arXiv subjects

Shuo Wang

Publications and source records attributed to Shuo Wang.

At least 397 records · Page 22Linked to original sources

arXiv2024

Say More with Less: Understanding Prompt Learning Behaviors through Gist Compression

Large language models (LLMs) require lengthy prompts as the input context to produce output aligned with user intentions, a process that incurs extra costs during inference. In this paper, we propose the Gist COnditioned deCOding (Gist-COCO) model, introducing a novel method for compressing prompts which also can assist the prompt interpretation and engineering. Gist-COCO employs an encoder-decoder based language model and then incorporates an additional encoder as a plugin module to compress prompts with inputs using gist tokens. It finetunes the compression plugin module and uses the representations of gist tokens to emulate the raw prompts in the vanilla language model. By verbalizing the representations of gist tokens into gist prompts, the compression ability of Gist-COCO can be generalized to different LLMs with high compression rates. Our experiments demonstrate that Gist-COCO outperforms previous prompt compression models in both passage and instruction compression tasks. Further analysis on gist verbalization results suggests that our gist prompts serve different functions in aiding language models. They may directly provide potential answers, generate the chain-of-thought, or simply repeat the inputs. All data and codes are available at https://github.com/OpenMatch/Gist-COCO .

cs.CL↗

arXiv2024

Two-fold symmetric superconductivity in the kagome superconductor RbV3Sb5

The recently discovered kagome superconductors offer a promising platform for investigating intertwined orders and novel states, including topology, superconductivity, charge density waves, and more. The interplay among these orders can spontaneously break rotational symmetry, giving rise to exotic phenomena such as nematicity or even nematic superconductivity. Here we present our findings on the two-fold symmetric superconductivity in thin-flake RbV3Sb5 in response to direction-dependent in-plane magnetic fields, in contrast to the inherent six-fold structural symmetry of the crystal lattice. The two-fold symmetry was evidenced through a combination of magnetoresistance transport experiments, critical magnetic field measurements, and observations of anisotropic superconducting gaps. Additionally, by altering the experimental configuration, we also detected the presence of six-fold symmetric components superimposed on the two-fold symmetry at the boundary between normal and superconducting states. Our results underscore the correlation-driven symmetry-breaking phenomena and emphasize the potential of this correlated kagome family as a promising platform for investigating intertwined orders, including unconventional superconductivity.

cond-mat.supr-con↗

arXiv2024

$\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens

Processing and reasoning over long contexts is crucial for many practical applications of Large Language Models (LLMs), such as document comprehension and agent construction. Despite recent strides in making LLMs process contexts with more than 100K tokens, there is currently a lack of a standardized benchmark to evaluate this long-context capability. Existing public benchmarks typically focus on contexts around 10K tokens, limiting the assessment and comparison of LLMs in processing longer contexts. In this paper, we propose $\infty$Bench, the first LLM benchmark featuring an average data length surpassing 100K tokens. $\infty$Bench comprises synthetic and realistic tasks spanning diverse domains, presented in both English and Chinese. The tasks in $\infty$Bench are designed to require well understanding of long dependencies in contexts, and make simply retrieving a limited number of passages from contexts not sufficient for these tasks. In our experiments, based on $\infty$Bench, we evaluate the state-of-the-art proprietary and open-source LLMs tailored for processing long contexts. The results indicate that existing long context LLMs still require significant advancements to effectively process 100K+ context. We further present three intriguing analyses regarding the behavior of LLMs processing long context.

cs.CL↗

arXiv2024

Hypercomplex structures arising from twistor spaces

A hyperkähler manifold is defined as a Riemannian manifold endowed with three covariantly constant complex structures that are quaternionically related. A twistor space is characterized as a holomorphic fiber bundle $p: \mathcal{Z} \rightarrow \mathbb{CP}^1$ possesses properties such as a family of holomorphic sections whose normal bundle is $\bigoplus^{2n}\mathcal{O}(1)$, a holomorphic section of $Λ^2(N\mathcal{Z})\otimes p^*(\mathcal{O}(2))$ that defines a symplectic form on each fiber, and a compatible real structure. According to the Hitchin-Karlhede-Lindström-Roček theorem (Comm. Math. Phys., 108(4):535-589, 1987), there exists a hyperkähler metric on the parameter space $M$ for the real sections of $\mathcal{Z}$. Utilizing the Kodaira-Spencer deformation theory, we facilitate the construction of a hypercomplex structure on $M$, predicated upon more relaxed presuppositions concerning $\mathcal{Z}$. This effort enriches our understanding of the classical theorem by Hitchin-Karlhede-Lindström-Roček.

