NP-Attack reduces query counts for black-box adversarial attacks.
problem Efficiency of black-box adversarial attacks is low.
method Uses Neural Process to characterize image structure and find adversarial examples.
result NP-Attack significantly decreases query counts.
Deep neural networks work well at approximating complicated functions when provided with data and trained by gradient descent methods. At the same time, there is a vast amount of existing functions that programmatically solve different tasks in a precise manner eliminating the need for training. In many cases, it is po…
Many deployed learned models are black boxes: given input, returns output. Internal information about the model, such as the architecture, optimisation procedure, or training data, is not disclosed explicitly as it might contain proprietary information or make the system more vulnerable. This work shows that such attri…
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.
We address a non-unique parameter fitting problem in the context of material science. In particular, we propose to resolve ambiguities in parameter space by augmenting a black-box artificial neural network (ANN) model with two different levels of expert knowledge and benchmark them against a pure black-box model.
Neural networks play an increasingly important role in the field of machine learning and are included in many applications in society. Unfortunately, neural networks suffer from adversarial samples generated to attack them. However, most of the generation approaches either assume that the attacker has full knowledge of…
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.
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.
Develops significance tests for neural networks without strong assumptions or excessive computation.
problem Addressing the black-box nature of deep neural networks for feature relevance testing.
method Derives one-split and two-split tests relaxing assumptions and computational complexity.
result Establishes asymptotic null distributions and consistency in Type II error.
Understanding how a learned black box works is of crucial interest for the future of Machine Learning. In this paper, we pioneer the question of the global interpretability of learned black box models that assign numerical values to symbolic sequential data. To tackle that task, we propose a spectral algorithm for the …
Paper proposes ZO-NGD for more efficient black-box attacks.
problem Vulnerability of state-of-the-art DNNs to adversarial attacks.
method Zeroth-order natural gradient descent (ZO-NGD) for black-box attacks.
result ZO-NGD achieves significantly lower model query complexities.
Develops black-box methods to estimate parameters of complex models.
problem Lack of efficient methods to produce simulations for complex statistical models.
method Pre-training deep neural networks on extensive simulated databases for well-structured likelihoods. Iterative algorithm for other complex dependencies.
result Successfully estimates and quantifies uncertainty of parameters from non-Gaussian models.
Adversarial examples pose a threat to deep neural network models in a variety of scenarios, from settings where the adversary has complete knowledge of the model and to the opposite "black box" setting. Black box attacks are particularly threatening as the adversary only needs access to the input and output of the mode…
New algorithm explains neural network extrema for better model generalization.
problem Understanding and improving neural network generalization.
method Dynamic extremum mapping and solving linear equations.
result Number of extrema correlates with model parameters, and new algorithm simplifies gradient issues.
This paper proposes a novel PGO framework to optimize systemic risk bailouts using neural networks.
problem Optimal bailout strategies for mitigating systemic risk in financial systems.
method Prediction-Gradient-Optimization (PGO) framework, using neural networks to approximate and forecast the objective function.
result The PGO framework effectively manages systemic risk through online optimization.
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.
IReEn reveals functionality of black-box agents via iterative neural synthesis.
problem Revealing the functionality of a black-box agent without privileged information.
method Iterative refinement of candidate programs using neural program synthesis.
result The approach finds a functional equivalent program in 78% of cases, outperforming state-of-the-art.
Pixle attacks images by rearranging pixels, bypassing neural networks.
problem Vulnerability of neural networks to black-box adversarial attacks.
method A novel attack that rearranges a small number of pixels in images.
result Successfully attacks a high percentage of samples on various datasets and models.
We interpret black box predictive models using causal attribution.
problem Interpreting models trained using machine learning in high-stakes applications.
method Estimate causal effects of model inputs on output using observational data.
result Effective interpretation of black box predictive models via causal attribution.
Recent studies have shown that adversarial examples in state-of-the-art image classifiers trained by deep neural networks (DNN) can be easily generated when the target model is transparent to an attacker, known as the white-box setting. However, when attacking a deployed machine learning service, one can only acquire t…
Paper proposes a new black-box adversarial attack using normalizing flows.
problem Adversarial vulnerability of deep neural networks.
method Proposes a novel black-box adversarial attack using normalizing flows.
result Demonstrates competitive performance against well-known black-box adversarial attack methods.
REST improves robustness of black-box models to geometric transformations.
problem Overconfident incorrect predictions on out-of-distribution samples.
method REinforcement Spatial Transform learner (REST) that transforms input data into in-distribution samples.
result Improves robustness to geometric transformations and sample efficiency.
AdvMind detects adversary intent in black-box attacks with high accuracy.
problem Detecting adversary intent in black-box adversarial attacks is challenging.
method AdvMind accounts for adversary adaptiveness and synthesizes queries to expose intent.
result AdvMind detects adversary intent with over 75% accuracy after observing less than 3 query batches.
Gradient rollback explains neural models by identifying influential training examples.
problem Explain predictions of neural black-box models, especially in applications requiring user trust.
method Gradient rollback, a general approach for influence estimation applicable to neural models with limited parameter updates.
result Gradient rollback provides faithful explanations for neural models, including knowledge graph embedding methods.
AxNN improves model interpretability without sacrificing predictive power.
problem Black-box nature of machine learning models hinders interpretation and explanation.
method AxNN combines ensembles of generalized additive model networks and additive index models.
result AxNN achieves both good predictive performance and model interpretability.
