Search

To mitigate the misuse of large language models (LLMs), such as disinformation, automated phishing, and academic cheating, there is a pressing need for the capability of identifying LLM-generated texts. Watermarking emerges as one promising solution: it plants statistical signals into LLMs' generative processes and subsequently verifies whether LLMs produce given texts. Various watermarking methods (``watermarkers'') have been proposed; yet, due to the lack of unified evaluation platforms, many critical questions remain under-explored: i) What are the strengths/limitations of various watermarkers, especially their attack robustness? ii) How do various design choices impact their robustness? iii) How to optimally operate watermarkers in adversarial environments? To fill this gap, we systematize existing LLM watermarkers and watermark removal attacks, mapping out their design spaces. We then develop WaterPark, a unified platform that integrates 10 state-of-the-art watermarkers and 12 representative attacks. More importantly, leveraging WaterPark, we conduct a comprehensive assessment of existing watermarkers, unveiling the impact of various design choices on their attack robustness. For instance, a watermarker's resilience to increasingly intensive attacks hinges on its context dependency. We further explore the best practices to operate watermarkers in adversarial environments. For instance, using a generic detector alongside a watermark-specific detector improves the security of vulnerable watermarkers. We believe our study sheds light on current LLM watermarking techniques while WaterPark serves as a valuable testbed to facilitate future research., Comment: 22 pages

Text-to-image diffusion models have emerged as powerful tools for generating high-quality images from textual descriptions. However, their increasing popularity has raised significant copyright concerns, as these models can be misused to reproduce copyrighted content without authorization. In response, recent studies have proposed various copyright protection methods, including adversarial perturbation, concept erasure, and watermarking techniques. However, their effectiveness and robustness against advanced attacks remain largely unexplored. Moreover, the lack of unified evaluation frameworks has hindered systematic comparison and fair assessment of different approaches. To bridge this gap, we systematize existing copyright protection methods and attacks, providing a unified taxonomy of their design spaces. We then develop CopyrightMeter, a unified evaluation framework that incorporates 17 state-of-the-art protections and 16 representative attacks. Leveraging CopyrightMeter, we comprehensively evaluate protection methods across multiple dimensions, thereby uncovering how different design choices impact fidelity, efficacy, and resilience under attacks. Our analysis reveals several key findings: (i) most protections (16/17) are not resilient against attacks; (ii) the "best" protection varies depending on the target priority; (iii) more advanced attacks significantly promote the upgrading of protections. These insights provide concrete guidance for developing more robust protection methods, while its unified evaluation protocol establishes a standard benchmark for future copyright protection research in text-to-image generation.

With the continuous development of large language models (LLMs), transformer-based models have made groundbreaking advances in numerous natural language processing (NLP) tasks, leading to the emergence of a series of agents that use LLMs as their control hub. While LLMs have achieved success in various tasks, they face numerous security and privacy threats, which become even more severe in the agent scenarios. To enhance the reliability of LLM-based applications, a range of research has emerged to assess and mitigate these risks from different perspectives. To help researchers gain a comprehensive understanding of various risks, this survey collects and analyzes the different threats faced by these agents. To address the challenges posed by previous taxonomies in handling cross-module and cross-stage threats, we propose a novel taxonomy framework based on the sources and impacts. Additionally, we identify six key features of LLM-based agents, based on which we summarize the current research progress and analyze their limitations. Subsequently, we select four representative agents as case studies to analyze the risks they may face in practical use. Finally, based on the aforementioned analyses, we propose future research directions from the perspectives of data, methodology, and policy, respectively.

We introduce Edify Image, a family of diffusion models capable of generating photorealistic image content with pixel-perfect accuracy. Edify Image utilizes cascaded pixel-space diffusion models trained using a novel Laplacian diffusion process, in which image signals at different frequency bands are attenuated at varying rates. Edify Image supports a wide range of applications, including text-to-image synthesis, 4K upsampling, ControlNets, 360 HDR panorama generation, and finetuning for image customization.

