arXiv subjects

Gang Wang

Publications and source records attributed to Gang Wang.

At least 163 records · Page 9Linked to original sources

arXiv2024

Practical Region-level Attack against Segment Anything Models

Segment Anything Models (SAM) have made significant advancements in image segmentation, allowing users to segment target portions of an image with a single click (i.e., user prompt). Given its broad applications, the robustness of SAM against adversarial attacks is a critical concern. While recent works have explored adversarial attacks against a pre-defined prompt/click, their threat model is not yet realistic: (1) they often assume the user-click position is known to the attacker (point-based attack), and (2) they often operate under a white-box setting with limited transferability. In this paper, we propose a more practical region-level attack where attackers do not need to know the precise user prompt. The attack remains effective as the user clicks on any point on the target object in the image, hiding the object from SAM. Also, by adapting a spectrum transformation method, we make the attack more transferable under a black-box setting. Both control experiments and testing against real-world SAM services confirm its effectiveness.

cs.CV↗

arXiv2024

Analysis on reservoir activation with the nonlinearity harnessed from solution-processed molybdenum disulfide

Reservoir computing is a recurrent neural network designed for approximating complex dynamics in, for instance, motion tracking, spatial-temporal pattern recognition, and chaotic attractor reconstruction. Its implementation demands intense computation for the nonlinear transformation of the reservoir input, i.e. activating the reservoir. Configuring physical nonlinear networks as the reservoir and employing the physical nonlinearity for the reservoir activation is an emergent solution to address the challenge. In this work, we analyze the feasibility of harnessing the nonlinearity from solution-processed molybdenum disulfide (MoS2) for reservoir activation. We fit the high-order nonlinearity, achieved by Stark modulation of MoS2, as the activation function to facilitate implementation of a reservoir computing model. Due to the high-order nonlinearity, the model can achieve long-term synchronization and robust generalization for complex dynamical system regression. As a potential application exploring this ability, we appoint the model to generate chaotic random numbers for secure data encryption. Given this reservoir activation capability, and the scalability of solution-processed MoS2, our results suggest the potential for realizing physical reservoir computing with solution-processed MoS2.

physics.app-ph↗

arXiv2024

Rank Resilience of Pattern Matrices against Structured Perturbations with Applications

In structured system theory, a pattern matrix is a matrix with entries either fixed to zero or free to take arbitrary numbers. The (generic) rank of a pattern matrix is the rank of almost all its realizations. The resilience of various system properties is closely tied to the rank resilience of the corresponding pattern matrices. Yet, existing literature predominantly explores the latter aspect by focusing on perturbations that change the zero-nonzero structure of pattern matrices, corresponding to link additions/deletions. In this paper, we consider the rank resilience of pattern matrices against structured perturbations that can arbitrarily alter the values of a prescribed set of entries, corresponding to link weight variations. We say a pattern matrix is structurally rank $r$ resilient against a perturbation pattern if almost all realizations of this pattern matrix have a rank not less than $r$ under arbitrary complex-valued realizations of the perturbation pattern. We establish a generic property in this concept. We then present combinatorial necessary and sufficient conditions for a rectangular pattern matrix to lose full rank under given perturbation patterns. We also generalize them to obtain a sufficient condition and a necessary one for losing an arbitrarily prescribed rank. We finally show our results can be applied to the resilience analysis of various properties of structured (descriptor) systems, including controllability and input-state observability, as well as characterizing zero structurally fixed modes.

cs.IT↗

arXiv2024

Isochrony-Controlled Speech-to-Text Translation: A study on translating from Sino-Tibetan to Indo-European Languages

End-to-end speech translation (ST), which translates source language speech directly into target language text, has garnered significant attention in recent years. Many ST applications require strict length control to ensure that the translation duration matches the length of the source audio, including both speech and pause segments. Previous methods often controlled the number of words or characters generated by the Machine Translation model to approximate the source sentence's length without considering the isochrony of pauses and speech segments, as duration can vary between languages. To address this, we present improvements to the duration alignment component of our sequence-to-sequence ST model. Our method controls translation length by predicting the duration of speech and pauses in conjunction with the translation process. This is achieved by providing timing information to the decoder, ensuring it tracks the remaining duration for speech and pauses while generating the translation. The evaluation on the Zh-En test set of CoVoST 2, demonstrates that the proposed Isochrony-Controlled ST achieves 0.92 speech overlap and 8.9 BLEU, which has only a 1.4 BLEU drop compared to the ST baseline.

cs.CL↗

arXiv2024

Harnessing physical entropy noise in structurally metastable 1T' molybdenum ditelluride for true random number generation

