With more and more deep neural networks being deployed as various daily services, their reliability is essential. It is frightening that deep neural networks are vulnerable and sensitive to adversarial attacks, the most common one of which for the services is evasion-based. Recent works usually strengthen the robustness by adversarial training or leveraging the knowledge of an amount of clean data. However, retraining and redeploying the model need a large computational budget, leading to heavy losses to the online service. In addition, when training, it is likely that only limited adversarial examples are available for the service provider, while much clean data may not be accessible. Based on the analysis on the defense for deployed models, we find that how to rapidly defend against a certain attack for a frozen original service model with limitations of few clean and adversarial examples, which is named as RaPiD (Rapid Plug-in Defender), is really important. Motivated by the generalization and the universal computation ability of pre-trained transformer models, we come up with a new defender method, CeTaD, which stands for Considering Pretrained Transformers as Defenders. In particular, we evaluate the effectiveness and the transferability of CeTaD in the case of one-shot adversarial examples and explore the impact of different parts of CeTaD as well as training data conditions. CeTaD is flexible for different differentiable service models, and suitable for various types of attacks.
相關內容
Screening mammography is the most widely used method for early breast cancer detection, significantly reducing mortality rates. The integration of information from multi-view mammograms enhances radiologists' confidence and diminishes false-positive rates since they can examine on dual-view of the same breast to cross-reference the existence and location of the lesion. Inspired by this, we present TransReg, a Computer-Aided Detection (CAD) system designed to exploit the relationship between craniocaudal (CC), and mediolateral oblique (MLO) views. The system includes cross-transformer to model the relationship between the region of interest (RoIs) extracted by siamese Faster RCNN network for mass detection problems. Our work is the first time cross-transformer has been integrated into an object detection framework to model the relation between ipsilateral views. Our experimental evaluation on DDSM and VinDr-Mammo datasets shows that our TransReg, equipped with SwinT as a feature extractor achieves state-of-the-art performance. Specifically, at the false positive rate per image at 0.5, TransReg using SwinT gets a recall at 83.3% for DDSM dataset and 79.7% for VinDr-Mammo dataset. Furthermore, we conduct a comprehensive analysis to demonstrate that cross-transformer can function as an auto-registration module, aligning the masses in dual-view and utilizing this information to inform final predictions. It is a replication diagnostic workflow of expert radiologists
Modeling collective motion in multi-agent systems has gained much attention in recent years. In particular, of interest are the conditions under which flocking dynamics emerges. We present a generalization of the multi-agent model of Olfati--Saber with non-linear navigational feedback forces. As opposed to the original model, our model is, in general, not dissipative. This makes obtaining sufficient conditions for flocking challenging due to the absence of an obvious choice of a Lyapunov function. By means of an alternative argument, we show that our model possesses a global attractor when the navigational feedback forces are bounded perturbations of the linear ones. We further demonstrate that, under mild conditions, the dynamics of the group converges to a complete velocity agreement at an exponential rate. We show that the attractor of a dissipative system can contain non-equilibrium solutions. We construct explicit examples of such solutions and obtain conditions under which they cannot exist. In addition, we present a case study of the energy efficiency of our model. We show how non-linear navigational feedback forces, which possess flexibility that linear forces lack, can be used to reduce on-board energy consumption.
Despite known differences between reading and listening in the brain, recent work has shown that text-based language models predict both text-evoked and speech-evoked brain activity to an impressive degree. This poses the question of what types of information language models truly predict in the brain. We investigate this question via a direct approach, in which we eliminate information related to specific low-level stimulus features (textual, speech, and visual) in the language model representations, and observe how this intervention affects the alignment with fMRI brain recordings acquired while participants read versus listened to the same naturalistic stories. We further contrast our findings with speech-based language models, which would be expected to predict speech-evoked brain activity better, provided they model language processing in the brain well. Using our direct approach, we find that both text-based and speech-based language models align well with early sensory regions due to shared low-level features. Text-based models continue to align well with later language regions even after removing these features, while, surprisingly, speech-based models lose most of their alignment. These findings suggest that speech-based models can be further improved to better reflect brain-like language processing.
