Paper introduces DNTs to clone black-box models efficiently.
problem Cloning functionality of black-box models.
method Deep Neural Trees (DNTs) trained with active learning.
result Trained DNT can clone task-specific behavior of black-box models.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,181 papers · 148 categories
Trend · papers per month
48 results for “Black-box Architectures”
New method uses graph neural networks for neural architecture search.
problem Finding optimal neural architectures efficiently.
method Bayesian graph neural network for feature extraction and graph Bayesian optimization.
result Significantly outperforms existing methods in benchmark tasks.
VOPy optimizes multiple objectives with flexible cone-based ordering.
problem Optimizing multiple objectives with partial order constraints.
method Flexible cone-based ordering, modular architecture, integration of existing and novel methods.
result Advances black-box vector optimization in noisy, discrete, or limited budget settings.
LA-MCTS learns search space partition for black-box optimization using Monte Carlo Tree Search.
problem High-dimensional black-box optimization challenges.
method LA-MCTS recursively splits search space into regions with high/low function values, learns nonlinear partition and local models online.
result LA-MCTS achieves strong performance in black-box optimization and reinforcement learning benchmarks, especially for high-dimensional problems.
Paper presents strong black-box attacks on unsupervised clustering models.
problem Adversarial attacks on unsupervised machine learning models.
method Iterative black-box attack on clustering algorithms.
result Adversarial samples can fool clustering algorithms irrespective of the algorithm used.
This research exposes internal attributes of neural networks from queries, with implications for security and privacy.
problem Exposing internal attributes of black-box neural networks to protect against attacks and vulnerabilities.
method Exposing internal attributes of neural networks through a sequence of queries.
result Revealed internal attributes of neural networks can be used to generate more effective adversarial examples.
Black-box adversarial examples improve ASR system accuracy.
problem Improving ASR system accuracy through targeted adversarial examples.
method Combining genetic algorithms and gradient estimation for black-box attacks.
result Achieved 89.25% targeted attack similarity with 94.6% audio file similarity.
Stabilizing black-box algorithms through task-oriented randomization
problem Ensuring stability of black-box models
method Task-oriented randomization
result Established rigorous theoretical foundations and demonstrated effectiveness through simulations and real-world applications
Beyond Black-Box Predictions: Identifying Marginal Feature Effects in Tabular Transformer Networkscs.LG
Proposes a tabular transformer model to maintain feature effect intelligibility.
problem Losing marginal feature effects in deep tabular transformer networks.
method Adapts tabular transformer networks to identify marginal feature effects.
result The model accurately identifies marginal feature effects, matching black-box performance while maintaining intelligibility.
New method for black-box adversarial attacks using pretrained model embeddings.
problem Efficiently attacking unknown target networks with high-level semantic patterns.
method Learn a low-dimensional embedding using a pretrained model, then search within the embedding space.
result Significant reduction in the number of queries for black-box adversarial attacks.
Enhances adversarial examples for better transferability across models.
problem Adversarial examples often have limited black-box transferability.
method Fine-tunes existing adversarial examples by increasing perturbation on a pre-specified layer of the source model.
result Our method achieves greater black-box transferability of adversarial examples.
Paper offers local neural network explanations by considering model architecture.
problem Creating true neighbourhoods for black box models.
method Penultimate layer decoding for local neighbourhood generation.
result Local explanations are more accurate and relevant to instances.
Tree ensemble kernels for Bayesian optimization with known constraints over mixed-feature spacesstat.ML
Tree ensemble kernels improve Bayesian optimization for mixed features and constraints.
problem Optimizing over mixed-feature spaces with known constraints.
method Kernel interpretation of tree ensembles as Gaussian Process prior, compatible optimization formulation for acquisition function, integration of known constraints.
result Framework outperforms state-of-the-art methods for mixed-feature spaces and constraints.
Contrastive embeddings improve neural architecture search performance.
problem Improving performance of neural architecture search algorithms.
method Contrastive learning to identify networks based on data Jacobians and produce embeddings.
result Traditional black-box optimization algorithms can reach state-of-the-art performance with contrastive embeddings.
iNNvestigate simplifies neural network analysis.
problem Understanding and analyzing complex neural networks is difficult.
method Provides a common interface and implementation for analysis methods.
result Demonstrates versatility in analyzing various neural network architectures.