math.DG↗

arXiv2024

From Text to CQL: Bridging Natural Language and Corpus Search Engine

Natural Language Processing (NLP) technologies have revolutionized the way we interact with information systems, with a significant focus on converting natural language queries into formal query languages such as SQL. However, less emphasis has been placed on the Corpus Query Language (CQL), a critical tool for linguistic research and detailed analysis within text corpora. The manual construction of CQL queries is a complex and time-intensive task that requires a great deal of expertise, which presents a notable challenge for both researchers and practitioners. This paper presents the first text-to-CQL task that aims to automate the translation of natural language into CQL. We present a comprehensive framework for this task, including a specifically curated large-scale dataset and methodologies leveraging large language models (LLMs) for effective text-to-CQL task. In addition, we established advanced evaluation metrics to assess the syntactic and semantic accuracy of the generated queries. We created innovative LLM-based conversion approaches and detailed experiments. The results demonstrate the efficacy of our methods and provide insights into the complexities of text-to-CQL task.

cs.CL↗

arXiv2024

Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages

While large language models (LLMs) have been pre-trained on multilingual corpora, their performance still lags behind in most languages compared to a few resource-rich languages. One common approach to mitigate this issue is to translate training data from resource-rich languages into other languages and then continue training. However, using the data obtained solely relying on translation while ignoring the original capabilities of LLMs across languages is not always effective, which we show will limit the performance of cross-lingual knowledge transfer. In this work, we propose SDRRL, a method based on Self-Distillation from Resource-Rich Languages that effectively improve multilingual performance by leveraging the internal capabilities of LLMs on resource-rich languages. We evaluate on different LLMs (LLaMA-2 and SeaLLM) and source languages across various comprehension and generation tasks, experimental results demonstrate that SDRRL can significantly enhance multilingual capabilities while minimizing the impact on original performance in resource-rich languages.

cs.CL↗

arXiv2024

UltraLink: An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset

Open-source large language models (LLMs) have gained significant strength across diverse fields. Nevertheless, the majority of studies primarily concentrate on English, with only limited exploration into the realm of multilingual abilities. In this work, we therefore construct an open-source multilingual supervised fine-tuning dataset. Different from previous works that simply translate English instructions, we consider both the language-specific and language-agnostic abilities of LLMs. Firstly, we introduce a knowledge-grounded data augmentation approach to elicit more language-specific knowledge of LLMs, improving their ability to serve users from different countries. Moreover, we find modern LLMs possess strong cross-lingual transfer capabilities, thus repeatedly learning identical content in various languages is not necessary. Consequently, we can substantially prune the language-agnostic supervised fine-tuning (SFT) data without any performance degradation, making multilingual SFT more efficient. The resulting UltraLink dataset comprises approximately 1 million samples across five languages (i.e., En, Zh, Ru, Fr, Es), and the proposed data construction method can be easily extended to other languages. UltraLink-LM, which is trained on UltraLink, outperforms several representative baselines across many tasks.

cs.CL↗

arXiv2024

VoltSchemer: Use Voltage Noise to Manipulate Your Wireless Charger

Wireless charging is becoming an increasingly popular charging solution in portable electronic products for a more convenient and safer charging experience than conventional wired charging. However, our research identified new vulnerabilities in wireless charging systems, making them susceptible to intentional electromagnetic interference. These vulnerabilities facilitate a set of novel attack vectors, enabling adversaries to manipulate the charger and perform a series of attacks. In this paper, we propose VoltSchemer, a set of innovative attacks that grant attackers control over commercial-off-the-shelf wireless chargers merely by modulating the voltage from the power supply. These attacks represent the first of its kind, exploiting voltage noises from the power supply to manipulate wireless chargers without necessitating any malicious modifications to the chargers themselves. The significant threats imposed by VoltSchemer are substantiated by three practical attacks, where a charger can be manipulated to: control voice assistants via inaudible voice commands, damage devices being charged through overcharging or overheating, and bypass Qi-standard specified foreign-object-detection mechanism to damage valuable items exposed to intense magnetic fields. We demonstrate the effectiveness and practicality of the VoltSchemer attacks with successful attacks on 9 top-selling COTS wireless chargers. Furthermore, we discuss the security implications of our findings and suggest possible countermeasures to mitigate potential threats.