An accurate description of the photon spectrum line shape is essential for extracting resonance parameters of the $\eta_c$ meson through the radiative transition $J/\psi \to \gamma \eta_{c}$. However, a persistent challenge remains in the form of a divergent tail at high photon energies, arising from the $E_{\gamma}^3$ factor in theoretical calculations. Various damping functions have been proposed to mitigate this effect in practical experiments, but their empirical nature lacks a rigorous theoretical basis. In this study, we introduce two key considerations: incorporating full-order contributions of the Bessel function in the overlap integral of charmonium wave functions and the phase space factor neglected in previous experimental studies. By accounting for these factors, we demonstrate a more rational and effective damping function of the divergent tail associated with the $E_{\gamma}^3$ term. We present the implications of these findings on experimental measurements and provide further insights through toy Monte Carlo simulations., Comment: 5 pages, 8 figures

Jailbreak attacks circumvent LLMs' built-in safeguards by concealing harmful queries within jailbreak prompts. While existing defenses primarily focus on mitigating the effects of jailbreak prompts, they often prove inadequate as jailbreak prompts can take arbitrary, adaptive forms. This paper presents RobustKV, a novel defense that adopts a fundamentally different approach by selectively removing critical tokens of harmful queries from key-value (KV) caches. Intuitively, for a jailbreak prompt to be effective, its tokens must achieve sufficient `importance' (as measured by attention scores), which inevitably lowers the importance of tokens in the concealed harmful query. Thus, by strategically evicting the KVs of the lowest-ranked tokens, RobustKV diminishes the presence of the harmful query in the KV cache, thus preventing the LLM from generating malicious responses. Extensive evaluation using benchmark datasets and models demonstrates that RobustKV effectively counters state-of-the-art jailbreak attacks while maintaining the LLM's general performance on benign queries. Moreover, RobustKV creates an intriguing evasiveness dilemma for adversaries, forcing them to balance between evading RobustKV and bypassing the LLM's built-in safeguards. This trade-off contributes to RobustKV's robustness against adaptive attacks. (warning: this paper contains potentially harmful content generated by LLMs.)

Simultaneous state estimation and mapping is an essential capability for mobile robots working in dynamic urban environment. The majority of existing SLAM solutions heavily rely on a primarily static assumption. However, due to the presence of moving vehicles and pedestrians, this assumption does not always hold, leading to localization accuracy decreased and maps distorted. To address this challenge, we propose TRLO, a dynamic LiDAR odometry that efficiently improves the accuracy of state estimation and generates a cleaner point cloud map. To efficiently detect dynamic objects in the surrounding environment, a deep learning-based method is applied, generating detection bounding boxes. We then design a 3D multi-object tracker based on Unscented Kalman Filter (UKF) and nearest neighbor (NN) strategy to reliably identify and remove dynamic objects. Subsequently, a fast two-stage iterative nearest point solver is employed to solve the state estimation using cleaned static point cloud. Note that a novel hash-based keyframe database management is proposed for fast access to search keyframes. Furthermore, all the detected object bounding boxes are leveraged to impose posture consistency constraint to further refine the final state estimation. Extensive evaluations and ablation studies conducted on the KITTI and UrbanLoco datasets demonstrate that our approach not only achieves more accurate state estimation but also generates cleaner maps, compared with baselines., Comment: 8pages, 5figures

Parameter Efficient Fine-Tuning (PEFT) offers an efficient solution for fine-tuning large pretrained language models for downstream tasks. However, most PEFT strategies are manually designed, often resulting in suboptimal performance. Recent automatic PEFT approaches aim to address this but face challenges such as search space entanglement, inefficiency, and lack of integration between parameter budgets and search processes. To overcome these issues, we introduce a novel Budget-guided Iterative search strategy for automatic PEFT (BIPEFT), significantly enhancing search efficiency. BIPEFT employs a new iterative search strategy to disentangle the binary module and rank dimension search spaces. Additionally, we design early selection strategies based on parameter budgets, accelerating the learning process by gradually removing unimportant modules and fixing rank dimensions. Extensive experiments on public benchmarks demonstrate the superior performance of BIPEFT in achieving efficient and effective PEFT for downstream tasks with a low parameter budget., Comment: Accepted to EMNLP 2024 (Findings)

We investigate operator dynamics and entanglement growth in dual-unitary circuits, a class of locally scrambled quantum systems that enables efficient simulation beyond the exponential complexity of the Hilbert space. By mapping the operator evolution to a classical Markov process,we perform Monte Carlo simulations to access the time evolution of local operator density and entanglement with polynomial computational cost. Our results reveal that the operator density converges exponentially to a steady-state value, with analytical bounds that match our simulations. Additionally, we observe a volume-law scaling of operator entanglement across different subregions,and identify a critical transition from maximal to sub-maximal entanglement growth, governed by the circuit's gate parameter. This transition, confirmed by both mean-field theory and Monte Carlo simulations, provides new insights into operator entanglement dynamics in quantum many-body systems. Our work offers a scalable computational framework for studying long-time operator evolution and entanglement, paving the way for deeper exploration of quantum information dynamics., Comment: 12 pages,12 figures