True random numbers are essential in various research and engineering problems. Their generation depends upon a robust physical entropy noise. Here, we present true random number generation by harnessing the conductance noise probed in structurally metastable 1T' molybdenum ditelluride (MoTe2). The noise, well-fitting a Poisson process, is proved a robust physical entropy noise at low and even cryogenic temperatures. Noise characteristic analysis suggests the noise may originate from the polarization variations of the underlying ferroelectric dipoles in 1T' MoTe2. We demonstrate the noise allows for true random number generation, enabling their use as seed for generating high-throughput secure random numbers exceeding 1 Mbit/s, appealing for practical applications in, for instance, cryptography where data security is now a severe issue. As an example, we show biometric information safeguarding in neural networks by using the random numbers as mask, proving a promising data security measure in big data and artificial intelligence.

cs.CR↗

arXiv2024

Abnormality Forecasting: Time Series Anomaly Prediction via Future Context Modeling

Identifying anomalies from time series data plays an important role in various fields such as infrastructure security, intelligent operation and maintenance, and space exploration. Current research focuses on detecting the anomalies after they occur, which can lead to significant financial/reputation loss or infrastructure damage. In this work we instead study a more practical yet very challenging problem, time series anomaly prediction, aiming at providing early warnings for abnormal events before their occurrence. To tackle this problem, we introduce a novel principled approach, namely future context modeling (FCM). Its key insight is that the future abnormal events in a target window can be accurately predicted if their preceding observation window exhibits any subtle difference to normal data. To effectively capture such differences, FCM first leverages long-term forecasting models to generate a discriminative future context based on the observation data, aiming to amplify those subtle but unusual difference. It then models a normality correlation of the observation data with the forecasting future context to complement the normality modeling of the observation data in foreseeing possible abnormality in the target window. A joint variate-time attention learning is also introduced in FCM to leverage both temporal signals and features of the time series data for more discriminative normality modeling in the aforementioned two views. Comprehensive experiments on five datasets demonstrate that FCM gains good recall rate (70\%+) on multiple datasets and significantly outperforms all baselines in F1 score. Code is available at https://github.com/mala-lab/FCM.

cs.LG↗

arXiv2024

Weak-eval-Strong: Evaluating and Eliciting Lateral Thinking of LLMs with Situation Puzzles

While advancements in NLP have significantly improved the performance of Large Language Models (LLMs) on tasks requiring vertical thinking, their lateral thinking capabilities remain under-explored and challenging to measure due to the complexity of assessing creative thought processes and the scarcity of relevant data. To address these challenges, we introduce SPLAT, a benchmark leveraging Situation Puzzles to evaluate and elicit LAteral Thinking of LLMs. This benchmark, containing 975 graded situation puzzles across three difficulty levels, employs a new multi-turn player-judge framework instead of the traditional model-based evaluation, which often necessitates a stronger evaluation model. This framework simulates an interactive game where the model (player) asks the evaluation model (judge) questions about an incomplete story to infer the full scenario. The judge answers based on a detailed reference scenario or evaluates if the player's predictions align with the reference one. This approach lessens dependence on more robust evaluation models, enabling the assessment of state-of-the-art LLMs. The experiments demonstrate that a robust evaluation model, such as WizardLM-2, closely matches human judgements in both intermediate question-answering and final scenario accuracy, achieving over 80% agreement-similar to the agreement levels among humans. Furthermore, applying data and reasoning processes from our benchmark to other lateral thinking-related benchmarks, e.g., RiddleSense and BrainTeaser, leads to performance enhancements. This suggests that our benchmark effectively evaluates and elicits the lateral thinking abilities of LLMs. Code is available at: https://github.com/chenqi008/LateralThinking.

cs.CL↗

arXiv2024

Distributed Data-driven Unknown-input Observers for State Estimation

Unknown inputs related to, e.g., sensor aging, modeling errors, or device bias, represent a major concern in wireless sensor networks, as they degrade the state estimation performance. To improve the performance, unknown-input observers (UIOs) have been proposed. Most of the results available to design UIOs are based on explicit system models, which can be difficult or impossible to obtain in real-world applications. Data-driven techniques, on the other hand, have become a viable alternative for the design and analysis of unknown systems using only data. In this context, a novel data-driven distributed unknown-input observer (D-DUIO) for unknown continuous-time linear time-invariant (LTI) systems is developed, which requires solely some data collected offline, without any prior knowledge of the system matrices. In the paper, first, a model-based approach to the design of a DUIO is presented. A sufficient condition for the existence of such a DUIO is recalled, and a new one is proposed, that is prone to a data-driven adaption. Moving to a data-driven approach, it is shown that under suitable assumptions on the input/output/state data collected from the continuous-time system, it is possible to both claim the existence of a D-DUIO and to derive its matrices in terms of the matrices of pre-collected data. Finally, the efficacy of the D-DUIO is illustrated by means of numerical examples.

