Generative model creates poisoning attacks against machine learning classifiers.
problem Poisoning attacks degrade machine learning classifier performance.
method Generative Adversarial Net with generator, discriminator, and classifier components.
result Effectively compromises machine learning classifiers, including deep networks.
BreachRadar detects points-of-compromise in bank transactions to prevent fraud.
problem Detecting and preventing bank transaction fraud caused by data breaches.
method A distributed alternating algorithm that assigns probabilities to different locations being compromised.
result BreachRadar achieves over 90% precision and recall in detecting compromised cards.
Adversarial training can lead to overfitting without compromising robustness.
problem Explaining benign overfitting in adversarially robust linear classification.
method Theoretical analysis and numerical experiments on adversarial training.
result Adversarially trained linear classifiers can achieve near-optimal risks despite overfitting noisy data.
One of the most prevalent symptoms among the elderly population, dementia, can be detected by classifiers trained on linguistic features extracted from narrative transcripts. However, these linguistic features are impacted in a similar but different fashion by the normal aging process. Aging is therefore a confounding …
Post-hoc explanations improve CNNs by replacing final linear layer with k-means classifier.
problem CNNs lack accurate data representation in their built-in prototypes.
method Introduces k-means-based post-hoc explanations for CNNs, leveraging spatial consistency of convolutional receptive fields.
result Using shallower, less compressed feature activations improves semantic fidelity at the cost of slight predictive performance.
Deep Learning algorithms have recently become the de-facto paradigm for various prediction problems, which include many privacy-preserving applications like online medical image analysis. Presumably, the privacy of data in a deep learning system is a serious concern. There have been several efforts to analyze and explo…
Adversarial noises are linearly separable for random neural networks.
problem The challenge of adversarial examples in neural networks.
method Theoretical proof and empirical evidence for two-layer networks with random initialization and neural tangent kernel setup.
result Adversarial noises are linearly separable with corresponding labels.
Gradient-based explanations correlate with Android malware classifier robustness.
problem Evasion attacks on Android malware classifiers using sparse perturbations.
method Investigated gradient-based attribution methods for explaining classifier decisions and their evenness, proposing metrics to assess adversarial robustness.
result Gradient-based explanations, especially Integrated Gradients, correlate with adversarial robustness of malware classifiers.
VACA models graph data for causal inference without hidden confounders.
problem Causal inference in observational data with hidden confounders.
method Variational graph autoencoders for structural causal models.
result Accurately approximates interventional and counterfactual distributions.
A smaller, less-trained model guides image generation, improving quality without sacrificing variation.
problem Improving image quality and variation in diffusion models without compromising one for the other.
method Guiding a conditional model with a smaller, less-trained version of the same model.
result Significant improvements in ImageNet generation, setting record FIDs.
Text-based analysis methods allow to reveal privacy relevant author attributes such as gender, age and identify of the text's author. Such methods can compromise the privacy of an anonymous author even when the author tries to remove privacy sensitive content. In this paper, we propose an automatic method, called Adver…
New attacks show ML models can be compromised even when targeting one concept.
problem Vulnerability of ML models to multi-concept attacks.
method Developed novel multi-concept attack techniques for deep learning.
result Successfully attacked one set of classifiers without impacting others.
In this article three models of firms interaction on the market are described. One of these models is described by using a differential equation and by Lotka-Volterra model, where the equation has a different form. Also, there are models of non-competing and competing firms. The article presents an algorithm for solvin…
Improves GANs by incorporating class information with a multi-hinge loss.
problem Improving GANs to better respect class information.
method Proposes a multi-class generalization of the Hinge loss for GANs.
result Improves Inception Scores and Frechet Inception Distance on Imagenet.
Background-Foreground classification is a well-studied problem in computer vision. Due to the pixel-wise nature of modeling and processing in the algorithm, it is usually difficult to satisfy real-time constraints. There is a trade-off between the speed (because of model complexity) and accuracy. Inspired by the reject…
Recent advances in deep learning have achieved impressive gains in classification accuracy on a variety of types of data, including images and text. Despite these gains, however, concerns have been raised about the calibration, robustness, and interpretability of these models. In this paper we propose a simple way to m…
The paper proposes reusable network components by making them compatible across tasks.
problem Training networks for different tasks independently leads to incompatible components.
method The paper splits a network into a features extractor and a target task head, and proposes various approaches to make them compatible.
result The proposed methods produce components that are directly compatible without compromising accuracy on original tasks.
