Matrix minimization techniques that employ the nuclear norm have gained recognition for their applicability in tasks like image inpainting, clustering, classification, and reconstruction. However, they come with inher...
详细信息
Matrix minimization techniques that employ the nuclear norm have gained recognition for their applicability in tasks like image inpainting, clustering, classification, and reconstruction. However, they come with inherent biases and computational burdens, especially when used to relax the rank function, making them less effective and efficient in real-world scenarios. To address these challenges, our research focuses on generalized nonconvex rank regularization problems in robust matrix completion, low-rank representation, and robust matrix regression. We introduce innovative approaches for effective and efficient low-rank matrix learning, grounded in generalized nonconvex rank relaxations inspired by various substitutes for the ?0-norm relaxed functions. These relaxations allow us to more accurately capture low-rank structures. Our optimization strategy employs a nonconvex and multi-variable alternating direction method of multipliers, backed by rigorous theoretical analysis for complexity and *** algorithm iteratively updates blocks of variables, ensuring efficient convergence. Additionally, we incorporate the randomized singular value decomposition technique and/or other acceleration strategies to enhance the computational efficiency of our approach, particularly for large-scale constrained minimization problems. In conclusion, our experimental results across a variety of image vision-related application tasks unequivocally demonstrate the superiority of our proposed methodologies in terms of both efficacy and efficiency when compared to most other related learning methods.
Co-saliency detection within a single image is a common vision problem that has not yet been well addressed. Existing methods often used a bottom-up strategy to infer co-saliency in an image in which salient regions a...
详细信息
Co-saliency detection within a single image is a common vision problem that has not yet been well addressed. Existing methods often used a bottom-up strategy to infer co-saliency in an image in which salient regions are firstly detected using visual primitives such as color and shape and then grouped and merged into a co-saliency map. However, co-saliency is intrinsically perceived complexly with bottom-up and top-down strategies combined in human vision. To address this problem, this study proposes a novel end-toend trainable network comprising a backbone net and two branch nets. The backbone net uses ground-truth masks as top-down guidance for saliency prediction, whereas the two branch nets construct triplet proposals for regional feature mapping and clustering, which drives the network to be bottom-up sensitive to co-salient regions. We construct a new dataset of 2019 natural images with co-saliency in each image to evaluate the proposed method. Experimental results show that the proposed method achieves state-of-the-art accuracy with a running speed of 28 fps.
Over-the-air computation(AirComp)enables federated learning(FL)to rapidly aggregate local models at the central server using waveform superposition property of wireless *** this paper,a robust transmission scheme for ...
详细信息
Over-the-air computation(AirComp)enables federated learning(FL)to rapidly aggregate local models at the central server using waveform superposition property of wireless *** this paper,a robust transmission scheme for an AirCompbased FL system with imperfect channel state information(CSI)is *** model CSI uncertainty,an expectation-based error model is *** main objective is to maximize the number of selected devices that meet mean-squared error(MSE)requirements for model broadcast and model *** problem is formulated as a combinatorial optimization problem and is solved in two ***,the priority order of devices is determined by a sparsity-inducing ***,a feasibility detection scheme is used to select the maximum number of devices to guarantee that the MSE requirements are *** alternating optimization(AO)scheme is used to transform the resulting nonconvex problem into two convex *** results illustrate the effectiveness and robustness of the proposed scheme.
Anomaly detection(AD) has been extensively studied and applied across various scenarios in recent years. However, gaps remain between the current performance and the desired recognition accuracy required for practical...
详细信息
Anomaly detection(AD) has been extensively studied and applied across various scenarios in recent years. However, gaps remain between the current performance and the desired recognition accuracy required for practical *** paper analyzes two fundamental failure cases in the baseline AD model and identifies key reasons that limit the recognition accuracy of existing approaches. Specifically, by Case-1, we found that the main reason detrimental to current AD methods is that the inputs to the recovery model contain a large number of detailed features to be recovered, which leads to the normal/abnormal area has not/has been recovered into its original state. By Case-2, we surprisingly found that the abnormal area that cannot be recognized in image-level representations can be easily recognized in the feature-level representation. Based on the above observations, we propose a novel recover-then-discriminate(ReDi) framework for *** takes a self-generated feature map(e.g., histogram of oriented gradients) and a selected prompted image as explicit input information to address the identified in Case-1. Additionally, a feature-level discriminative network is introduced to amplify abnormal differences between the recovered and input representations. Extensive experiments on two widely used yet challenging AD datasets demonstrate that ReDi achieves state-of-the-art recognition accuracy.
Backdoor attacks pose great threats to deep neural network models. All existing backdoor attacks are designed for unstructured data(image, voice, and text), but not structured tabular data, which has wide real-world a...