eess.SY↗

arXiv2024

Enhancing noise characterization with robust time delay interferometry combination

Time delay interferometry (TDI) is essential for suppressing laser frequency noise and achieving the targeted sensitivity for space-borne gravitational wave (GW) missions. In Paper I, we examined the performance of the fiducial second-generation TDI Michelson configuration versus an alternative, the hybrid Relay, in noise suppression and data analysis. The results showed that both TDI schemes have comparable performances in mitigating laser and clock noises. However, when analyzing chirp signal from the coalescence of massive binary black holes, the Michelson configuration becomes inferior due to its vulnerable T channel and numerous null frequencies. In contrast, the hybrid Relay is more robust in dynamic unequal-arm scenarios. In this work, we further investigate the noise characterization capabilities of these two TDI configurations. Our investigations demonstrate that hybrid Relay achieves more robust noise parameter inference than the Michelson configuration. Moreover, the performance can be enhanced by replacing the T channel of hybrid Relay with a second-generation TDI null stream $C^{12}_3$. The combined three data streams, including two science observables from the hybrid Relay and $C^{12}_3$, could reduce the instabilities of noise spectra in the targeting frequency band and form an optimal dataset for characterizing noises.

gr-qc↗

arXiv2024

Impact of Imprecision of the Time Delay on Imaging Result in Confocal Algorithm

The confocal microwave imaging (CMI) algorithm, which is used in radar imaging, has been applied to microwave medical imaging (MMI) [1, 2]. In MMI, the diseased region to be imaged has different electromagnetic characteristics from that of the surroundings. Time -domain MMI system often radiates an ultra-wideband pulse and then collect the backscatter signals with an antenna array. The time delay is then compensated for every unit in the array according to the time flight to each focal point within the region of interest. The compensated signals are finally summed to calculate the pixel value of each focal point. This process is repeated to achieve the value for all focal points in a 3D space to reconstruct the image. Since the method is only constrained in the time domain, the complexity is minimal, and an image can be obtained usually in few seconds. This paper discusses the robustness of CMI in MMI. Specifically, we analyzed the variation of image contrast as errors occur in the time-delay calculation. A simplified model of breast cancer detection was implemented to study the relationship between time-shift errors and the impact on images, quantitatively.

physics.med-ph↗

arXiv2024

PlainUSR: Chasing Faster ConvNet for Efficient Super-Resolution

Reducing latency is a roaring trend in recent super-resolution (SR) research. While recent progress exploits various convolutional blocks, attention modules, and backbones to unlock the full potentials of the convolutional neural network (ConvNet), achieving real-time performance remains a challenge. To this end, we present PlainUSR, a novel framework incorporating three pertinent modifications to expedite ConvNet for efficient SR. For the convolutional block, we squeeze the lighter but slower MobileNetv3 block into a heavier but faster vanilla convolution by reparameterization tricks to balance memory access and calculations. For the attention module, by modulating input with a regional importance map and gate, we introduce local importance-based attention to realize high-order information interaction within a 1-order attention latency. As to the backbone, we propose a plain U-Net that executes channel-wise discriminate splitting and concatenation. In the experimental phase, PlainUSR exhibits impressively low latency, great scalability, and competitive performance compared to both state-of-the-art latency-oriented and quality-oriented methods. In particular, compared to recent NGswin, the PlainUSR-L is 16.4x faster with competitive performance.

eess.IV↗

arXiv2024

Effect of vector meson spin coherence on the measurements of chiral magnetic effect in heavy-ion collisions