Proposes R2LDA for improved LDA classifier performance.
problem Poor performance of LDA classifiers in small to comparable data sizes.
method Doubly regularized LDA with automatic parameter selection.
result Consistent and effective performance in noisy test data.
Fine-tuning neural networks to guarantee performance on specific examples can also introduce incorrect inputs.
problem Ensuring reliable performance of neural networks on specific examples.
method Using SMT solvers to fine-tune ReLU neural networks to guarantee outcomes on a finite set of particular examples.
result Fine-tuning can introduce incorrect inputs that trigger unexpected performance.
Adversarial attacks can manipulate deep trading policies, compromising their performance.
problem Adversarial attacks can compromise deep reinforcement learning trading policies.
method Developed a threat model and proposed two attack techniques.
result Demonstrated the effectiveness of adversarial attacks against DQN trading agents.
New method certifies individual fairness in representations.
problem Ensuring fairness in data representations without sacrificing utility.
method Mapping similar individuals to close latent representations to certify individual fairness.
result Certifies individual fairness for existing and new data points.
Proposes a sparse Naïve Bayes classifier to improve performance and interpretability.
problem Naïve Bayes assumes feature independence, which is violated in real data.
method Integrates feature correlation and performance measures for feature selection.
result Competitive results in accuracy, sparsity, and running times for balanced datasets.
Attack graphs provide compact representations of the attack paths that an attacker can follow to compromise network resources by analysing network vulnerabilities and topology. These representations are a powerful tool for security risk assessment. Bayesian inference on attack graphs enables the estimation of the risk …
Adversarial attacks hide cyber-physical attacks in ICS.
problem Hiding cyber-physical attacks in industrial control systems.
method Modeling an attacker compromising sensors, manipulating data, and evaluating attacks on both continuous and mixed data.
result Successfully hides cyber-physical attacks with 2.87 out of 12 sensors compromised on average.
Recent work on mode connectivity in the loss landscape of deep neural networks has demonstrated that the locus of (sub-)optimal weight vectors lies on continuous paths. In this work, we train a neural network that serves as a hypernetwork, mapping a latent vector into high-performance (low-loss) weight vectors, general…
Computer vision models are unstable due to task symmetries and labelling issues.
problem Instability of computer vision models in classification tasks.
method Analysis of symmetries, categorical nature, and labelling issues.
result Instability is a necessary result of current computer vision formulation.
A new method creates simpler, more interpretable decision trees from complex ensembles.
problem Complex tree ensembles reduce interpretability and control over machine learning models.
method Dynamic-programming based algorithm for finding a minimum-size decision tree.
result Optimal born-again trees are simpler and more interpretable than original ensembles.
PAIR optimizes machine learning models to generalize better to out-of-distribution data.
problem Optimization of machine learning models for out-of-distribution (OOD) generalization often leads to compromises that weaken robustness.
method Introduces a multi-objective optimization (MOO) perspective and a new optimization scheme called PAreto Invariant Risk Minimization (PAIR).
result PAIR improves robustness of OOD objectives by cooperatively optimizing with other objectives, yielding top OOD performances.
The paper proposes simple models for interpretable predictions while maintaining privacy.
problem Balancing interpretability and privacy in complex machine learning models.
method Locally linear maps per class to approximate complex models, ensuring differential privacy.
result High classification accuracy with differentially private explanations.
Machine learning has become an important component for many systems and applications including computer vision, spam filtering, malware and network intrusion detection, among others. Despite the capabilities of machine learning algorithms to extract valuable information from data and produce accurate predictions, it ha…
New methods improve anomaly detection with reduced false positives.
problem Effective anomaly detection with controlled error rates.
method Leave-one-out-, bootstrap-, and cross-conformal anomaly detection methods.
result Improved anomaly detection with reduced false positives.