cs.CR↗

arXiv2024

LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks

LoRA employs lightweight modules to customize large language models (LLMs) for each downstream task or domain, where different learned additional modules represent diverse skills. Combining existing LoRAs to address new tasks can enhance the reusability of learned LoRAs, particularly beneficial for tasks with limited annotated data. Most prior works on LoRA combination primarily rely on task-level weights for each involved LoRA, making different examples and tokens share the same LoRA weights. However, in generative tasks, different tokens may necessitate diverse skills to manage. Taking the Chinese math task as an example, understanding the problem description may depend more on the Chinese LoRA, while the calculation part may rely more on the math LoRA. To this end, we propose LoRA-Flow, which utilizes dynamic weights to adjust the impact of different LoRAs. The weights at each step are determined by a fusion gate with extremely few parameters, which can be learned with only 200 training examples. Experiments across six generative tasks demonstrate that our method consistently outperforms baselines with task-level fusion weights. This underscores the necessity of introducing dynamic fusion weights for LoRA combination.

cs.CL↗

arXiv2024

Physics informed data-driven near-wall modelling for lattice Boltzmann simulation of high Reynolds number turbulent flows

Data-driven approaches offer novel opportunities for improving the performance of turbulent flow simulations, which are critical to wide-ranging applications from wind farms and aerodynamic designs to weather and climate forecasting. While conventional continuum Navier-Stokes solvers have been the subject of a significant amount of work in this domain, there has hitherto been very limited effort in the same direction for the more scalable and highly performant lattice Boltzmann method (LBM), even though it has been successfully applied to a variety of turbulent flow simulations using large-eddy simulation (LES) techniques. In this work, we establish a data-driven framework for the LES-based lattice Boltzmann simulation of near-wall turbulent flow fields. We do this by training neural networks using improved delayed detached eddy simulation data. Crucially, this is done in combination with physics-based information that substantially constrains the data-driven predictions. Using data from turbulent channel flow at a friction Reynolds number at $5200$, our simulations accurately predict the behaviour of the wall model at arbitrary friction Reynolds numbers up to $1.0 \times 10^6$. In contradistinction with other models that use direct numerical simulation datasets, our physics-informed model requires data from very limited regions within the wall-bounded plane, reducing by three orders of magnitude the quantity of data needed for training. We also demonstrate that our model can handle data configurations when the near-wall grid is sparse. Our physics-informed neural network approach opens up the possibility of employing LBM in combination with highly specific and therefore much more limited quantities of macroscopic data, substantially facilitating the investigation of a wide-range of turbulent flow applications at very large scale.

physics.flu-dyn↗

arXiv2024

Learning with Mixture of Prototypes for Out-of-Distribution Detection

Out-of-distribution (OOD) detection aims to detect testing samples far away from the in-distribution (ID) training data, which is crucial for the safe deployment of machine learning models in the real world. Distance-based OOD detection methods have emerged with enhanced deep representation learning. They identify unseen OOD samples by measuring their distances from ID class centroids or prototypes. However, existing approaches learn the representation relying on oversimplified data assumptions, e.g, modeling ID data of each class with one centroid class prototype or using loss functions not designed for OOD detection, which overlook the natural diversities within the data. Naively enforcing data samples of each class to be compact around only one prototype leads to inadequate modeling of realistic data and limited performance. To tackle these issues, we propose PrototypicAl Learning with a Mixture of prototypes (PALM) which models each class with multiple prototypes to capture the sample diversities, and learns more faithful and compact samples embeddings to enhance OOD detection. Our method automatically identifies and dynamically updates prototypes, assigning each sample to a subset of prototypes via reciprocal neighbor soft assignment weights. PALM optimizes a maximum likelihood estimation (MLE) loss to encourage the sample embeddings to be compact around the associated prototypes, as well as a contrastive loss on all prototypes to enhance intra-class compactness and inter-class discrimination at the prototype level. Moreover, the automatic estimation of prototypes enables our approach to be extended to the challenging OOD detection task with unlabelled ID data. Extensive experiments demonstrate the superiority of PALM, achieving state-of-the-art average AUROC performance of 93.82 on the challenging CIFAR-100 benchmark. Code is available at https://github.com/jeff024/PALM.

cs.LG↗

arXiv2024

Invisible Finger: Practical Electromagnetic Interference Attack on Touchscreen-based Electronic Devices