In recent years, the scientific community has become increasingly interested on peptides with non-canonical amino acids due to their superior stability and resistance to proteolytic degradation. These peptides present promising modifications to biological, pharmacological, and physiochemical attributes in both endogenous and engineered peptides. Notwithstanding their considerable advantages, the scientific community exhibits a conspicuous absence of an effective pre-trained model adept at distilling feature representations from such complex peptide sequences. We herein propose PepLand, a novel pre-training architecture for representation and property analysis of peptides spanning both canonical and non-canonical amino acids. In essence, PepLand leverages a comprehensive multi-view heterogeneous graph neural network tailored to unveil the subtle structural representations of peptides. Empirical validations underscore PepLand's effectiveness across an array of peptide property predictions, encompassing protein-protein interactions, permeability, solubility, and synthesizability. The rigorous evaluation confirms PepLand's unparalleled capability in capturing salient synthetic peptide features, thereby laying a robust foundation for transformative advances in peptide-centric research domains. We have made all the source code utilized in this study publicly accessible via GitHub at //github.com/zhangruochi/pepland
Accelerated life-tests (ALTs) are applied for inferring lifetime characteristics of highly reliable products. In particular, step-stress ALTs increase the stress level at which units under test are subject at certain pre-fixed times, thus accelerating product wear and inducing its failure. In some cases, due to cost or product nature constraints, continuous monitoring of devices is infeasible but the units are inspected for failures at particular inspection time points. In such setups, the ALT response is interval-censored. Furthermore, when a test unit fails, there are often more than one fatal cause for the failure, known as competing risks. In this paper, we assume that all competing risks are independent and follow an exponential distribution with scale parameter depending on the stress level. Under this setup, we present a family of robust estimators based on the density power divergence, including the classical maximum likelihood estimator as a particular case. We derive asymptotic and robustness properties of the MDPDE, showing its consistency for large samples. Based on these MDPDEs, estimates of the lifetime characteristics of the product as well as estimates of cause-specific lifetime characteristics have been developed. Direct, transformed and bootstrap confidence intervals for the mean lifetime to failure, reliability at a mission time, and distribution quantiles are proposed, and their performance is empirically compared through simulations. Besides, the performance of the MDPDE family has been examined through an extensive numerical study and the methods of inference discussed here are illustrated with a real-data example regarding electronic devices.
Numerous applications in the field of molecular communications (MC) such as healthcare systems are often event-driven. The conventional Shannon capacity may not be the appropriate metric for assessing performance in such cases. We propose the identification (ID) capacity as an alternative metric. Particularly, we consider randomized identification (RI) over the discrete-time Poisson channel (DTPC), which is typically used as a model for MC systems that utilize molecule-counting receivers. In the ID paradigm, the receiver's focus is not on decoding the message sent. However, he wants to determine whether a message of particular significance to him has been sent or not. In contrast to Shannon transmission codes, the size of ID codes for a Discrete Memoryless Channel (DMC) grows doubly exponentially fast with the blocklength, if randomized encoding is used. In this paper, we derive the capacity formula for RI over the DTPC subject to some peak and average power constraints. Furthermore, we analyze the case of state-dependent DTPC.
Many networks can be characterised by the presence of communities, which are groups of units that are closely linked and can be relevant in understanding the system's overall function. Recently, hypergraphs have emerged as a fundamental tool for modelling systems where interactions are not limited to pairs but may involve an arbitrary number of nodes. Using a dual approach to community detection, in this study we extend the concept of link communities to hypergraphs, allowing us to extract informative clusters of highly related hyperedges. We analyze the dendrograms obtained by applying hierarchical clustering to distance matrices among hyperedges on a variety of real-world data, showing that hyperlink communities naturally highlight the hierarchical and multiscale structure of higher-order networks. Moreover, by using hyperlink communities, we are able to extract overlapping memberships from nodes, overcoming limitations of traditional hard clustering methods. Finally, we introduce higher-order network cartography as a practical tool for categorizing nodes into different structural roles based on their interaction patterns and community participation. This approach helps identify different types of individuals in a variety of real-world social systems. Our work contributes to a better understanding of the structural organization of real-world higher-order systems.
Online learning holds the promise of enabling efficient long-term credit assignment in recurrent neural networks. However, current algorithms fall short of offline backpropagation by either not being scalable or failing to learn long-range dependencies. Here we present a high-performance online learning algorithm that merely doubles the memory and computational requirements of a single inference pass. We achieve this by leveraging independent recurrent modules in multi-layer networks, an architectural motif that has recently been shown to be particularly powerful. Experiments on synthetic memory problems and on the challenging long-range arena benchmark suite reveal that our algorithm performs competitively, establishing a new standard for what can be achieved through online learning. This ability to learn long-range dependencies offers a new perspective on learning in the brain and opens a promising avenue in neuromorphic computing.
The new era of technology has brought us to the point where it is convenient for people to share their opinions over an abundance of platforms. These platforms have a provision for the users to express themselves in multiple forms of representations, including text, images, videos, and audio. This, however, makes it difficult for users to obtain all the key information about a topic, making the task of automatic multi-modal summarization (MMS) essential. In this paper, we present a comprehensive survey of the existing research in the area of MMS.
Graph neural networks (GNNs) have been proven to be effective in various network-related tasks. Most existing GNNs usually exploit the low-frequency signals of node features, which gives rise to one fundamental question: is the low-frequency information all we need in the real world applications? In this paper, we first present an experimental investigation assessing the roles of low-frequency and high-frequency signals, where the results clearly show that exploring low-frequency signal only is distant from learning an effective node representation in different scenarios. How can we adaptively learn more information beyond low-frequency information in GNNs? A well-informed answer can help GNNs enhance the adaptability. We tackle this challenge and propose a novel Frequency Adaptation Graph Convolutional Networks (FAGCN) with a self-gating mechanism, which can adaptively integrate different signals in the process of message passing. For a deeper understanding, we theoretically analyze the roles of low-frequency signals and high-frequency signals on learning node representations, which further explains why FAGCN can perform well on different types of networks. Extensive experiments on six real-world networks validate that FAGCN not only alleviates the over-smoothing problem, but also has advantages over the state-of-the-arts.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191