Despite the impressive advancements made in recent low-light image enhancement techniques, the scarcity of paired data has emerged as a significant obstacle to further advancements. This work proposes a mean-teacher-based semi-supervised low-light enhancement (Semi-LLIE) framework that integrates the unpaired data into model training. The mean-teacher technique is a prominent semi-supervised learning method, successfully adopted for addressing high-level and low-level vision tasks. However, two primary issues hinder the naive mean-teacher method from attaining optimal performance in low-light image enhancement. Firstly, pixel-wise consistency loss is insufficient for transferring realistic illumination distribution from the teacher to the student model, which results in color cast in the enhanced images. Secondly, cutting-edge image enhancement approaches fail to effectively cooperate with the mean-teacher framework to restore detailed information in dark areas due to their tendency to overlook modeling structured information within local regions. To mitigate the above issues, we first introduce a semantic-aware contrastive loss to faithfully transfer the illumination distribution, contributing to enhancing images with natural colors. Then, we design a Mamba-based low-light image enhancement backbone to effectively enhance Mamba's local region pixel relationship representation ability with a multi-scale feature learning scheme, facilitating the generation of images with rich textural details. Further, we propose novel perceptive loss based on the large-scale vision-language Recognize Anything Model (RAM) to help generate enhanced images with richer textual details. The experimental results indicate that our Semi-LLIE surpasses existing methods in both quantitative and qualitative metrics.

When Unmanned Aerial Vehicles (UAVs) perform high-precision communication tasks, such as searching for users and providing emergency coverage, positioning errors between base stations and users make it challenging to deploy trajectory planning algorithms. To address these challenges caused by position errors, a framework was proposed to compensate it by Channel Knowledge Map (CKM), which stores channel state information (CSI). By taking the positions with errors as input, the generated CKM could give a prediction of signal attenuation which is close to true positions. Based on that, the predictions are utilized to calculate the received power and a PPO-based algorithm is applied to optimize the compensation. After training, the framework is able to find a strategy that minimize the flight time under communication constraints and positioning error. Besides, the confidence interval is calculated to assist the allocation of power and the update of CKM is studied to adapt to the dynamic environment. Simulation results show the robustness of CKM to positioning error and environmental changes, and the superiority of CKM-assisted UAV communication design.

This paper introduces a learning-based low-level controller for quadcopters, which adaptively controls quadcopters with significant variations in mass, size, and actuator capabilities. Our approach leverages a combination of imitation learning and reinforcement learning, creating a fast-adapting and general control framework for quadcopters that eliminates the need for precise model estimation or manual tuning. The controller estimates a latent representation of the vehicle's system parameters from sensor-action history, enabling it to adapt swiftly to diverse dynamics. Extensive evaluations in simulation demonstrate the controller's ability to generalize to unseen quadcopter parameters, with an adaptation range up to 16 times broader than the training set. In real-world tests, the controller is successfully deployed on quadcopters with mass differences of 3.7 times and propeller constants varying by more than 100 times, while also showing rapid adaptation to disturbances such as off-center payloads and motor failures. These results highlight the potential of our controller in extreme adaptation to simplify the design process and enhance the reliability of autonomous drone operations in unpredictable environments. The video and code are at: https://github.com/muellerlab/xadapt_ctrl, Comment: 12 pages, 9 figures

Metro operation management relies on accurate predictions of passenger flow in the future. This study begins by integrating cross-city (including source and target city) knowledge and developing a short-term passenger flow prediction framework (METcross) for the metro. Firstly, we propose a basic framework for modeling cross-city metro passenger flow prediction from the perspectives of data fusion and transfer learning. Secondly, METcross framework is designed to use both static and dynamic covariates as inputs, including economy and weather, that help characterize station passenger flow features. This framework consists of two steps: pre-training on the source city and fine-tuning on the target city. During pre-training, data from the source city trains the feature extraction and passenger flow prediction models. Fine-tuning on the target city involves using the source city's trained model as the initial parameter and fusing the feature embeddings of both cities to obtain the passenger flow prediction results. Finally, we tested the basic prediction framework and METcross framework on the metro networks of Wuxi and Chongqing to experimentally analyze their efficacy. Results indicate that the METcross framework performs better than the basic framework and can reduce the Mean Absolute Error and Root Mean Squared Error by 22.35% and 26.18%, respectively, compared to single-city prediction models.

