Leveraging Information Consistency in Frequency and Spatial Domain for Adversarial Attacks

Adversarial examples are a key method to exploit deep neural networks. Using gradient information, such examples can be generated in an efficient way without altering the victim model. Recent frequency domain transformation has further enhanced the transferability of such adversarial examples, such as spectrum simulation attack. In this work, we investigate the effectiveness of frequency domain-based attacks, aligning with similar findings in the spatial domain. Furthermore, such consistency between the frequency and spatial domains provides insights into how gradient-based adversarial attacks induce perturbations across different domains, which is yet to be explored. Hence, we propose a simple, effective, and scalable gradient-based adversarial attack algorithm leveraging the information consistency in both frequency and spatial domains. We evaluate the algorithm for its effectiveness against different models. Extensive experiments demonstrate that our algorithm achieves state-of-the-art results compared to other gradient-based algorithms. Our code is available at: https://github.com/LMBTough/FSA.

Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data

Despite the proven utility of large language models (LLMs) in real-world applications, there remains a lack of understanding regarding how they leverage their large-scale pretraining text corpora to achieve such capabilities. In this work, we investigate the interplay between generalization and memorization in pretrained LLMs at scale, through a comprehensive $n$-gram analysis of their training data. Our experiments focus on three general task types: translation, question-answering, and multiple-choice reasoning. With various sizes of open-source LLMs and their pretraining corpora, we observe that as the model size increases, the task-relevant $n$-gram pair data becomes increasingly important, leading to improved task performance, decreased memorization, stronger generalization, and emergent abilities. Our results support the hypothesis that LLMs' capabilities emerge from a delicate balance of memorization and generalization with sufficient task-related pretraining data, and point the way to larger-scale analyses that could further improve our understanding of these models.

ReLaX-VQA: Residual Fragment and Layer Stack Extraction for Enhancing Video Quality Assessment

With the rapid growth of User-Generated Content (UGC) exchanged between users and sharing platforms, the need for video quality assessment in the wild has emerged. UGC is mostly acquired using consumer devices and undergoes multiple rounds of compression or transcoding before reaching the end user. Therefore, traditional quality metrics that require the original content as a reference cannot be used. In this paper, we propose ReLaX-VQA, a novel No-Reference Video Quality Assessment (NR-VQA) model that aims to address the challenges of evaluating the diversity of video content and the assessment of its quality without reference videos. ReLaX-VQA uses fragments of residual frames and optical flow, along with different expressions of spatial features of the sampled frames, to enhance motion and spatial perception. Furthermore, the model enhances abstraction by employing layer-stacking techniques in deep neural network features (from Residual Networks and Vision Transformers). Extensive testing on four UGC datasets confirms that ReLaX-VQA outperforms existing NR-VQA methods with an average SRCC value of 0.8658 and PLCC value of 0.8872. We will open source the code and trained models to facilitate further research and applications of NR-VQA: https://github.com/xinyiW915/ReLaX-VQA.

Towards Scale-Aware Full Surround Monodepth with Transformers

Full surround monodepth (FSM) methods can learn from multiple camera views simultaneously in a self-supervised manner to predict the scale-aware depth, which is more practical for real-world applications in contrast to scale-ambiguous depth from a standalone monocular camera. In this work, we focus on enhancing the scale-awareness of FSM methods for depth estimation. To this end, we propose to improve FSM from two perspectives: depth network structure optimization and training pipeline optimization. First, we construct a transformer-based depth network with neighbor-enhanced cross-view attention (NCA). The cross-attention modules can better aggregate the cross-view context in both global and neighboring views. Second, we formulate a transformer-based feature matching scheme with progressive training to improve the structure-from-motion (SfM) pipeline. That allows us to learn scale-awareness with sufficient matches and further facilitate network convergence by removing mismatches based on SfM loss. Experiments demonstrate that the resulting Scale-aware full surround monodepth (SA-FSM) method largely improves the scale-aware depth predictions without median-scaling at the test time, and performs favorably against the state-of-the-art FSM methods, e.g., surpassing SurroundDepth by 3.8% in terms of accuracy at delta<1.25 on the DDAD benchmark.

An Active Search Strategy with Multiple Unmanned Aerial Systems for Multiple Targets

The challenge of efficient target searching in vast natural environments has driven the need for advanced multi-UAV active search strategies. This paper introduces a novel method in which global and local information is adeptly merged to avoid issues such as myopia and redundant back-and-forth movements. In addition, a trajectory generation method is used to ensure the search pattern within continuous space. To further optimize multi-agent cooperation, the Voronoi partition technique is employed, ensuring a reduction in repetitive flight patterns and making the control of multiple agents in a decentralized way. Through a series of experiments, the evaluation and comparison results demonstrate the efficiency of our approach in various environments. The primary application of this innovative approach is demonstrated in the search for horseshoe crabs within their wild habitats, showcasing its potential to revolutionize ecological survey and conservation efforts.