Touchscreen-based electronic devices such as smart phones and smart tablets are widely used in our daily life. While the security of electronic devices have been heavily investigated recently, the resilience of touchscreens against various attacks has yet to be thoroughly investigated. In this paper, for the first time, we show that touchscreen-based electronic devices are vulnerable to intentional electromagnetic interference (IEMI) attacks in a systematic way and how to conduct this attack in a practical way. Our contribution lies in not just demonstrating the attack, but also analyzing and quantifying the underlying mechanism allowing the novel IEMI attack on touchscreens in detail. We show how to calculate both the minimum amount of electric field and signal frequency required to induce touchscreen ghost touches. We further analyze our IEMI attack on real touchscreens with different magnitudes, frequencies, duration, and multitouch patterns. The mechanism of controlling the touchscreen-enabled electronic devices with IEMI signals is also elaborated. We design and evaluate an out-of-sight touchscreen locator and touch injection feedback mechanism to assist a practical IEMI attack. Our attack works directly on the touchscreen circuit regardless of the touchscreen scanning mechanism or operating system. Our attack can inject short-tap, long-press, and omni-directional gestures on touchscreens from a distance larger than the average thickness of common tabletops. Compared with the state-of-the-art touchscreen attack, ours can accurately inject different types of touch events without the need for sensing signal synchronization, which makes our attack more robust and practical. In addition, rather than showing a simple proof-of-concept attack, we present and demonstrate the first ready-to-use IEMI based touchscreen attack vector with end-to-end attack scenarios.

cs.CR↗

arXiv2024

Programmable EM Sensor Array for Golden-Model Free Run-time Trojan Detection and Localization

Side-channel analysis has been proven effective at detecting hardware Trojans in integrated circuits (ICs). However, most detection techniques rely on large external probes and antennas for data collection and require a long measurement time to detect Trojans. Such limitations make these techniques impractical for run-time deployment and ineffective in detecting small Trojans with subtle side-channel signatures. To overcome these challenges, we propose a Programmable Sensor Array (PSA) for run-time hardware Trojan detection, localization, and identification. PSA is a tampering-resilient integrated on-chip magnetic field sensor array that can be re-programmed to change the sensors' shape, size, and location. Using PSA, EM side-channel measurement results collected from sensors at different locations on an IC can be analyzed to localize and identify the Trojan. The PSA has better performance than conventional external magnetic probes and state-of-the-art on-chip single-coil magnetic field sensors. We fabricated an AES-128 test chip with four AES Hardware Trojans. They were successfully detected, located, and identified with the proposed on-chip PSA within 10 milliseconds using our proposed cross-domain analysis.

cs.CR↗

arXiv2024

Stream Query Denoising for Vectorized HD Map Construction

To enhance perception performance in complex and extensive scenarios within the realm of autonomous driving, there has been a noteworthy focus on temporal modeling, with a particular emphasis on streaming methods. The prevailing trend in streaming models involves the utilization of stream queries for the propagation of temporal information. Despite the prevalence of this approach, the direct application of the streaming paradigm to the construction of vectorized high-definition maps (HD-maps) fails to fully harness the inherent potential of temporal information. This paper introduces the Stream Query Denoising (SQD) strategy as a novel approach for temporal modeling in high-definition map (HD-map) construction. SQD is designed to facilitate the learning of temporal consistency among map elements within the streaming model. The methodology involves denoising the queries that have been perturbed by the addition of noise to the ground-truth information from the preceding frame. This denoising process aims to reconstruct the ground-truth information for the current frame, thereby simulating the prediction process inherent in stream queries. The SQD strategy can be applied to those streaming methods (e.g., StreamMapNet) to enhance the temporal modeling. The proposed SQD-MapNet is the StreamMapNet equipped with SQD. Extensive experiments on nuScenes and Argoverse2 show that our method is remarkably superior to other existing methods across all settings of close range and long range. The code will be available soon.

cs.CV↗

arXiv2024

A Duty to Forget, a Right to be Assured? Exposing Vulnerabilities in Machine Unlearning Services

The right to be forgotten requires the removal or "unlearning" of a user's data from machine learning models. However, in the context of Machine Learning as a Service (MLaaS), retraining a model from scratch to fulfill the unlearning request is impractical due to the lack of training data on the service provider's side (the server). Furthermore, approximate unlearning further embraces a complex trade-off between utility (model performance) and privacy (unlearning performance). In this paper, we try to explore the potential threats posed by unlearning services in MLaaS, specifically over-unlearning, where more information is unlearned than expected. We propose two strategies that leverage over-unlearning to measure the impact on the trade-off balancing, under black-box access settings, in which the existing machine unlearning attacks are not applicable. The effectiveness of these strategies is evaluated through extensive experiments on benchmark datasets, across various model architectures and representative unlearning approaches. Results indicate significant potential for both strategies to undermine model efficacy in unlearning scenarios. This study uncovers an underexplored gap between unlearning and contemporary MLaaS, highlighting the need for careful considerations in balancing data unlearning, model utility, and security.