Recurrent neural networks (RNNs) are powerful and effective for processing sequential data. However, RNNs are usually considered "black box" models whose internal structure and learned parameters are not interpretable. In this paper, we propose an interpretable RNN based on the sequential iterative soft-thresholding al…
Efficiently explains model outputs using HSIC, a dependence measure.
problem Efficiently explain model outputs for various architectures.
method HSIC, RKHS, Reproducing Kernel Hilbert Spaces, black-box attribution.
result Up to 8 times faster than previous methods while maintaining fidelity.
A new method trains neural networks to sample from complex distributions.
problem Training neural networks to efficiently sample from complex target distributions.
method Amortized Stein Variational Gradient Descent (SVGD) to iteratively adjust network parameters.
result Our method effectively trains neural networks to sample from any target distribution.
BAR reprograms black-box ML models for transfer learning with scarce data.
problem Transfer learning with limited data and resources.
method Zeroth-order optimization and multi-label mapping techniques to reprogram black-box models.
result BAR outperforms state-of-the-art methods and baseline transfer learning approaches.
IANN visualizes all input variables effects simultaneously.
problem Inability to visualize all input variables effects simultaneously in black-box functions.
method Interpretable Architecture Neural Network (IANN) approach.
result Visualization of all input variables effects directly and simultaneously.
Enhances adversarial example transferability by fine-tuning existing examples.
problem Adversarial examples are often overfit to a source model, limiting black-box transferability.
method Intermediate Level Attack (ILA) fine-tunes adversarial examples on a pre-specified layer of the source model.
result ILAs achieve high transferability to target models without knowledge of their architecture.
Method makes non-interpretable models more intervenable.
problem Making non-interpretable models more understandable and controllable.
method Intervenability formalization and fine-tuning of black-box models.
result Fine-tuned black-box models are more intervenable and often better-calibrated.
Study examines adversarial robustness of ANN variants, revealing differences in black-box settings.
problem Adversarial robustness of alternative neural network architectures.
method Analysis of conventional, stochastic ANNs, and SNNs across three datasets; experiments in white-box and black-box settings.
result Stochastic ANNs are more robust than conventional ANNs in black-box settings, especially with surrogate attacks.
Efficient neural architecture search by sampling structure and operations.
problem Efficiently searching for optimal neural architectures.
method Decouples structure and operation search, using reinforcement learning with policy vectors.
result Significantly improved efficiency compared to traditional methods.
PRETZEL optimizes machine learning prediction serving systems for better performance.
problem Low latency, high throughput, and graceful performance degradation under heavy load in prediction serving systems.
method Introducing a novel white box architecture enabling both end-to-end and multi-model optimizations.
result Average 5.5x reduction in 99th percentile latency, 25x reduction in memory footprint, and 4.7x increase in throughput compared to state-of-the-art approaches.
Paper finds optimal membership inference strategies for machine learning models.
problem Determining if a sample was part of the training set of a machine learning model.
method Derives optimal strategies for membership inference with assumptions on parameter distribution, showing that black-box attacks are as good as white-box attacks.
result Optimal strategies are not tractable, leading to approximations that outperform existing methods.
DNAS disentangles neural architecture search for better interpretability and performance.
problem Lack of interpretability in existing neural architecture search methods.
method DNAS disentangles the hidden representation of the controller into semantically meaningful concepts.
result DNAS achieves state-of-the-art performance and competitive architectures.
Bayesian optimization improved for high-dimensional outputs using randomized priors.
problem Efficient global optimization of high-dimensional black-box functions.
method Deep learning framework with bootstrapped ensembles of neural architectures with randomized priors.
result Superior performance in tasks with high-dimensional outputs compared to state-of-the-art methods.
Orthogonal deep models defend against black-box attacks by ensuring internal representations are nearly orthogonal.
problem Vulnerability of deep learning models to black-box adversarial attacks.
method Introduce a gradient regularization scheme to encourage deep models' internal representations to be orthogonal to another model's.
result Orthogonal deep models significantly boost robustness against transferable black-box adversarial attacks.
New neural network designs learn contact dynamics efficiently.
problem Learning contact dynamics in robotics from noisy data.
method Physically structured neural networks.
result Data-efficient learning of discontinuous contact events.
Law explains how deep networks separate data for classification.
problem Black-box nature of deep learning limits architecture design and interpretation.
method Studied how deep neural networks process data in intermediate layers.
result Law of geometric data separation emerges in various architectures and datasets.
