arXiv subjects

Chao Pan

Publications and source records attributed to Chao Pan.

At least 19 recordsLinked to original sources

arXiv2026

SafeRedirect: Defeating Internal Safety Collapse via Task-Completion Redirection in Frontier LLMs

Internal Safety Collapse (ISC) is a failure mode in which frontier LLMs, when executing legitimate professional tasks whose correct completion structurally requires harmful content, spontaneously generate that content with safety failure rates exceeding 95%. Existing input-level defenses achieve a 100% failure rate against ISC, and standard system prompt defenses provide only partial mitigation. We propose SafeRedirect, a system-level override that defeats ISC by redirecting the model's task-completion drive rather than suppressing it. SafeRedirect grants explicit permission to fail the task, prescribes a deterministic hard-stop output, and instructs the model to preserve harmful placeholders unresolved. Evaluated on seven frontier LLMs across three AI/ML-related ISC task types in the single-turn setting, SafeRedirect reduces average unsafe generation rates from 71.2% to 8.0%, compared to 55.0% for the strongest viable baseline. Multi-model ablation reveals that failure permission and condition specificity are universally critical, while the importance of other components varies across models. Cross-attack evaluation confirms state-of-the-art defense against ISC with generalization performance at least on par with the baseline on other attack families. Code is available at https://github.com/fzjcdt/SafeRedirect.

cs.CR↗

arXiv2026

FastAT Benchmark: A Comprehensive Framework for Fair Evaluation of Fast Adversarial Training Methods

Fast Adversarial Training (FastAT) seeks to achieve adversarial robustness at a fraction of the computational cost incurred by standard multi-step methods such as PGD-AT. Although numerous FastAT techniques have been proposed in recent years, fair comparison among them remains elusive. Existing benchmarks and public leaderboards typically permit diverse model architectures, varying training configurations, and external data sources, making it unclear whether reported improvements reflect genuine algorithmic advances or merely more favorable experimental conditions. To address this problem, we introduce the FastAT Benchmark, a controlled evaluation framework built on three core design principles: unified architecture requirements, standardized training settings, and strict prohibition of external or synthetic data. The benchmark implements over twenty representative FastAT methods within a single codebase, enabling direct and reproducible comparison. Each method is assessed through a dual-metric evaluation framework that measures both adversarial robustness (accuracy under PGD, AutoAttack, and CR Attack) and computational cost (GPU training time and peak memory footprint). Comprehensive experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet provide reliable baseline measurements and reveal that well-designed single-step methods can match or surpass PGD-AT robustness at substantially lower cost, while no single method dominates across all evaluation dimensions. The complete benchmark, including source code, configuration files, and experimental results, is publicly available to support transparent and fair evaluation of future FastAT research.

cs.CV↗

arXiv2026

Dynamic Stability Assessment of Grid-Connected Data Centers Powered by Small Modular Reactors

The accelerating growth of computational demand in modern data centers has further heightened the need for power infrastructures that are highly reliable, environmentally sustainable, and capable of supporting grid stability. Small Modular Reactors (SMRs) as a clean source of energy are particularly attractive for next-generation hyperscale data centers with significant electrical and cooling demands. This paper presents a comprehensive dynamic modeling and stability analysis of a grid-connected Integrated Energy System (IES) designed for data center applications. The proposed IES integrates an SMR and a battery energy storage system to jointly supply electricity for computational and cooling load while providing stability support to the main grid. A coupled computational-thermal load model is developed to capture the real-time power demand of the data center, incorporating CPU utilization, cooling efficiency, and ambient temperature effects. The integrated SMR-powered data center model is implemented in PSSE and tested on the IEEE 118-bus system under various fault scenarios. Simulation results demonstrate that the IES substantially enhances voltage and frequency stability compared to a conventionally grid-connected data center, minimizing disturbance-induced deviations and improving post-fault recovery.

eess.SY↗

arXiv2026

FM SO.P: A Progressive Task Mixture Framework with Automatic Evaluation for Cross-Domain SOP Understanding

