This paper addresses the tradeoff between standard accuracy on clean examples and robustness against adversarial examples in deep neural networks (DNNs). Although adversarial training (AT) improves robustness, it degrades the standard accuracy, thus yielding the tradeoff. To mitigate this tradeoff, we propose a novel AT method called ARREST, which comprises three components: (i) adversarial finetuning (AFT), (ii) representation-guided knowledge distillation (RGKD), and (iii) noisy replay (NR). AFT trains a DNN on adversarial examples by initializing its parameters with a DNN that is standardly pretrained on clean examples. RGKD and NR respectively entail a regularization term and an algorithm to preserve latent representations of clean examples during AFT. RGKD penalizes the distance between the representations of the standardly pretrained and AFT DNNs. NR switches input adversarial examples to nonadversarial ones when the representation changes significantly during AFT. By combining these components, ARREST achieves both high standard accuracy and robustness. Experimental results demonstrate that ARREST mitigates the tradeoff more effectively than previous AT-based methods do.
相關內容
This paper investigates risk bounds for quantile additive trend filtering, a method gaining increasing significance in the realms of additive trend filtering and quantile regression. We investigate the constrained version of quantile trend filtering within additive models, considering both fixed and growing input dimensions. In the fixed dimension case, we discover an error rate that mirrors the non-quantile minimax rate for additive trend filtering, featuring the main term $n^{-2r/(2r+1)}V^{2/(2r+1)}$, when the underlying quantile function is additive, with components whose $(r-1)$th derivatives are of bounded variation by $V$. In scenarios with a growing input dimension $d$, quantile additive trend filtering introduces a polynomial factor of $d^{(2r+2)/(2r+1)}$. This aligns with the non-quantile variant, featuring a linear factor $d$, particularly pronounced for larger $r$ values. Additionally, we propose a practical algorithm for implementing quantile trend filtering within additive models, using dimension-wise backfitting. We conduct experiments with evenly spaced data points or data that samples from a uniform distribution in the interval $[0,1]$, applying distinct component functions and introducing noise from normal and heavy-tailed distributions. Our findings confirm the estimator's convergence as $n$ increases and its superiority, particularly in heavy-tailed distribution scenarios. These results deepen our understanding of additive trend filtering models in quantile settings, offering valuable insights for practical applications and future research.
Sharding is essential for improving blockchain scalability. Existing protocols overlook diverse adversarial attacks, limiting transaction throughput. This paper presents Reticulum, a groundbreaking sharding protocol addressing this issue, boosting blockchain scalability. Reticulum employs a two-phase approach, adapting transaction throughput based on runtime adversarial attacks. It comprises "control" and "process" shards in two layers. Process shards contain at least one trustworthy node, while control shards have a majority of trusted nodes. In the first phase, transactions are written to blocks and voted on by nodes in process shards. Unanimously accepted blocks are confirmed. In the second phase, blocks without unanimous acceptance are voted on by control shards. Blocks are accepted if the majority votes in favor, eliminating first-phase opponents and silent voters. Reticulum uses unanimous voting in the first phase, involving fewer nodes, enabling more parallel process shards. Control shards finalize decisions and resolve disputes. Experiments confirm Reticulum's innovative design, providing high transaction throughput and robustness against various network attacks, outperforming existing sharding protocols for blockchain networks.
This paper presents a new method for combining (or aggregating or ensembling) multivariate probabilistic forecasts, considering dependencies between quantiles and marginals through a smoothing procedure that allows for online learning. We discuss two smoothing methods: dimensionality reduction using Basis matrices and penalized smoothing. The new online learning algorithm generalizes the standard CRPS learning framework into multivariate dimensions. It is based on Bernstein Online Aggregation (BOA) and yields optimal asymptotic learning properties. The procedure uses horizontal aggregation, i.e., aggregation across quantiles. We provide an in-depth discussion on possible extensions of the algorithm and several nested cases related to the existing literature on online forecast combination. We apply the proposed methodology to forecasting day-ahead electricity prices, which are 24-dimensional distributional forecasts. The proposed method yields significant improvements over uniform combination in terms of continuous ranked probability score (CRPS). We discuss the temporal evolution of the weights and hyperparameters and present the results of reduced versions of the preferred model. A fast C++ implementation of the proposed algorithm will be made available in connection with this paper as an open-source R-Package on CRAN.
Gaussian mixtures are widely used for approximating density functions in various applications such as density estimation, belief propagation, and Bayesian filtering. These applications often utilize Gaussian mixtures as initial approximations that are updated recursively. A key challenge in these recursive processes stems from the exponential increase in the mixture's order, resulting in intractable inference. To overcome the difficulty, the Gaussian mixture reduction (GMR), which approximates a high order Gaussian mixture by one with a lower order, can be used. Although existing clustering-based methods are known for their satisfactory performance and computational efficiency, their convergence properties and optimal targets remain unknown. In this paper, we propose a novel optimization-based GMR method based on composite transportation divergence (CTD). We develop a majorization-minimization algorithm for computing the reduced mixture and establish its theoretical convergence under general conditions. Furthermore, we demonstrate that many existing clustering-based methods are special cases of ours, effectively bridging the gap between optimization-based and clustering-based techniques. Our unified framework empowers users to select the most appropriate cost function in CTD to achieve superior performance in their specific applications. Through extensive empirical experiments, we demonstrate the efficiency and effectiveness of our proposed method, showcasing its potential in various domains.