The path-specific effect (PSE) is of primary interest in mediation analysis when multiple intermediate variables between treatment and outcome are observed, as it can isolate the specific effect through each mediator, thus mitigating potential bias arising from other intermediate variables serving as mediator-outcome confounders. However, estimation and inference of PSE become challenging in the presence of nonignorable missing covariates, a situation particularly common in epidemiological research involving sensitive patient information. In this paper, we propose a fully nonparametric methodology to address this challenge. We establish identification for PSE by expressing it as a functional of observed data and demonstrate that the associated nuisance functions can be uniquely determined through sequential optimization problems by leveraging a shadow variable. Then we propose a sieve-based regression imputation approach for estimation. We establish the large-sample theory for the proposed estimator, and introduce a robust and efficient approach to make inference for PSE. The proposed method is applied to the NHANES dataset to investigate the mediation roles of dyslipidemia and obesity in the pathway from Type 2 diabetes mellitus to cardiovascular disease., Comment: 37 pages, 6 figures

Physics-informed deep learning (PIDL)-based models have recently garnered remarkable success in traffic state estimation (TSE). However, the prior knowledge used to guide regularization training in current mainstream architectures is based on deterministic physical models. The drawback is that a solely deterministic model fails to capture the universally observed traffic flow dynamic scattering effect, thereby yielding unreliable outcomes for traffic control. This study, for the first time, proposes stochastic physics-informed deep learning (SPIDL) for traffic state estimation. The idea behind such SPIDL is simple and is based on the fact that a stochastic fundamental diagram provides the entire range of possible speeds for any given density with associated probabilities. Specifically, we select percentile-based fundamental diagram and distribution-based fundamental diagram as stochastic physics knowledge, and design corresponding physics-uninformed neural networks for effective fusion, thereby realizing two specific SPIDL models, namely \text{$\alpha$}-SPIDL and \text{$\cal B$}-SPIDL. The main contribution of SPIDL lies in addressing the "overly centralized guidance" caused by the one-to-one speed-density relationship in deterministic models during neural network training, enabling the network to digest more reliable knowledge-based constraints.Experiments on the real-world dataset indicate that proposed SPIDL models achieve accurate traffic state estimation in sparse data scenarios. More importantly, as expected, SPIDL models reproduce well the scattering effect of field observations, demonstrating the effectiveness of fusing stochastic physics model knowledge with deep learning frameworks., Comment: under review in Information Fusion

In this paper, we study user association and wireless bandwidth allocation for a hierarchical federated learning system that consists of mobile users, edge servers, and a cloud server. To minimize the length of a global round in hierarchical federated learning with equal bandwidth allocation, we formulate a combinatorial optimization problem. We design the twin sorting dynamic programming (TSDP) algorithm that obtains a globally optimal solution in polynomial time when there are two edge servers. In addition, we put forward the TSDP-assisted algorithm for user association when there are three or more edge servers. Furthermore, given a user association matrix, we formulate and solve a convex optimization problem for optimal wireless bandwidth allocation. Simulation results show that the proposed approach outperforms a number of alternative schemes., Comment: 14 pages

Most LiDAR odometry and SLAM systems construct maps in point clouds, which are discrete and sparse when zoomed in, making them not directly suitable for navigation. Mesh maps represent a dense and continuous map format with low memory consumption, which can approximate complex structures with simple elements, attracting significant attention of researchers in recent years. However, most implementations operate under a static environment assumption. In effect, moving objects cause ghosting, potentially degrading the quality of meshing. To address these issues, we propose a plug-and-play meshing module adapting to dynamic environments, which can easily integrate with various LiDAR odometry to generally improve the pose estimation accuracy of odometry. In our meshing module, a novel two-stage coarse-to-fine dynamic removal method is designed to effectively filter dynamic objects, generating consistent, accurate, and dense mesh maps. To our best know, this is the first mesh construction method with explicit dynamic removal. Additionally, conducive to Gaussian process in mesh construction, sliding window-based keyframe aggregation and adaptive downsampling strategies are used to ensure the uniformity of point cloud. We evaluate the localization and mapping accuracy on five publicly available datasets. Both qualitative and quantitative results demonstrate the superiority of our method compared with the state-of-the-art algorithms. The code and introduction video are publicly available at https://yaepiii.github.io/CAD-Mesher/., Comment: 9 pages, 7 figures