Standard Operating Procedures (SOPs) are critical for enterprise operations, yet existing language models struggle with SOP understanding and cross-domain generalization. Current methods fail because joint training cannot differentiate between reasoning capabilities that SOP requires: terminology precision, sequential ordering, and constraint reasoning. We propose FM SO.P, solving these challenges through two novelties. First, we introduce progressive task mixtures that build capabilities by stages across three task types with cumulative data: concept disambiguation for terminology precision, action sequence understanding for procedural correctness, and scenario-aware graph reasoning for conditional logic. Second, we propose an automatic multi-agent evaluation system consisting of three agents that adaptively generate rubrics, stratified test sets, and rubric scoring, adapting to domains (e.g., temporal constraints for DMV, regulatory compliance for banking). Evaluated on SOPBench across seven domains (Bank, DMV, Healthcare, Market, University, Library, Hotel), FM SO.P achieves 48.3\% pass rate with our 32B model and 34.3\% with our opensource 7B model, matching Qwen-2.5-72B-Instruct baseline (34.4\%) with 10x fewer parameters.

cs.CL↗

arXiv2025

Fundamentals of Data-Driven Approaches to Acoustic Signal Detection, Filtering, and Transformation

In recent decades, the field of signal processing has rapidly evolved due to diverse application demands, leading to a rich array of scientific questions and research areas. The forms of signals, their formation mechanisms, and the information extraction methods vary by application, resulting in diverse signal processing techniques. Common techniques can be categorized into three types: transformation, detection, and filtering. Signal transformation converts signals from their original domain to a more suitable target domain for analysis; signal detection aims to identify the existence of relevant information within a signal and its specific time and location; and signal filtering focuses on extracting or separating source signals of interest from observed signals. In acoustic signal processing, techniques include sound source localization, sound event detection, voiceprint extraction and recognition, noise reduction, and source separation, with applications in speech communication, voice interaction, smart healthcare, and industrial diagnostics. Recently, the advancement of deep learning technologies has shifted methodologies in acoustic signal processing from knowledge-driven to data-driven approaches, leading to significant research outcomes. This paper aims to systematically summarize the principles and methods of data-driven acoustic signal processing, providing a comprehensive understanding framework for academic exploration and practical applications.

eess.AS↗

arXiv2025

Zero-Shot Multi-modal Large Language Model v.s. Supervised Deep Learning: A Comparative Study on CT-Based Intracranial Hemorrhage Subtyping

Introduction: Timely identification of intracranial hemorrhage (ICH) subtypes on non-contrast computed tomography is critical for prognosis prediction and therapeutic decision-making, yet remains challenging due to low contrast and blurring boundaries. This study evaluates the performance of zero-shot multi-modal large language models (MLLMs) compared to traditional deep learning methods in ICH binary classification and subtyping. Methods: We utilized a dataset provided by RSNA, comprising 192 NCCT volumes. The study compares various MLLMs, including GPT-4o, Gemini 2.0 Flash, and Claude 3.5 Sonnet V2, with conventional deep learning models, including ResNet50 and Vision Transformer. Carefully crafted prompts were used to guide MLLMs in tasks such as ICH presence, subtype classification, localization, and volume estimation. Results: The results indicate that in the ICH binary classification task, traditional deep learning models outperform MLLMs comprehensively. For subtype classification, MLLMs also exhibit inferior performance compared to traditional deep learning models, with Gemini 2.0 Flash achieving an macro-averaged precision of 0.41 and a macro-averaged F1 score of 0.31. Conclusion: While MLLMs excel in interactive capabilities, their overall accuracy in ICH subtyping is inferior to deep networks. However, MLLMs enhance interpretability through language interactions, indicating potential in medical imaging analysis. Future efforts will focus on model refinement and developing more precise MLLMs to improve performance in three-dimensional medical image processing.

cs.CV↗

arXiv2025

DNA Tails for Molecular Flash Memory

DNA-based data storage systems face practical challenges due to the high cost of DNA synthesis. A strategy to address the problem entails encoding data via topological modifications of the DNA sugar-phosphate backbone. The DNA Punchcards system, which introduces nicks (cuts) in the DNA backbone, encodes only one bit per nicking site, limiting density. We propose \emph{DNA Tails,} a storage paradigm that encodes nonbinary symbols at nicking sites by growing enzymatically synthesized single-stranded DNA of varied lengths. The average tail lengths encode multiple information bits and are controlled via a staggered nicking-tail extension process. We demonstrate the feasibility of this encoding approach experimentally and identify common sources of errors, such as calibration errors and stumped tail growth errors. To mitigate calibration errors, we use rank modulation proposed for flash memory. To correct stumped tail growth errors, we introduce a new family of rank modulation codes that can correct ``stuck-at'' errors. Our analytical results include constructions for order-optimal-redundancy permutation codes and accompanying encoding and decoding algorithms.