The chiral magnetic effect (CME) in heavy-ion collisions reflects the local violation of ${\cal P}$ and ${\cal CP}$ symmetries in strong interactions and manifests as electric charge separation along the direction of the magnetic field created by the wounded nuclei. The experimental observables for the CME, such as the $γ_{112}$ correlator, the $R_{Ψ_2}(ΔS)$ correlator, and the signed balance functions, however, are also subject to non-CME backgrounds, including those from resonance decays. A previous study showed that the CME observables are affected by the diagonal component of the spin density matrix, the $ρ_{00}$ for vector mesons. In this work, we study the contributions from the other elements of the spin density matrix using a toy model and a multiphase transport model. We find that the real part of the $ρ_{1-1}$ component, $\mathrm{Re}\,ρ_{1-1}$, affects the CME observables in a manner opposite to that of the $ρ_{00}$. All three aforementioned CME observables show a linear dependence on $\mathrm{Re}\,ρ_{1-1}$ in the model calculations, supporting our analytical derivations. The rest elements of the spin density matrix do not contribute to the CME observables. The off-diagonal terms in the spin density matrix indicate spin coherence and may be nonzero in heavy-ion collisions due to local spin polarization or spin-spin correlations. Thus, $\mathrm{Re}\,ρ_{1-1}$, along with $ρ_{00}$, could play a significant role in interpreting measurements in search of the CME.

nucl-th↗

arXiv2024

ORCHID: Streaming Threat Detection over Versioned Provenance Graphs

While Endpoint Detection and Response (EDR) are able to efficiently monitor threats by comparing static rules to the event stream, their inability to incorporate past system context leads to high rates of false alarms. Recent work has demonstrated Provenance-based Intrusion Detection Systems (Prov-IDS) that can examine the causal relationships between abnormal behaviors to improve threat classification. However, employing these Prov-IDS in practical settings remains difficult -- state-of-the-art neural network based systems are only fast in a fully offline deployment model that increases attacker dwell time, while simultaneously using simplified and less accurate provenance graphs to reduce memory consumption. Thus, today's Prov-IDS cannot operate effectively in the real-time streaming setting required for commercial EDR viability. This work presents the design and implementation of ORCHID, a novel Prov-IDS that performs fine-grained detection of process-level threats over a real time event stream. ORCHID takes advantage of the unique immutable properties of a versioned provenance graphs to iteratively embed the entire graph in a sequential RNN model while only consuming a fraction of the computation and memory costs. We evaluate ORCHID on four public datasets, including DARPA TC, to show that ORCHID can provide competitive classification performance while eliminating detection lag and reducing memory consumption by two orders of magnitude.

cs.CR↗

arXiv2024

Chemical versus physical pressure effects on the structure transition of bilayer nickelates

The observation of high-$T_c$ superconductivity (HTSC) in concomitant with pressure-induced orthorhombic-tetragonal structural transition in the bilayer La$_{3}$Ni$_2$O$_7$ has sparked hopes of achieving HTSC by stabilizing the tetragonal phase at ambient pressure. To mimic the effect of external physical pressures, the application of chemical pressure via replacing La$^3$$^+$ with smaller rare-earth R$^3$$^+$ has been considered as a potential route. Here we clarify the distinct effects of chemical and physical pressures on the structural transition of bilayer nickelates through a combined experimental and theoretical investigation. Contrary to general expectations, we find that substitutions of smaller R$^3$$^+$ for La$^3$$^+$ in La$_{3-x}$R$_x$Ni$_2$O$_{7-δ}$, despite of an overall lattice contraction, produce stronger orthorhombic structural distortions and thus require higher pressures to induce the structural transition. We established a quantitative relationship between the critical pressure $P_c$ for structural transition and the average size of $A$-site cations. A linear extrapolation of $P_c$ versus <$r_A$> yields a putative critical value of <$r_A$>$_c$ ~ 1.23 angstrom for $P_c$ ~ 1 bar. The negative correlation between $P_c$ and <$r_A$> indicates that it is unlikely to reduce $P_c$ to ambient by replacing La$^3$$^+$ with smaller R$^3$$^+$ ions. Instead, partial substitution of La$^3$$^+$ with larger cations such as alkaline-earth Sr$^2$$^+$ or Ba$^2$$^+$ might be a feasible approach. Our results provide valuable guidelines in the quest of ambient-pressure HTSC in bilayer nickelates.

cond-mat.str-el↗

arXiv2024

Heavy-Ball Momentum Accelerated Actor-Critic With Function Approximation

By using an parametric value function to replace the Monte-Carlo rollouts for value estimation, the actor-critic (AC) algorithms can reduce the variance of stochastic policy gradient so that to improve the convergence rate. While existing works mainly focus on analyzing convergence rate of AC algorithms under Markovian noise, the impacts of momentum on AC algorithms remain largely unexplored. In this work, we first propose a heavy-ball momentum based advantage actor-critic (\mbox{HB-A2C}) algorithm by integrating the heavy-ball momentum into the critic recursion that is parameterized by a linear function. When the sample trajectory follows a Markov decision process, we quantitatively certify the acceleration capability of the proposed HB-A2C algorithm. Our theoretical results demonstrate that the proposed HB-A2C finds an $ε$-approximate stationary point with $\oo{ε^{-2}}$ iterations for reinforcement learning tasks with Markovian noise. Moreover, we also reveal the dependence of learning rates on the length of the sample trajectory. By carefully selecting the momentum factor of the critic recursion, the proposed HB-A2C can balance the errors introduced by the initialization and the stoschastic approximation.