We propose the convex-roof extension of quantum conditional mutual information ("co(QCMI)") as a diagnostic of long-range entanglement in a mixed state. We focus primarily on topological states subjected to local decoherence, and employ the Levin-Wen scheme to define co(QCMI), so that for a pure state, co(QCMI) equals topological entanglement entropy (TEE). By construction, co(QCMI) is zero if and only if a mixed state can be decomposed as a convex sum of pure states with zero TEE. We show that co(QCMI) is non-increasing with increasing decoherence when Kraus operators are proportional to the product of onsite unitaries. This implies that unlike a pure state transition between a topologically trivial and a non-trivial phase, the long-range entanglement at a decoherence-induced topological phase transition as quantified by co(QCMI) is less than or equal to that in the proximate topological phase. For the 2d toric code decohered by onsite bit/phase-flip noise, we show that co(QCMI) is non-zero below the error-recovery threshold and zero above it. Relatedly, the decohered state cannot be written as a convex sum of short-range entangled pure states below the threshold. We conjecture and provide evidence that in this example, co(QCMI) equals TEE of a recently introduced pure state. In particular, we develop a tensor-assisted Monte Carlo (TMC) computation method to efficiently evaluate the R\'enyi TEE for the aforementioned pure state and provide non-trivial consistency checks for our conjecture. We use TMC to also calculate the universal scaling dimension of the anyon-condensation order parameter at this transition., Comment: 17 pages main text, 3 pages of appendices, 7 figures

Personalized text-to-image generation models enable users to create images that depict their individual possessions in diverse scenes, finding applications in various domains. To achieve the personalization capability, existing methods rely on finetuning a text-to-image foundation model on a user's custom dataset, which can be non-trivial for general users, resource-intensive, and time-consuming. Despite attempts to develop finetuning-free methods, their generation quality is much lower compared to their finetuning counterparts. In this paper, we propose Joint-Image Diffusion (\jedi), an effective technique for learning a finetuning-free personalization model. Our key idea is to learn the joint distribution of multiple related text-image pairs that share a common subject. To facilitate learning, we propose a scalable synthetic dataset generation technique. Once trained, our model enables fast and easy personalization at test time by simply using reference images as input during the sampling process. Our approach does not require any expensive optimization process or additional modules and can faithfully preserve the identity represented by any number of reference images. Experimental results show that our model achieves state-of-the-art generation quality, both quantitatively and qualitatively, significantly outperforming both the prior finetuning-based and finetuning-free personalization baselines., Comment: CVPR 24

Univariate marked Hawkes processes are used to model a range of real-world phenomena including earthquake aftershock sequences, contagious disease spread, content diffusion on social media platforms, and order book dynamics. This paper illustrates a fundamental connection between univariate marked Hawkes processes and multivariate Hawkes processes. Exploiting this connection renders a framework that can be built upon for expressive and flexible inference on diverse data. Specifically, multivariate unmarked Hawkes representations are introduced as a tool to parameterize univariate marked Hawkes processes. We show that such multivariate representations can asymptotically approximate a large class of univariate marked Hawkes processes, are stationary given the approximated process is stationary, and that resultant conditional intensity parameters are identifiable. A simulation study demonstrates the efficacy of this approach, and provides heuristic bounds for error induced by the relatively larger parameter space of multivariate Hawkes processes., Comment: 26 pages, 3 figures, submitted to the Annals of Statistics

Thanks to their remarkable denoising capabilities, diffusion models are increasingly being employed as defensive tools to reinforce the security of other models, notably in purifying adversarial examples and certifying adversarial robustness. However, the security risks of these practices themselves remain largely unexplored, which is highly concerning. To bridge this gap, this work investigates the vulnerabilities of security-enhancing diffusion models. Specifically, we demonstrate that these models are highly susceptible to DIFF2, a simple yet effective backdoor attack, which substantially diminishes the security assurance provided by such models. Essentially, DIFF2 achieves this by integrating a malicious diffusion-sampling process into the diffusion model, guiding inputs embedded with specific triggers toward an adversary-defined distribution while preserving the normal functionality for clean inputs. Our case studies on adversarial purification and robustness certification show that DIFF2 can significantly reduce both post-purification and certified accuracy across benchmark datasets and models, highlighting the potential risks of relying on pre-trained diffusion models as defensive tools. We further explore possible countermeasures, suggesting promising avenues for future research.

We design 3D-printed motor-driven active particles and find that their dynamics can be characterized using the model of overdamped chiral active Brownian particles (ABPs), as demonstrated by measured angular statistics and translational mean squared displacements (MSDs). Furthermore, we propose a minimal model that reproduces the double-peak velocity distributions and further predicts a transition from the single-peak to the double-peak displacement distributions in short-time regimes. The model provides a clear physics picture of these phenomena, originating from the competition between the active motion and the translational diffusion. Our experiments confirm such picture. The minimal model enhances our understanding of activity-driven non-Gaussian phenomena. The designed particles could be further applied in the study of collective chiral motions.

