergence analysis in the context of variational inequalities, based on which it is possible to design a series of concrete ADMM-based algorithms with provable convergence in the prediction-correction structure. The proposed algorithmic framework and roadmap for convergence analysis are eligible to various convex optimization problems with different degrees of separability, in which both linear equality and linear inequality constraints can be included. The analysis is comprehensive yet can be presented by elementary mathematics, and hence generically understandable.

math.OC↗