cs.CR↗

arXiv2024

DeepTaster: Adversarial Perturbation-Based Fingerprinting to Identify Proprietary Dataset Use in Deep Neural Networks

Training deep neural networks (DNNs) requires large datasets and powerful computing resources, which has led some owners to restrict redistribution without permission. Watermarking techniques that embed confidential data into DNNs have been used to protect ownership, but these can degrade model performance and are vulnerable to watermark removal attacks. Recently, DeepJudge was introduced as an alternative approach to measuring the similarity between a suspect and a victim model. While DeepJudge shows promise in addressing the shortcomings of watermarking, it primarily addresses situations where the suspect model copies the victim's architecture. In this study, we introduce DeepTaster, a novel DNN fingerprinting technique, to address scenarios where a victim's data is unlawfully used to build a suspect model. DeepTaster can effectively identify such DNN model theft attacks, even when the suspect model's architecture deviates from the victim's. To accomplish this, DeepTaster generates adversarial images with perturbations, transforms them into the Fourier frequency domain, and uses these transformed images to identify the dataset used in a suspect model. The underlying premise is that adversarial images can capture the unique characteristics of DNNs built with a specific dataset. To demonstrate the effectiveness of DeepTaster, we evaluated the effectiveness of DeepTaster by assessing its detection accuracy on three datasets (CIFAR10, MNIST, and Tiny-ImageNet) across three model architectures (ResNet18, VGG16, and DenseNet161). We conducted experiments under various attack scenarios, including transfer learning, pruning, fine-tuning, and data augmentation. Specifically, in the Multi-Architecture Attack scenario, DeepTaster was able to identify all the stolen cases across all datasets, while DeepJudge failed to detect any of the cases.

cs.CR↗

arXiv2023

ROS package search for robot software development: a knowledge graph-based approach

ROS (Robot Operating System) packages have become increasingly popular as a type of software artifact that can be effectively reused in robotic software development. Indeed, finding suitable ROS packages that closely match the software's functional requirements from the vast number of available packages is a nontrivial task using current search methods. The traditional search methods for ROS packages often involve inputting keywords related to robotic tasks into general-purpose search engines or code hosting platforms to obtain approximate results of all potentially suitable ROS packages. However, the accuracy of these search methods remains relatively low because the task-related keywords may not precisely match the functionalities offered by the ROS packages. To improve the search accuracy of ROS packages, this paper presents a novel semantic-based search approach that relies on the semantic-level ROS Package Knowledge Graph (RPKG) to automatically retrieve the most suitable ROS packages. Firstly, to construct the RPKG, we employ multi-dimensional feature extraction techniques to extract semantic concepts from the dataset of ROS package text descriptions. The semantic features extracted from this process result in a substantial number of entities and relationships. Subsequently, we create a robot domain-specific small corpus and further fine-tune a pre-trained language model, BERT-ROS, to generate embeddings that effectively represent the semantics of the extracted features. These embeddings play a crucial role in facilitating semantic-level understanding and comparisons during the ROS package search process within the RPKG. Secondly, we introduce a novel semantic matching-based search algorithm that incorporates the weighted similarities of multiple features from user search queries, which searches out more accurate ROS packages than the traditional keyword search method.

cs.SE↗

arXiv2023

Transferring Modality-Aware Pedestrian Attentive Learning for Visible-Infrared Person Re-identification

Visible-infrared person re-identification (VI-ReID) aims to search the same pedestrian of interest across visible and infrared modalities. Existing models mainly focus on compensating for modality-specific information to reduce modality variation. However, these methods often lead to a higher computational overhead and may introduce interfering information when generating the corresponding images or features. To address this issue, it is critical to leverage pedestrian-attentive features and learn modality-complete and -consistent representation. In this paper, a novel Transferring Modality-Aware Pedestrian Attentive Learning (TMPA) model is proposed, focusing on the pedestrian regions to efficiently compensate for missing modality-specific features. Specifically, we propose a region-based data augmentation module PedMix to enhance pedestrian region coherence by mixing the corresponding regions from different modalities. A lightweight hybrid compensation module, i.e., the Modality Feature Transfer (MFT), is devised to integrate cross attention and convolution networks to fully explore the discriminative modality-complete features with minimal computational overhead. Extensive experiments conducted on the benchmark SYSU-MM01 and RegDB datasets demonstrated the effectiveness of our proposed TMPA model.

cs.CV↗