Pre-trained language models (PLMs) have attracted enormous attention over the past few years with their unparalleled performances. Meanwhile, the soaring cost to train PLMs as well as their amazing generalizability have jointly contributed to few-shot fine-tuning and prompting as the most popular training paradigms for natural language processing (NLP) models. Nevertheless, existing studies have shown that these NLP models can be backdoored such that model behavior is manipulated when trigger tokens are presented. In this paper, we propose PromptFix, a novel backdoor mitigation strategy for NLP models via adversarial prompt-tuning in few-shot settings. Unlike existing NLP backdoor removal methods, which rely on accurate trigger inversion and subsequent model fine-tuning, PromptFix keeps the model parameters intact and only utilizes two extra sets of soft tokens which approximate the trigger and counteract it respectively. The use of soft tokens and adversarial optimization eliminates the need to enumerate possible backdoor configurations and enables an adaptive balance between trigger finding and preservation of performance. Experiments with various backdoor attacks validate the effectiveness of the proposed method and the performances when domain shift is present further shows PromptFix's applicability to models pretrained on unknown data source which is the common case in prompt tuning scenarios., Comment: NAACL 2024

The fusion of a low-resolution hyperspectral image (LR-HSI) with a high-resolution multispectral image (HR-MSI) has emerged as an effective technique for achieving HSI super-resolution (SR). Previous studies have mainly concentrated on estimating the posterior distribution of the latent high-resolution hyperspectral image (HR-HSI), leveraging an appropriate image prior and likelihood computed from the discrepancy between the latent HSI and observed images. Low rankness stands out for preserving latent HSI characteristics through matrix factorization among the various priors. However, the primary limitation in previous studies lies in the generalization of a fusion model with fixed resolution scales, which necessitates retraining whenever output resolutions are changed. To overcome this limitation, we propose a novel continuous low-rank factorization (CLoRF) by integrating two neural representations into the matrix factorization, capturing spatial and spectral information, respectively. This approach enables us to harness both the low rankness from the matrix factorization and the continuity from neural representation in a self-supervised manner.Theoretically, we prove the low-rank property and Lipschitz continuity in the proposed continuous low-rank factorization. Experimentally, our method significantly surpasses existing techniques and achieves user-desired resolutions without the need for neural network retraining. Code is available at https://github.com/wangting1907/CLoRF-Fusion.

Face Recognition Systems (FRS) have increasingly integrated into critical applications, including surveillance and user authentication, highlighting their pivotal role in modern security systems. Recent studies have revealed vulnerabilities in FRS to adversarial (e.g., adversarial patch attacks) and backdoor attacks (e.g., training data poisoning), raising significant concerns about their reliability and trustworthiness. Previous studies primarily focus on traditional adversarial or backdoor attacks, overlooking the resource-intensive or privileged-manipulation nature of such threats, thus limiting their practical generalization, stealthiness, universality and robustness. Correspondingly, in this paper, we delve into the inherent vulnerabilities in FRS through user studies and preliminary explorations. By exploiting these vulnerabilities, we identify a novel attack, facial identity backdoor attack dubbed FIBA, which unveils a potentially more devastating threat against FRS:an enrollment-stage backdoor attack. FIBA circumvents the limitations of traditional attacks, enabling broad-scale disruption by allowing any attacker donning a specific trigger to bypass these systems. This implies that after a single, poisoned example is inserted into the database, the corresponding trigger becomes a universal key for any attackers to spoof the FRS. This strategy essentially challenges the conventional attacks by initiating at the enrollment stage, dramatically transforming the threat landscape by poisoning the feature database rather than the training data., Comment: 19 pages,version 3

Explicit Congestion Notification (ECN)-based congestion control schemes have been widely adopted in high-speed data center networks (DCNs), where the ECN marking threshold plays a determinant role in guaranteeing a packet lossless DCN. However, existing approaches either employ static settings with immutable thresholds that cannot be dynamically self-adjusted to adapt to network dynamics, or fail to take into account many-to-one traffic patterns and different requirements of different types of traffic, resulting in relatively poor performance. To address these problems, this paper proposes a novel learning-based automatic ECN tuning scheme, named PET, based on the multi-agent Independent Proximal Policy Optimization (IPPO) algorithm. PET dynamically adjusts ECN thresholds by fully considering pivotal congestion-contributing factors, including queue length, output data rate, output rate of ECN-marked packets, current ECN threshold, the extent of incast, and the ratio of mice and elephant flows. PET adopts the Decentralized Training and Decentralized Execution (DTDE) paradigm and combines offline and online training to accommodate network dynamics. PET is also fair and readily deployable with commodity hardware. Comprehensive experimental results demonstrate that, compared with state-of-the-art static schemes and the learning-based automatic scheme, our PET achieves better performance in terms of flow completion time, convergence rate, queue length variance, and system robustness.