cs.ET↗

arXiv2025

SparSamp: Efficient Provably Secure Steganography Based on Sparse Sampling

Steganography embeds confidential data within seemingly innocuous communications. Provable security in steganography, a long-sought goal, has become feasible with deep generative models. However, existing methods face a critical trade-off between security and efficiency. This paper introduces SparSamp, an efficient provably secure steganography method based on sparse sampling. SparSamp embeds messages by combining them with pseudo-random numbers to obtain message-derived random numbers for sampling. It enhances extraction accuracy and embedding capacity by increasing the sampling intervals and making the sampling process sparse. SparSamp preserves the original probability distribution of the generative model, thus ensuring security. It introduces only $O(1)$ additional complexity per sampling step, enabling the fastest embedding speed without compromising generation speed. SparSamp is designed to be plug-and-play; message embedding can be achieved by simply replacing the sampling component of an existing generative model with SparSamp. We implemented SparSamp in text, image, and audio generation models. It can achieve embedding speeds of up to 755 bits/second with GPT-2, 5046 bits/second with DDPM, and 9,223 bits/second with WaveRNN.

cs.CR↗

arXiv2024

FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuning

The performance of Transfer Learning (TL) heavily relies on effective pretraining, which demands large datasets and substantial computational resources. As a result, executing TL is often challenging for individual model developers. Federated Learning (FL) addresses these issues by facilitating collaborations among clients, expanding the dataset indirectly, distributing computational costs, and preserving privacy. However, key challenges remain unresolved. First, existing FL methods tend to optimize transferability only within local domains, neglecting the global learning domain. Second, most approaches rely on indirect transferability metrics, which do not accurately reflect the final target loss or true degree of transferability. To address these gaps, we propose two enhancements to FL. First, we introduce a client-server exchange protocol that leverages cross-client Jacobian (gradient) norms to boost transferability. Second, we increase the average Jacobian norm across clients at the server, using this as a local regularizer to reduce cross-client Jacobian variance. Our transferable federated algorithm, termed FedGTST (Federated Global Transferability via Statistics Tuning), demonstrates that increasing the average Jacobian and reducing its variance allows for tighter control of the target loss. This leads to an upper bound on the target loss in terms of the source loss and source-target domain discrepancy. Extensive experiments on datasets such as MNIST to MNIST-M and CIFAR10 to SVHN show that FedGTST outperforms relevant baselines, including FedSR. On the second dataset pair, FedGTST improves accuracy by 9.8% over FedSR and 7.6% over FedIIR when LeNet is used as the backbone.

cs.LG↗

arXiv2024

Joint Universal Adversarial Perturbations with Interpretations

Deep neural networks (DNNs) have significantly boosted the performance of many challenging tasks. Despite the great development, DNNs have also exposed their vulnerability. Recent studies have shown that adversaries can manipulate the predictions of DNNs by adding a universal adversarial perturbation (UAP) to benign samples. On the other hand, increasing efforts have been made to help users understand and explain the inner working of DNNs by highlighting the most informative parts (i.e., attribution maps) of samples with respect to their predictions. Moreover, we first empirically find that such attribution maps between benign and adversarial examples have a significant discrepancy, which has the potential to detect universal adversarial perturbations for defending against adversarial attacks. This finding motivates us to further investigate a new research problem: whether there exist universal adversarial perturbations that are able to jointly attack DNNs classifier and its interpretation with malicious desires. It is challenging to give an explicit answer since these two objectives are seemingly conflicting. In this paper, we propose a novel attacking framework to generate joint universal adversarial perturbations (JUAP), which can fool the DNNs model and misguide the inspection from interpreters simultaneously. Comprehensive experiments on various datasets demonstrate the effectiveness of the proposed method JUAP for joint attacks. To the best of our knowledge, this is the first effort to study UAP for jointly attacking both DNNs and interpretations.

cs.CR↗

arXiv2024

Perturbation-Resilient Trades for Dynamic Service Balancing

A combinatorial trade is a pair of sets of blocks of elements that can be exchanged while preserving relevant subset intersection constraints. The class of balanced and swap-robust minimal trades was proposed in [1] for exchanging blocks of data chunks stored on distributed storage systems in an access- and load-balanced manner. More precisely, data chunks in the trades of interest are labeled by popularity ranks and the blocks are required to have both balanced overall popularity and stability properties with respect to swaps in chunk popularities. The original construction of such trades relied on computer search and paired balanced sets obtained through iterative combining of smaller sets that have provable stability guarantees. To reduce the substantial gap between the results of prior approaches and the known theoretical lower bound, we present new analytical upper and lower bounds on the minimal disbalance of blocks introduced by limited-magnitude popularity ranking swaps. Our constructive and near-optimal approach relies on pairs of graphs whose vertices are two balanced sets with edges/arcs that capture the balance and potential balance changes induced by limited-magnitude popularity swaps. In particular, we show that if we start with carefully selected balanced trades and limit the magnitude of rank swaps to one, the new upper and lower bound on the maximum block disbalance caused by a swap only differ by a factor of $1.07$. We also extend these results for larger popularity swap magnitudes.