cs.LG↗

arXiv2024

Guaranteeing Accuracy and Fairness under Fluctuating User Traffic: A Bankruptcy-Inspired Re-ranking Approach

Out of sustainable and economical considerations, two-sided recommendation platforms must satisfy the needs of both users and providers. Previous studies often show that the two sides' needs show different urgency: providers need a relatively long-term exposure demand while users want more short-term and accurate service. However, our empirical study reveals that previous methods for trading off fairness-accuracy often fail to guarantee long-term fairness and short-term accuracy simultaneously in real applications of fluctuating user traffic. Especially, when user traffic is low, the user experience often drops a lot. Our theoretical analysis also confirms that user traffic is a key factor in such a trade-off problem. How to guarantee accuracy and fairness under fluctuating user traffic remains a problem. Inspired by the bankruptcy problem in economics, we propose a novel fairness-aware re-ranking approach named BankFair. Intuitively, BankFair employs the Talmud rule to leverage periods of abundant user traffic to offset periods of user traffic scarcity, ensuring consistent user service at every period while upholding long-term fairness. Specifically, BankFair consists of two modules: (1) employing the Talmud rule to determine the required fairness degree under varying periods of user traffic; and (2) conducting an online re-ranking algorithm based on the fairness degree determined by the Talmud rule. Experiments on two real-world recommendation datasets show that BankFair outperforms all baselines regarding accuracy and provider fairness.

cs.IR↗

arXiv2024

Neural Retrievers are Biased Towards LLM-Generated Content

Recently, the emergence of large language models (LLMs) has revolutionized the paradigm of information retrieval (IR) applications, especially in web search, by generating vast amounts of human-like texts on the Internet. As a result, IR systems in the LLM era are facing a new challenge: the indexed documents are now not only written by human beings but also automatically generated by the LLMs. How these LLM-generated documents influence the IR systems is a pressing and still unexplored question. In this work, we conduct a quantitative evaluation of IR models in scenarios where both human-written and LLM-generated texts are involved. Surprisingly, our findings indicate that neural retrieval models tend to rank LLM-generated documents higher. We refer to this category of biases in neural retrievers towards the LLM-generated content as the \textbf{source bias}. Moreover, we discover that this bias is not confined to the first-stage neural retrievers, but extends to the second-stage neural re-rankers. Then, in-depth analyses from the perspective of text compression indicate that LLM-generated texts exhibit more focused semantics with less noise, making it easier for neural retrieval models to semantic match. To mitigate the source bias, we also propose a plug-and-play debiased constraint for the optimization objective, and experimental results show its effectiveness. Finally, we discuss the potential severe concerns stemming from the observed source bias and hope our findings can serve as a critical wake-up call to the IR community and beyond. To facilitate future explorations of IR in the LLM era, the constructed two new benchmarks are available at https://github.com/KID-22/Source-Bias.

cs.IR↗

arXiv2024

Time-Sensitive Networking (TSN) for Industrial Automation: Current Advances and Future Directions

With the introduction of Cyber-Physical Systems (CPS) and Internet of Things (IoT) technologies, the automation industry is undergoing significant changes, particularly in improving production efficiency and reducing maintenance costs. Industrial automation applications often need to transmit time- and safety-critical data to closely monitor and control industrial processes. Several Ethernet-based fieldbus solutions, such as PROFINET IRT, EtherNet/IP, and EtherCAT, are widely used to ensure real-time communications in industrial automation systems. These solutions, however, commonly incorporate additional mechanisms to provide latency guarantees, making their interoperability a grand challenge. The IEEE 802.1 Time Sensitive Networking (TSN) task group was formed to enhance and optimize IEEE 802.1 network standards, particularly for Ethernet-based networks. These solutions can be evolved and adapted for cross-industry scenarios, such as large-scale distributed industrial plants requiring multiple industrial entities to work collaboratively. This paper provides a comprehensive review of current advances in TSN standards for industrial automation. It presents the state-of-the-art IEEE TSN standards and discusses the opportunities and challenges of integrating TSN into the automation industry. Some promising research directions are also highlighted for applying TSN technologies to industrial automation applications.

cs.NI↗