Muon imaging technology is an innovative imaging technique that can be applied in volcano imaging, heavy nuclear material detection, and archaeological research. The Micromegas detector is a promising choice for muon imaging due to its high spatial resolution and large area. However, the large number of readout channels poses a challenge for electronics. In this paper, a compact front-end electronics (FEE) for reading Micromegas detectors is presented. The electronics use the commercial current-to-digital readout chip, ADAS1128, which integrates 128 current amplifiers for multi-channel charge measurement. After verifying the basic performance of the electronics, the energy resolution was obtained with a radioactive source. Furthermore, a muon imaging system prototype was set up and its spatial resolution was evaluated in a test with cosmic ray muons. The system prototype can reconstruct the boundaries of sufficiently massive objects with a size of 2 cm in a scattering imaging test.

Although Federated Learning (FL) enables collaborative learning in Artificial Intelligence of Things (AIoT) design, it fails to work on low-memory AIoT devices due to its heavy memory usage. To address this problem, various federated pruning methods are proposed to reduce memory usage during inference. However, few of them can substantially mitigate the memory burdens during pruning and training. As an alternative, zeroth-order or backpropagation-free (BP-Free) methods can partially alleviate the memory consumption, but they suffer from scaling up and large computation overheads, since the gradient estimation error and floating point operations (FLOPs) increase as the dimensionality of the model parameters grows. In this paper, we propose a federated foresight pruning method based on Neural Tangent Kernel (NTK), which can seamlessly integrate with federated BP-Free training frameworks. We present an approximation to the computation of federated NTK by using the local NTK matrices. Moreover, we demonstrate that the data-free property of our method can substantially reduce the approximation error in extreme data heterogeneity scenarios. Since our approach improves the performance of the vanilla BP-Free method with fewer FLOPs and truly alleviates memory pressure during training and inference, it makes FL more friendly to low-memory devices. Comprehensive experimental results obtained from simulation- and real test-bed-based platforms show that our federated foresight-pruning method not only preserves the ability of the dense model with a memory reduction up to 9x but also boosts the performance of the vanilla BP-Free method with dramatically fewer FLOPs.

Automatically condensing multiple topic-related scientific papers into a succinct and concise summary is referred to as Multi-Document Scientific Summarization (MDSS). Currently, while commonly used abstractive MDSS methods can generate flexible and coherent summaries, the difficulty in handling global information and the lack of guidance during decoding still make it challenging to generate better summaries. To alleviate these two shortcomings, this paper introduces summary candidates into MDSS, utilizing the global information of the document set and additional guidance from the summary candidates to guide the decoding process. Our insights are twofold: Firstly, summary candidates can provide instructive information from both positive and negative perspectives, and secondly, selecting higher-quality candidates from multiple options contributes to producing better summaries. Drawing on the insights, we propose a summary candidates fusion framework -- Disentangling Instructive information from Ranked candidates (DIR) for MDSS. Specifically, DIR first uses a specialized pairwise comparison method towards multiple candidates to pick out those of higher quality. Then DIR disentangles the instructive information of summary candidates into positive and negative latent variables with Conditional Variational Autoencoder. These variables are further incorporated into the decoder to guide generation. We evaluate our approach with three different types of Transformer-based models and three different types of candidates, and consistently observe noticeable performance improvements according to automatic and human evaluation. More analyses further demonstrate the effectiveness of our model in handling global information and enhancing decoding controllability., Comment: Accepted by SIGIR 2024