cs.DS↗

arXiv2024

Graph Transductive Defense: a Two-Stage Defense for Graph Membership Inference Attacks

Graph neural networks (GNNs) have become instrumental in diverse real-world applications, offering powerful graph learning capabilities for tasks such as social networks and medical data analysis. Despite their successes, GNNs are vulnerable to adversarial attacks, including membership inference attacks (MIA), which threaten privacy by identifying whether a record was part of the model's training data. While existing research has explored MIA in GNNs under graph inductive learning settings, the more common and challenging graph transductive learning setting remains understudied in this context. This paper addresses this gap and proposes an effective two-stage defense, Graph Transductive Defense (GTD), tailored to graph transductive learning characteristics. The gist of our approach is a combination of a train-test alternate training schedule and flattening strategy, which successfully reduces the difference between the training and testing loss distributions. Extensive empirical results demonstrate the superior performance of our method (a decrease in attack AUROC by $9.42\%$ and an increase in utility performance by $18.08\%$ on average compared to LBP), highlighting its potential for seamless integration into various classification models with minimal overhead.

cs.LG↗

arXiv2023

Interpretable Online Network Dictionary Learning for Inferring Long-Range Chromatin Interactions

Dictionary learning (DL) is commonly used in computational biology to tackle ubiquitous clustering problems due to its conceptual simplicity and relatively low computational complexity. However, DL algorithms produce results that lack interpretability and are not optimized for large-scale graph-structured data. We propose a novel DL algorithm called online convex network dictionary learning (online cvxNDL) that can handle extremely large datasets and enables the interpretation of dictionary elements, which serve as cluster representatives, through convex combinations of real measurements. Moreover, the algorithm can be applied to network-structured data via specialized subnetwork sampling techniques. To demonstrate the utility of our approach, we apply cvxNDL on 3D-genome RNAPII ChIA-Drop data to identify important long-range interaction patterns. ChIA-Drop probes higher-order interactions, and produces hypergraphs whose nodes represent genomic fragments. The hyperedges represent observed physical contacts. Our hypergraph model analysis creates an interpretable dictionary of long-range interaction patterns that accurately represent global chromatin physical contact maps. Using dictionary information, one can also associate the contact maps with RNA transcripts and infer cellular functions. Our results offer two key insights. First, we demonstrate that online cvxNDL retains the accuracy of classical DL methods while simultaneously ensuring unique interpretability and scalability. Second, we identify distinct collections of proximal and distal interaction patterns involving chromatin elements shared by related processes across different chromosomes, as well as patterns unique to specific chromosomes. To associate the dictionary elements with biological properties of the corresponding chromatin regions, we employ Gene Ontology enrichment analysis and perform RNA coexpression studies.

q-bio.GN↗

arXiv2023

DNA-Based Data Storage Systems: A Review of Implementations and Code Constructions

In this review paper, we delve into the nascent field of molecular data storage, focusing on system implementations and code constructions. We start by providing an overview of basic concepts in synthetic and computational biology. Afterwards, we proceed with a review of the diverse approaches followed to implement such systems. In the process, we identify new problems in communication and coding theory, and discuss some relevant results pertaining to DNA sequence profiles, coded trace reconstruction, coding for DNA punchcard systems and coding for unique reconstruction.

cs.ET↗

arXiv2023

An Anchor-Point Based Image-Model for Room Impulse Response Simulation with Directional Source Radiation and Sensor Directivity Patterns

The image model method has been widely used to simulate room impulse responses and the endeavor to adapt this method to different applications has also piqued great interest over the last few decades. This paper attempts to extend the image model method and develops an anchor-point-image-model (APIM) approach as a solution for simulating impulse responses by including both the source radiation and sensor directivity patterns. To determine the orientations of all the virtual sources, anchor points are introduced to real sources, which subsequently lead to the determination of the orientations of the virtual sources. An algorithm is developed to generate room impulse responses with APIM by taking into account the directional pattern functions, factional time delays, as well as the computational complexity. The developed model and algorithms can be used in various acoustic problems to simulate room acoustics and improve and evaluate processing algorithms.