GACEM optimizes complex multi-modal problems using neural networks.
problem Black-box optimization and constraint satisfaction in multi-modal environments.
method Modified Cross-Entropy Method with masked auto-regressive neural network.
result GACEM outperforms traditional CEM in diverse solutions, mode discovery, and sample efficiency.
Recent works have demonstrated that machine learning models are vulnerable to model inversion attacks, which lead to the exposure of sensitive information contained in their training dataset. While some model inversion attacks have been developed in the past in the black-box attack setting, in which the adversary does …
Develops transparent global models consistent with local explanations.
problem Creating globally interpretable models that align with local explanations from black-box models.
method Custom boolean features from sparse local contrastive explanations are used to train a globally transparent model.
result Custom transparent models have higher local consistency compared to other strategies.
MPHD transfers knowledge across different domains for Bayesian optimization.
problem Optimizing functions with unknown or diverse domains.
method MPHD uses neural nets to map domain-specific contexts to GP specifications, enabling transfer learning across heterogeneous search spaces.
result MPHD improves black-box function optimization performance on diverse domains.
New black-box attack method improves GNN defense without needing training data.
problem Vulnerability of Graph Neural Networks to adversarial attacks.
method Developed a gradient-based black-box attack algorithm, BBGA, which does not require access to training data.
result BBGA achieves stable attack performance without accessing training sets, and is effective against various defenses.
New methods improve Bayesian inference for complex economic models.
problem Difficulty in parameter estimation for simulation models, especially in economics.
method Neural network-based black-box approximate Bayesian inference methods.
result Neural network methods provide state-of-the-art parameter inference for economic simulation models.
Current neural network-based classifiers are susceptible to adversarial examples even in the black-box setting, where the attacker only has query access to the model. In practice, the threat model for real-world systems is often more restrictive than the typical black-box model where the adversary can observe the full …
Hybrid neural network infers states from black-box systems.
problem Inference of state models in black-box systems without source code instrumentation.
method Convolutional and recurrent layers learn correlations between time series signals.
result Improves state change point detection by up to 102%.
Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models. Adversarial examples often exhibit black-box transfer, meaning that adversarial examples for one model can fool another model. However, adversarial examples may be overfit to exploit the particular architecture and …
Proposes a Bayesian approach to explain, justify, and quantify uncertainty in DNNs.
problem Lack of transparency and confidence in DNNs for critical applications.
method Bayesian approach to extract explanations, justifications, and uncertainty estimates from black box DNNs.
result Improves interpretability and reliability of DNNs, validated on CIFAR-10.
New framework for variational coresets simplifies Bayesian inference for complex models.
problem Efficient Bayesian inference for complex models like neural networks.
method Black-box variational inference for coresets that handle intractable posterior distributions.
result Principled application of variational coresets to Bayesian neural networks.
Paper proposes a black-box technique to generate adversarial samples.
problem Robustness of Deep Neural Networks (DNNs) to adversarial samples.
method Black-box Momentum Iterative Fast Gradient Sign Method (BMI-FGSM) using Differential Evolution to approximate gradients.
result Achieves high success rates in generating adversarial samples and misclassification.
Paper proposes B3D method for black-box backdoor detection.
problem Detecting backdoor attacks in black-box models without access to training data.
method Gradient-free optimization to reverse-engineer triggers, simple strategy for reliable predictions.
result Effectiveness of B3D method corroborated on hundreds of DNN models.
Note that this paper is superceded by "Black-Box Adversarial Attacks with Limited Queries and Information." Current neural network-based image classifiers are susceptible to adversarial examples, even in the black-box setting, where the attacker is limited to query access without access to gradients. Previous methods -…
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.
We derive a novel sensitivity analysis of input variables for predictive epistemic and aleatoric uncertainty. We use Bayesian neural networks with latent variables as a model class and illustrate the usefulness of our sensitivity analysis on real-world datasets. Our method increases the interpretability of complex blac…
DAEGEN generates adversarial inputs for neural networks using a black-box differential technique.
problem Generating adversarial inputs that highlight differences between neural network models.
method DAEGEN uses a local search-based optimization algorithm to find difference-inducing adversarial examples (DIAEs).
result DAEGEN is the first black-box differential technique for adversarial input generation and performs well compared to existing methods.
Deep neural networks (DNNs) are one of the most prominent technologies of our time, as they achieve state-of-the-art performance in many machine learning tasks, including but not limited to image classification, text mining, and speech processing. However, recent research on DNNs has indicated ever-increasing concern o…
Neural programming involves training neural networks to learn programs, mathematics, or logic from data. Previous works have failed to achieve good generalization performance, especially on problems and programs with high complexity or on large domains. This is because they mostly rely either on black-box function eval…
Recently, neural networks trained as optimizers under the "learning to learn" or meta-learning framework have been shown to be effective for a broad range of optimization tasks including derivative-free black-box function optimization. Recurrent neural networks (RNNs) trained to optimize a diverse set of synthetic non-…
Analyzing large-scale, multi-experiment studies requires scientists to test each experimental outcome for statistical significance and then assess the results as a whole. We present Black Box FDR (BB-FDR), an empirical-Bayes method for analyzing multi-experiment studies when many covariates are gathered per experiment.…
Novel framework for Bayesian neural networks incorporating task-specific constraints.
problem Task-specific constraints in supervised model deployment.
method Introduces Output-Constrained BNN (OC-BNN) framework.
result OC-BNNs effectively incorporate prior expert knowledge and desiderata like safety and fairness.
Obtaining the state of the art performance of deep learning models imposes a high cost to model generators, due to the tedious data preparation and the substantial processing requirements. To protect the model from unauthorized re-distribution, watermarking approaches have been introduced in the past couple of years. W…