Contrastive Learning (CL) has attracted enormous attention due to its remarkable capability in unsupervised representation learning. However, recent works have revealed the vulnerability of CL to backdoor attacks: the feature extractor could be misled to embed backdoored data close to an attack target class, thus fooling the downstream predictor to misclassify it as the target. Existing attacks usually adopt a fixed trigger pattern and poison the training set with trigger-injected data, hoping for the feature extractor to learn the association between trigger and target class. However, we find that such fixed trigger design fails to effectively associate trigger-injected data with target class in the embedding space due to special CL mechanisms, leading to a limited attack success rate (ASR). This phenomenon motivates us to find a better backdoor trigger design tailored for CL framework. In this paper, we propose a bi-level optimization approach to achieve this goal, where the inner optimization simulates the CL dynamics of a surrogate victim, and the outer optimization enforces the backdoor trigger to stay close to the target throughout the surrogate CL procedure. Extensive experiments show that our attack can achieve a higher attack success rate (e.g., $99\%$ ASR on ImageNet-100) with a very low poisoning rate ($1\%$). Besides, our attack can effectively evade existing state-of-the-art defenses. Code is available at: https://github.com/SWY666/SSL-backdoor-BLTO., Comment: Accepted by ICLR 2024

Propelled by their remarkable capabilities to generate novel and engaging content, Generative Artificial Intelligence (GenAI) technologies are disrupting traditional workflows in many industries. While prior research has examined GenAI from a techno-centric perspective, there is still a lack of understanding about how users perceive and utilize GenAI in real-world scenarios. To bridge this gap, we conducted semi-structured interviews with (N=18) GenAI users in creative industries, investigating the human-GenAI co-creation process within a holistic LUA (Learning, Using and Assessing) framework. Our study uncovered an intriguingly complex landscape: Prospects-GenAI greatly fosters the co-creation between human expertise and GenAI capabilities, profoundly transforming creative workflows; Challenges-Meanwhile, users face substantial uncertainties and complexities arising from resource availability, tool usability, and regulatory compliance; Strategies-In response, users actively devise various strategies to overcome many of such challenges. Our study reveals key implications for the design of future GenAI tools., Comment: In Proceedings of the CHI Conference on Human Factors in Computing Systems (CHI'24), May 11-16, 2024, Honolulu, HI, USA. (accidentally submitted as arXiv:2302.10827v2)

Materials with in-plane electrical anisotropy have great potential for designing artificial synaptic devices. However, natural materials with strong intrinsic in-plane electrical anisotropy are rare. We introduce a simple strategy to produce extremely large electrical anisotropy via grating gating of a semiconductor two-dimensional electron gas (2DEG) of AlGaN/GaN. We show that periodically modulated electric potential in the 2DEG induces in-plane electrical anisotropy, which is significantly enhanced in a magnetic field, leading to an ultra large electrical anisotropy. This is induced by a giant positive magnetoresistance and a giant negative magnetoresistance under two orthogonally oriented in-plane current flows, respectively. This giant electrical anisotropy is in-situ tunable by tailoring both the grating gate voltage and the magnetic field. Our semiconductor device with controllable giant electrical anisotropy will stimulate new device applications, such as multi-terminal memtransistors and bionic synapses.

This paper studies system identification of high-dimensional ARMA models with binary-valued observations. The existing paper can only deal with the case where the regression term is only one-dimensional. In this paper, the ARMA model with arbitrary dimensions is considered, which is more challenging. Different from the identification of FIR models with binary-valued observations, the prediction of original system output and the parameter both need to be estimated in ARMA models. An online identification algorithm consisting of parameter estimation and prediction of original system output is proposed. The parameter estimation and the prediction of original output are strongly coupled but mutually reinforcing. By analyzing the two estimates at the same time instead of analyzing separately, we finally prove that the parameter estimate can converge to the true parameter with convergence rate O(1/k) under certain conditions. Simulations are given to demonstrate the theoretical results.

Most point process models for earthquakes currently in the literature assume the magnitude distribution is i.i.d. potentially hindering the ability of the model to describe the main features of data sets containing multiple earthquake mainshock aftershock sequences in succession. This study presents a novel multidimensional fractional Hawkes process model designed to capture magnitude dependent triggering behaviour by incorporating history dependence into the magnitude distribution. This is done by discretising the magnitude range into disjoint intervals and modelling events with magnitude in these ranges as the subprocesses of a mutually exciting Hawkes process using the Mittag-Leffler density as the kernel function. We demonstrate this model's use by applying it to two data sets, Japan and the Middle America Trench, both containing multiple mainshock aftershock sequences and compare it to the existing ETAS model by using information criteria, residual diagnostics and retrospective prediction performance. We find that for both data sets all metrics indicate that the multidimensional fractional Hawkes process performs favourably against the ETAS model. Furthermore, using the multidimensional fractional Hawkes process we are able to infer characteristics of the data sets that are consistent with results currently in the literature and that cannot be found by using the ETAS model., Comment: 37 pages, 10 tables, 3 figures