Model selection in supervised learning provides costless guarantees as if the model that best balances bias and variance was known a priori. We study the feasibility of similar guarantees for cumulative regret minimization in the stochastic contextual bandit setting. Recent work [Marinov and Zimmert, 2021] identifies instances where no algorithm can guarantee costless regret bounds. Nevertheless, we identify benign conditions where costless model selection is feasible: gradually increasing class complexity, and diminishing marginal returns for best-in-class policy value with increasing class complexity. Our algorithm is based on a novel misspecification test, and our analysis demonstrates the benefits of using model selection for reward estimation. Unlike prior work on model selection in contextual bandits, our algorithm carefully adapts to the evolving bias-variance trade-off as more data is collected. In particular, our algorithm and analysis go beyond adapting to the complexity of the simplest realizable class and instead adapt to the complexity of the simplest class whose estimation variance dominates the bias. For short horizons, this provides improved regret guarantees that depend on the complexity of simpler classes.
This paper considers the problem of recovering signals modeled by generative models from linear measurements contaminated with sparse outliers. We propose an outlier detection approach for reconstructing the ground-truth signals modeled by generative models under sparse outliers. We establish theoretical recovery guarantees for reconstruction of signals using generative models in the presence of outliers, giving lower bounds on the number of correctable outliers. Our results are applicable to both linear generator neural networks and the nonlinear generator neural networks with an arbitrary number of layers. We propose an iterative alternating direction method of multipliers (ADMM) algorithm for solving the outlier detection problem via $\ell_1$ norm minimization, and a gradient descent algorithm for solving the outlier detection problem via squared $\ell_1$ norm minimization. We conduct extensive experiments using variational auto-encoder and deep convolutional generative adversarial networks, and the experimental results show that the signals can be successfully reconstructed under outliers using our approach. Our approach outperforms the traditional Lasso and $\ell_2$ minimization approach.
In the era of digital markets, the challenge for consumers is discerning quality amidst information asymmetry. While traditional markets use brand mechanisms to address this issue, transferring such systems to internet-based P2P markets, where misleading practices like fake ratings are rampant, remains challenging. Current internet platforms strive to counter this through verification algorithms, but these efforts find themselves in a continuous tug-of-war with counterfeit actions. Exploiting the transparency, immutability, and traceability of blockchain technology, this paper introduces a robust reputation voting system grounded in it. Unlike existing blockchain-based reputation systems, our model harnesses an intrinsically economically incentivized approach to bolster agent integrity. We optimize this model to mirror real-world user behavior, preserving the reputation system's foundational sustainability. Through Monte-Carlo simulations, using both uniform and power-law distributions enabled by an innovative inverse transform method, we traverse a broad parameter landscape, replicating real-world complexity. The findings underscore the promise of a sustainable, transparent, and formidable reputation mechanism. Given its structure, our framework can potentially function as a universal, sustainable oracle for offchain-onchain bridging, aiding entities in perpetually cultivating their reputation. Future integration with technologies like Ring Signature and Zero Knowledge Proof could amplify the system's privacy facets, rendering it particularly influential in the ever-evolving digital domain.
The collection and curation of high-quality training data is crucial for developing text classification models with superior performance, but it is often associated with significant costs and time investment. Researchers have recently explored using large language models (LLMs) to generate synthetic datasets as an alternative approach. However, the effectiveness of the LLM-generated synthetic data in supporting model training is inconsistent across different classification tasks. To better understand factors that moderate the effectiveness of the LLM-generated synthetic data, in this study, we look into how the performance of models trained on these synthetic data may vary with the subjectivity of classification. Our results indicate that subjectivity, at both the task level and instance level, is negatively associated with the performance of the model trained on synthetic data. We conclude by discussing the implications of our work on the potential and limitations of leveraging LLM for synthetic data generation.
This paper proposes an online target speaker voice activity detection system for speaker diarization tasks, which does not require a priori knowledge from the clustering-based diarization system to obtain the target speaker embeddings. By adapting the conventional target speaker voice activity detection for real-time operation, this framework can identify speaker activities using self-generated embeddings, resulting in consistent performance without permutation inconsistencies in the inference phase. During the inference process, we employ a front-end model to extract the frame-level speaker embeddings for each coming block of a signal. Next, we predict the detection state of each speaker based on these frame-level speaker embeddings and the previously estimated target speaker embedding. Then, the target speaker embeddings are updated by aggregating these frame-level speaker embeddings according to the predictions in the current block. Our model predicts the results for each block and updates the target speakers' embeddings until reaching the end of the signal. Experimental results show that the proposed method outperforms the offline clustering-based diarization system on the DIHARD III and AliMeeting datasets. The proposed method is further extended to multi-channel data, which achieves similar performance with the state-of-the-art offline diarization systems.
Face recognition technology has advanced significantly in recent years due largely to the availability of large and increasingly complex training datasets for use in deep learning models. These datasets, however, typically comprise images scraped from news sites or social media platforms and, therefore, have limited utility in more advanced security, forensics, and military applications. These applications require lower resolution, longer ranges, and elevated viewpoints. To meet these critical needs, we collected and curated the first and second subsets of a large multi-modal biometric dataset designed for use in the research and development (R&D) of biometric recognition technologies under extremely challenging conditions. Thus far, the dataset includes more than 350,000 still images and over 1,300 hours of video footage of approximately 1,000 subjects. To collect this data, we used Nikon DSLR cameras, a variety of commercial surveillance cameras, specialized long-rage R&D cameras, and Group 1 and Group 2 UAV platforms. The goal is to support the development of algorithms capable of accurately recognizing people at ranges up to 1,000 m and from high angles of elevation. These advances will include improvements to the state of the art in face recognition and will support new research in the area of whole-body recognition using methods based on gait and anthropometry. This paper describes methods used to collect and curate the dataset, and the dataset's characteristics at the current stage.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191