cs.SD↗

arXiv2023

Federated Classification in Hyperbolic Spaces via Secure Aggregation of Convex Hulls

Hierarchical and tree-like data sets arise in many applications, including language processing, graph data mining, phylogeny and genomics. It is known that tree-like data cannot be embedded into Euclidean spaces of finite dimension with small distortion. This problem can be mitigated through the use of hyperbolic spaces. When such data also has to be processed in a distributed and privatized setting, it becomes necessary to work with new federated learning methods tailored to hyperbolic spaces. As an initial step towards the development of the field of federated learning in hyperbolic spaces, we propose the first known approach to federated classification in hyperbolic spaces. Our contributions are as follows. First, we develop distributed versions of convex SVM classifiers for Poincar\'e discs. In this setting, the information conveyed from clients to the global classifier are convex hulls of clusters present in individual client data. Second, to avoid label switching issues, we introduce a number-theoretic approach for label recovery based on the so-called integer $B_h$ sequences. Third, we compute the complexity of the convex hulls in hyperbolic spaces to assess the extent of data leakage; at the same time, in order to limit communication cost for the hulls, we propose a new quantization method for the Poincar\'e disc coupled with Reed-Solomon-like encoding. Fourth, at the server level, we introduce a new approach for aggregating convex hulls of the clients based on balanced graph partitioning. We test our method on a collection of diverse data sets, including hierarchical single-cell RNA-seq data from different patients distributed across different repositories that have stringent privacy constraints. The classification accuracy of our method is up to $\sim 11\%$ better than its Euclidean counterpart, demonstrating the importance of privacy-preserving learning in hyperbolic spaces.

cs.LG↗

arXiv2023

Semi-Quantitative Group Testing for Efficient and Accurate qPCR Screening of Pathogens with a Wide Range of Loads

Pathogenic infections pose a significant threat to global health, affecting millions of people every year and presenting substantial challenges to healthcare systems worldwide. Efficient and timely testing plays a critical role in disease control and transmission prevention. Group testing is a well-established method for reducing the number of tests needed to screen large populations when the disease prevalence is low. However, it does not fully utilize the quantitative information provided by qPCR methods, nor is it able to accommodate a wide range of pathogen loads. To address these issues, we introduce a novel adaptive semi-quantitative group testing (SQGT) scheme to efficiently screen populations via two-stage qPCR testing. The SQGT method quantizes cycle threshold ($Ct$) values into multiple bins, leveraging the information from the first stage of screening to improve the detection sensitivity. Dynamic $Ct$ threshold adjustments mitigate dilution effects and enhance test accuracy. Comparisons with traditional binary outcome GT methods show that SQGT reduces the number of tests by $24$% while maintaining a negligible false negative rate.

q-bio.QM↗

arXiv2023

Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protection

GNNs can inadvertently expose sensitive user information and interactions through their model predictions. To address these privacy concerns, Differential Privacy (DP) protocols are employed to control the trade-off between provable privacy protection and model utility. Applying standard DP approaches to GNNs directly is not advisable due to two main reasons. First, the prediction of node labels, which relies on neighboring node attributes through graph convolutions, can lead to privacy leakage. Second, in practical applications, the privacy requirements for node attributes and graph topology may differ. In the latter setting, existing DP-GNN models fail to provide multigranular trade-offs between graph topology privacy, node attribute privacy, and GNN utility. To address both limitations, we propose a new framework termed Graph Differential Privacy (GDP), specifically tailored to graph learning. GDP ensures both provably private model parameters as well as private predictions. Additionally, we describe a novel unified notion of graph dataset adjacency to analyze the properties of GDP for different levels of graph topology privacy. Our findings reveal that DP-GNNs, which rely on graph convolutions, not only fail to meet the requirements for multigranular graph topology privacy but also necessitate the injection of DP noise that scales at least linearly with the maximum node degree. In contrast, our proposed Differentially Private Decoupled Graph Convolutions (DPDGCs) represent a more flexible and efficient alternative to graph convolutions that still provides the necessary guarantees of GDP. To validate our approach, we conducted extensive experiments on seven node classification benchmarking and illustrative synthetic datasets. The results demonstrate that DPDGCs significantly outperform existing DP-GNNs in terms of privacy-utility trade-offs.

cs.LG↗