BCDP enhances privacy by protecting sensitive features more precisely.
problem Uniform privacy protection in LDP degrades performance for sensitive features.
method Bayesian Coordinate Differential Privacy (BCDP) adjusts privacy protection per feature sensitivity.
result BCDP improves accuracy in downstream tasks without sacrificing privacy.
This paper tackles bias in federated learning without compromising data privacy.
problem Bias in federated learning models.
method Three pre-processing and in-processing methods to mitigate bias.
result Proposed methods are effective even with skewed data distributions or a small number of participating parties.
Paper examines adversarial attacks on event cause analysis in power grids.
problem Adversarial attacks manipulate data to mislead event classifiers.
method Investigated adversarial attacks on CNN-based event cause analysis.
result Demonstrated adversaries can misclassify events through stealthy data manipulations.
Clustering algorithms have become a popular tool in computer security to analyze the behavior of malware variants, identify novel malware families, and generate signatures for antivirus systems. However, the suitability of clustering algorithms for security-sensitive settings has been recently questioned by showing tha…
PINN-FEM combines PINNs and FEM for accurate Dirichlet boundary condition enforcement.
problem Challenges in enforcing Dirichlet boundary conditions in PINNs.
method Hybrid approach combining PINNs and FEM for strong boundary condition enforcement.
result PINN-FEM outperforms standard PINN models in accuracy and robustness.
We study investment strategy in different models of financial markets, where the investors cannot reach a perfect knowledge about available assets. The investor spends a certain effort to get information; this allows him to better choose the investment strategy, and puts a selective pressure upon assets. The best strat…
In this small article one compromise monetization strategy is proposed, which hopefully may lead to a more satisfactory coexistence of IP manufacturers and consumers. The motto is "fair exchange": you use our IP-product, we use your product (in form of money); when you do not need our product any more, we change back.
Noise analysis detects backdoors in DNNs quickly.
problem Detecting backdoors in DNNs trained on compromised data.
method Noise-infused image titration curves to quantify robustness and detect backdoors.
result DNNs with backdoors are more sensitive to noise and reveal their targets.
Model shows how advisors can manipulate naive investors.
problem How financial advisors manipulate naive investors.
method Agent-Based Model with Nash equilibria and best response functions.
result Greediness/naivety of investors emerge naturally from the model.
New method reduces discrete flow transitions, improving perplexity estimation.
problem Stochasticity in discrete paths makes rectification strategies ineffective.
method Dynamic-optimal-transport-like minimization objective with minibatch strategies.
result 32 times reduction in transitions for same perplexity.
iSTFTNet2 improves iSTFTNet's speed and lightness with 1D-2D CNN.
problem Efficiently synthesizing high-fidelity speech.
method Improved iSTFTNet using 1D-2D CNNs for temporal and spectrogram structures.
result iSTFTNet2 is faster and more lightweight with comparable speech quality.
New method controls bias in training data for fair outcomes.
problem Ensuring equal treatment between different groups in machine learning.
method Contrastive information estimation to control mutual information between representations and protected attributes.
result Our method provides strong theoretical guarantees on the parity of any downstream algorithm.
New algorithms optimize time series classification speed and accuracy.
problem Efficiently classify time series data quickly without sacrificing accuracy.
method Optimization criterion balancing misclassification and delay costs, derived non-myopic algorithms.
result Supervised-based algorithms outperform unsupervised-based ones in real data sets.
PT-WGAN reduces PET image noise without losing details.
problem Low-dose PET images suffer from noise and artifacts.
method Parameter-transferred Wasserstein GAN for denoising.
result PT-WGAN outperforms state-of-the-art methods in denoising.
L2F learns to forget, improving few-shot learning performance.
problem Few-shot learning challenges in adapting to unseen tasks.
method Task-and-layer-wise attenuation on compromised initialization to reduce prior knowledge influence.
result Faster adaptation and improved performance demonstrated experimentally.
Differentially private statistical inference using β-divergence.
problem Achieving differential privacy without altering data generation.
method Sampling from a generalised posterior minimizing β-divergence. result More precise inference with broader applicability.
SafeML monitors ML systems for safety and security risks.
problem Ensuring safety and explainability of ML systems in safety-critical domains.
method Statistical difference measures of ECDF to detect distributional shifts.
result Approach can detect invalid application contexts of ML components.