DMS: Addressing Information Loss with More Steps for Pragmatic Adversarial Attacks

Despite the exceptional performance of deep neural networks (DNNs) across different domains, they are vulnerable to adversarial samples, in particular for tasks related to computer vision. Such vulnerability is further influenced by the digital container formats used in computers, where the discrete numerical values are commonly used for storing the pixel values. This paper examines how information loss in file formats impacts the effectiveness of adversarial attacks. Notably, we observe a pronounced hindrance to the adversarial attack performance due to the information loss of the non-integer pixel values. To address this issue, we explore to leverage the gradient information of the attack samples within the model to mitigate the information loss. We introduce the Do More Steps (DMS) algorithm, which hinges on two core techniques: gradient ascent-based \textit{adversarial integerization} (DMS-AI) and integrated gradients-based \textit{attribution selection} (DMS-AS). Our goal is to alleviate such lossy process to retain the attack performance when storing these adversarial samples digitally. In particular, DMS-AI integerizes the non-integer pixel values according to the gradient direction, and DMS-AS selects the non-integer pixels by comparing attribution results. We conduct thorough experiments to assess the effectiveness of our approach, including the implementations of the DMS-AI and DMS-AS on two large-scale datasets with various latest gradient-based attack methods. Our empirical findings conclusively demonstrate the superiority of our proposed DMS-AI and DMS-AS pixel integerization methods over the standardised methods, such as rounding, truncating and upper approaches, in maintaining attack integrity.

T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback

Diffusion-based text-to-video (T2V) models have achieved significant success but continue to be hampered by the slow sampling speed of their iterative sampling processes. To address the challenge, consistency models have been proposed to facilitate fast inference, albeit at the cost of sample quality. In this work, we aim to break the quality bottleneck of a video consistency model (VCM) to achieve $\textbf{both fast and high-quality video generation}$. We introduce T2V-Turbo, which integrates feedback from a mixture of differentiable reward models into the consistency distillation (CD) process of a pre-trained T2V model. Notably, we directly optimize rewards associated with single-step generations that arise naturally from computing the CD loss, effectively bypassing the memory constraints imposed by backpropagating gradients through an iterative sampling process. Remarkably, the 4-step generations from our T2V-Turbo achieve the highest total score on VBench, even surpassing Gen-2 and Pika. We further conduct human evaluations to corroborate the results, validating that the 4-step generations from our T2V-Turbo are preferred over the 50-step DDIM samples from their teacher models, representing more than a tenfold acceleration while improving video generation quality.

Revealing the Trade-off in ISAC Systems: The KL Divergence Perspective

Integrated sensing and communication (ISAC) is regarded as a promising technique for 6G communication network. In this letter, we investigate the Pareto bound of the ISAC system in terms of a unified Kullback-Leibler (KL) divergence performance metric. We firstly present the relationship between KL divergence and explicit ISAC performance metric, i.e., demodulation error and probability of detection. Thereafter, we investigate the impact of constellation and beamforming design on the Pareto bound via deep learning and semi-definite relaxation (SDR) techniques. Simulation results show the trade-off between sensing and communication performance in terms of bit error rate (BER) and probability of detection under different parameter set-ups.

STAR-RIS Aided Secure MIMO Communication Systems

This paper investigates simultaneous transmission and reflection reconfigurable intelligent surface (STAR-RIS) aided physical layer security (PLS) in multiple-input multiple-output (MIMO) systems, where the base station (BS) transmits secrecy information with the aid of STAR-RIS against multiple eavesdroppers equipped with multiple antennas. We aim to maximize the secrecy rate by jointly optimizing the active beamforming at the BS and passive beamforming at the STAR-RIS, subject to the hardware constraint for STAR-RIS. To handle the coupling variables, a minimum mean-square error (MMSE) based alternating optimization (AO) algorithm is applied. In particular, the amplitudes and phases of STAR-RIS are divided into two blocks to simplify the algorithm design. Besides, by applying the Majorization-Minimization (MM) method, we derive a closed-form expression of the STAR-RIS's phase shifts. Numerical results show that the proposed scheme significantly outperforms various benchmark schemes, especially as the number of STAR-RIS elements increases.

Grid Monitoring and Protection with Continuous Point-on-Wave Measurements and Generative AI

Purpose This article presents a case for a next-generation grid monitoring and control system, leveraging recent advances in generative artificial intelligence (AI), machine learning, and statistical inference. Advancing beyond earlier generations of wide-area monitoring systems built upon supervisory control and data acquisition (SCADA) and synchrophasor technologies, we argue for a monitoring and control framework based on the streaming of continuous point-on-wave (CPOW) measurements with AI-powered data compression and fault detection. Methods and Results: The architecture of the proposed design originates from the Wiener-Kallianpur innovation representation of a random process that transforms causally a stationary random process into an innovation sequence with independent and identically distributed random variables. This work presents a generative AI approach that (i) learns an innovation autoencoder that extracts innovation sequence from CPOW time series, (ii) compresses the CPOW streaming data with innovation autoencoder and subband coding, and (iii) detects unknown faults and novel trends via nonparametric sequential hypothesis testing. Conclusion: This work argues that conventional monitoring using SCADA and phasor measurement unit (PMU) technologies is ill-suited for a future grid with deep penetration of inverter-based renewable generations and distributed energy resources. A monitoring system based on CPOW data streaming and AI data analytics should be the basic building blocks for situational awareness of a highly dynamic future grid.