RAAL optimizes black box function optimization with multifidelity models.
problem Time-consuming and unfeasible black box optimization.
method Resource Aware Multifidelity Active Learning (RAAL) for efficient optimization.
result RAAL optimizes black box function optimization with multifidelity models.
BOAH optimizes expensive hyperparameter searches quickly.
problem Expensive hyperparameter optimization for neural networks.
method Multi-fidelity Bayesian optimization and HyperBand integration.
result Efficient optimization of complex design spaces.
Optimizes latent space of VAEs using decoder uncertainty to generate valid objects.
problem Lack of robustness in optimizing VAE latent space for black-box properties.
method Importance sampling-based estimator of decoder epistemic uncertainty to guide optimization.
result Improves trade-off between black-box objective and validity of generated samples.
This research secures deployed sentiment analysis models by identifying and defending against attack vectors.
problem Securing deployed machine learning models, particularly sentiment analysis systems, from adversarial attacks.
method BAD (Build, Attack, Defend) Architecture, evaluating two implementations.
result Demonstrated a viable methodology for securing machine learning models in production.
This research discovers model architecture and training dataset characteristics through strategic input probing.
problem Discovering model architecture and training dataset characteristics in black box models.
method Structured input probes and model outputs are used to train a deep classifier for image and text classification.
result The approach successfully distinguishes between different image and text datasets and architectures.
As machine learning algorithms are increasingly applied to high impact yet high risk tasks, such as medical diagnosis or autonomous driving, it is critical that researchers can explain how such algorithms arrived at their predictions. In recent years, a number of image saliency methods have been developed to summarize …
RobNets improve robustness of deep neural networks against adversarial attacks.
problem Vulnerability of deep neural networks to adversarial attacks.
method One-shot neural architecture search, finetuning sub-networks, and analyzing robustness indicators.
result RobNets achieve superior robustness performance across various datasets.
New method for interpreting complex ML models.
problem Interpreting complex black-box ML models.
method Functional decomposition of black-box predictions into simpler subfunctions.
result Main effects provide insights into feature contributions and interactions.
Operator learning approximates complex mappings for PDEs and experimental data.
problem Approximating mappings between infinite-dimensional function spaces for scientific computing.
method Formalizing operator learning as function-to-function regression and incorporating physical constraints.
result Development of rigorous uncertainty quantification frameworks for operator learning.
New method shows unfair explanations can be created for any classifier.
problem Fairness in black-box classifier explanations is not guaranteed.
method Constructs a new classifier with similar performance but altered explanations.
result Explanation methods can be manipulated to show unfair decisions.
Paper presents a method to disrupt deep uncertainty estimation without affecting accuracy.
problem Uncertainty estimation in deep neural networks for risk-sensitive applications.
method A novel attack that cripples uncertainty estimation without reducing accuracy.
result The attack causes the network to be more confident in incorrect predictions than correct ones.
Novel method prioritizes genetic variants in nonlinear models.
problem Variable selection in nonlinear and nonparametric regression.
method Developed RATE measure for summarizing variable importance.
result RATE explains improved predictive accuracy of nonlinear models.
Proposes a new MOBO framework for better estimation of uncertain parameters in expensive black-box functions.
problem Estimating the unknown utopia in multi-objective optimization problems with expensive black-box functions.
method Nested weighted Tchebycheff Multi-objective Bayesian Optimization (WTB-MOBO) with ensemble model selection.
result Improves MOBO performance by selecting the best model from an ensemble of predictive models.
A method interprets black-box models using an ensemble of gradient boosting machines.
problem Local and global interpretation of black-box models.
method An ensemble of gradient boosting machines (GBMs) to form a generalized additive model.
result Efficiency and properties demonstrated on synthetic and real datasets.
New method improves adversarial transferability from Bayesian neural networks.
problem Improving the effectiveness of black-box evasion attacks.
method Sampling from the posterior distribution of neural network weights to build a surrogate.
result Significantly improved success rates of state-of-the-art attacks (up to 83.2 percentage points).
New framework explains neural network behavior through geometric postulates.
problem Understanding neural network mechanisms and making them more transparent.
method Introducing the Pursuit of Subspaces (PoS) hypothesis as an axiomatic framework.
result Unified geometric perspective on neural network representation, computation, and generalization.
Theoretical study on how model architecture affects contrastive learning performance.
problem Understanding the role of model architecture in self-supervised learning.
method Theoretical analysis of contrastive learning, focusing on model capacity and clustering structures.
result Contrastive representations have lower dimensionality than the number of clusters in the data distribution.