详细信息
Backdoor attacks pose great threats to deep neural network models. All existing backdoor attacks are designed for unstructured data(image, voice, and text), but not structured tabular data, which has wide real-world applications, e.g., recommendation systems, fraud detection, and click-through rate prediction. To bridge this research gap, we make the first attempt to design a backdoor attack framework, named BAD-FM, for tabular data prediction models. Unlike images or voice samples composed of homogeneous pixels or signals with continuous values, tabular data samples contain well-defined heterogeneous fields that are usually sparse and discrete. Tabular data prediction models do not solely rely on deep networks but combine shallow components(e.g., factorization machine, FM) with deep components to capture sophisticated feature interactions among fields. To tailor the backdoor attack framework to tabular data models, we carefully design field selection and trigger formation algorithms to intensify the influence of the trigger on the backdoored model. We evaluate BAD-FM with extensive experiments on four datasets, i.e.,HUAWEI, Criteo, Avazu, and KDD. The results show that BAD-FM can achieve an attack success rate as high as 100%at a poisoning ratio of 0.001%, outperforming baselines adapted from existing backdoor attacks against unstructured data models. As tabular data prediction models are widely adopted in finance and commerce, our work may raise alarms on the potential risks of these models and spur future research on defenses.
As the adoption of explainable AI(XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention...
详细信息
As the adoption of explainable AI(XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention on privacy-preserving model explanations. This article presents the first thorough survey about privacy attacks on model explanations and their countermeasures. Our contribution to this field comprises a thorough analysis of research papers with a connected taxonomy that facilitates the categorization of privacy attacks and countermeasures based on the targeted explanations. This work also includes an initial investigation into the causes of privacy leaks. Finally, we discuss unresolved issues and prospective research directions uncovered in our analysis. This survey aims to be a valuable resource for the research community and offers clear insights for those new to this domain. To support ongoing research, we have established an online resource repository, which will be continuously updated with new and relevant findings.
With the rise of artificial intelligence and cloud computing, machine-learning-as-a-service platforms,such as Google, Amazon, and IBM, have emerged to provide sophisticated tasks for cloud applications. These propriet...
详细信息
With the rise of artificial intelligence and cloud computing, machine-learning-as-a-service platforms,such as Google, Amazon, and IBM, have emerged to provide sophisticated tasks for cloud applications. These proprietary models are vulnerable to model extraction attacks due to their commercial value. In this paper, we propose a time-efficient model extraction attack framework called Swift Theft that aims to steal the functionality of cloud-based deep neural network models. We distinguish Swift Theft from the existing works with a novel distribution estimation algorithm and reference model settings, finding the most informative query samples without querying the victim model. The selected query samples can be applied to various cloud models with a one-time selection. We evaluate our proposed method through extensive experiments on three victim models and six datasets, with up to 16 models for each dataset. Compared to the existing attacks, Swift Theft increases agreement(i.e., similarity) by 8% while consuming 98% less selecting time.
The authors consider the property of detectability of discrete event systems in the presence of sensor attacks in the context of *** authors model the system using an automaton and study the general notion of detectab...
详细信息
The authors consider the property of detectability of discrete event systems in the presence of sensor attacks in the context of *** authors model the system using an automaton and study the general notion of detectability where a given set of state pairs needs to be(eventually or periodically)distinguished in any estimate of the state of the *** authors adopt the ALTER sensor attack model from previous work and formulate four notions of CA-detectability in the context of this attack model based on the following attributes:strong or weak;eventual or *** authors present verification methods for strong CA-detectability and weak *** authors present definitions of strong and weak periodic CA-detectability that are based on the construction of a verifier automaton called the augmented *** development also resulted in relaxing assumptions in prior results on D-detectability,which is a special case of CA-detectability.
This study investigates a safe reinforcement learning algorithm for grid-forming(GFM)inverter based frequency *** guarantee the stability of the inverter-based resource(IBR)system under the learned control policy,a mo...
详细信息
This study investigates a safe reinforcement learning algorithm for grid-forming(GFM)inverter based frequency *** guarantee the stability of the inverter-based resource(IBR)system under the learned control policy,a modelbased reinforcement learning(MBRL)algorithm is combined with Lyapunov approach,which determines the safe region of states and *** obtain near optimal control policy,the control performance is safely improved by approximate dynamic programming(ADP)using data sampled from the region of attraction(ROA).Moreover,to enhance the control robustness against parameter uncertainty in the inverter,a Gaussian process(GP)model is adopted by the proposed algorithm to effectively learn system dynamics from *** simulations validate the effectiveness of the proposed algorithm.
Large language models (LLMs) have recently shown remarkable performance in a variety of natural language processing (NLP) *** further explore LLMs'reasoning abilities in solving complex problems,recent research [1...
Large language models (LLMs) have recently shown remarkable performance in a variety of natural language processing (NLP) *** further explore LLMs'reasoning abilities in solving complex problems,recent research [1-3]has investigated chain-of-thought (CoT) reasoning in complex multimodal scenarios,such as science question answering (scienceQA) tasks [4],by fine-tuning multimodal models through human-annotated CoT ***,collected CoT rationales often miss the necessary rea-soning steps and specific expertise.
暂无评论