This paper explores evasion attacks against Bayesian models.
problem Bayesian predictive models are vulnerable to evasion attacks.
method Developed gradient-based attacks for specific point predictions and entire posterior distributions.
result Optimal evasion attacks can be designed against Bayesian models.
Paper proposes a new method to attack Bayesian forecasting models.
problem Lack of research on adversarial attacks against time series forecasting systems.
method Decision analysis based attacking strategy for Bayesian forecasting models.
result Demonstrates the vulnerability of Bayesian forecasting models to adversarial attacks.
Attack graphs are a powerful tool for security risk assessment by analysing network vulnerabilities and the paths attackers can use to compromise network resources. The uncertainty about the attacker's behaviour makes Bayesian networks suitable to model attack graphs to perform static and dynamic analysis. Previous app…
Bayesian explanations are more resilient to adversarial attacks than deterministic ones.
problem Stability of saliency-based explanations under adversarial attacks in Neural Networks.
method Empirical and theoretical analysis of Bayesian vs deterministic Neural Networks.
result Bayesian explanations are more stable under adversarial perturbations and direct attacks.
We use Bayesian optimization to create efficient adversarial attacks with limited queries.
problem Creating adversarial examples with limited query access.
method Bayesian optimization for query-efficient adversarial attacks.
result Our method reduces query count by up to 80% compared to state-of-the-art methods.
Bayesian neural networks are vulnerable to adversarial attacks.
problem Adversarial robustness of Bayesian neural networks.
method Examination of adversarial robustness through three tasks: label prediction, adversarial example detection, and semantic shift detection.
result Bayesian neural networks are highly susceptible to adversarial attacks.
Bayesian Neural Networks are robust to gradient-based attacks in the large-data limit.
problem Vulnerability of deep learning models to adversarial attacks.
method Analysis of adversarial attacks in the large-data, overparametrized limit for Bayesian Neural Networks.
result BNN posteriors are robust to gradient-based adversarial attacks in the limit.
Bayesian framework robustifies classifiers against malicious attacks.
problem Adversarial attacks on classification algorithms in security and business.
method Adversarial risk analysis and approximate Bayesian computation.
result Robustifies statistical classification algorithms against attacks.
Bayesian Optimization improves machine learning for detecting network attacks.
problem Detecting network attacks to secure critical information.
method Bayesian Optimization for tuning machine learning algorithms (SVM-RBF, RF, k-NN).
result The proposed framework achieves high accuracy and low false alarms.
A recent paper by Liu et al. combines the topics of adversarial training and Bayesian Neural Networks (BNN) and suggests that adversarially trained BNNs are more robust against adversarial attacks than their non-Bayesian counterparts. Here, I analyze the proposed defense and suggest that one needs to adjust the adversa…
Bayesian adversaries can outsmart traditional adversarial attacks.
problem Bayesian adversaries can manipulate machine learning models through small perturbations.
method Developed a continuous-time particle system (Abram) to approximate the gradient flow of the Bayesian adversarial robustness problem.
result Abram approximates the minimizer of the Bayesian adversarial robustness problem under certain assumptions.
Bayesian optimisation method targets graph classification models against adversarial attacks.
problem Adversarial attacks on graph classification models, especially for graph-level tasks.
method Bayesian optimisation-based attack method for graph classification models.
result Effectiveness and flexibility of the proposed method validated on various graph classification tasks.
P-BO reduces black-box adversarial attacks by 10x with Bayesian optimization and function prior.
problem Efficiently generating adversarial examples against black-box models.
method Prior-guided Bayesian Optimization (P-BO) with a function prior initialized from a surrogate model.
result Significantly reduces the number of queries needed for adversarial attacks.
Bayesian models can be tricked into believing false data.
problem Vulnerability of Bayesian inference to data poisoning attacks.
method Developed attacks to manipulate Bayesian posterior through deletion and replication of data.
result Demonstrated that Bayesian inference can be steered to target distributions.
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 …
Bayesian method improves Federated Learning robustness against corrupted updates.
problem Adversarial attacks on Federated Learning models with unknown number of compromised clients.
method Adaptive Bayesian aggregation based on likelihood of clients being honest.
result Consistently achieves state-of-the-art performance across various attack types.
Efficient method for generating adversarial examples with limited query budget.
problem Developing black-box adversarial attacks with limited information.
method Bayesian Optimization in a structured low-dimensional subspace.
result Significantly higher attack success rate with fewer queries.
PAC-Bayesian bounds estimate adversarial robustness.
problem Estimating robustness to imperceptible input perturbations.
method PAC-Bayesian framework for averaging over hypotheses.
result General bounds valid for any type of adversarial attacks.
Paper assesses adversarial robustness of MCMC and BDK methods for deep Bayesian networks.
problem Assessing adversarial robustness of deep neural networks under MCMC and BDK approximations.
method Characterizes robustness of MCMC and BDK methods to FGSM and PGD attacks.
result Full MCMC-based inference shows excellent robustness, outperforming standard point estimation.
New MCMC method estimates differential privacy from multiple MIAs without worst-case assumptions.
problem Bayesian estimation of differential privacy from membership inference attacks.
method Bayesian estimation via MCMC algorithm (MCMC-DP-Est).
result More cautious privacy analysis with joint estimation of MIA strengths and privacy parameter.
Deep learning detects APT attacks with high accuracy and low false positives.
problem Detecting Advanced Persistent Threat (APT) attacks in network traffic.
method Used C5.0 decision tree, Bayesian network, and 6-layer deep neural network models on NSL-KDD dataset.
result Deep learning model achieved 98.85% accuracy and 1.13 false positive rate.
BOSH improves decision-based attacks by optimizing solution paths.
problem Generating optimal adversarial examples for decision-based attacks.
method BOSH-attack uses Bayesian Optimization and Successive Halving to explore solution paths.
result BOSH converges to better solutions with fewer queries.
A new adversarial attack method using structured search and contextual bandits.
problem Black-box adversarial attacks on deep learning models.
method Structured search space and Bayesian optimization for contextual bandits.
result Achieves state-of-the-art success rates and query efficiencies.
UAG defends GNNs against adversarial attacks by quantifying and explaining uncertainties.
problem Lack of uncertainty quantification in GNNs makes them vulnerable to adversarial attacks.
method UAG uses Bayesian Uncertainty Technique (BUT) and Uncertainty-aware Attention Technique (UAT).
result UAG outperforms state-of-the-art solutions in defending adversarial attacks on GNNs.
We present a new algorithm to train a robust neural network against adversarial attacks. Our algorithm is motivated by the following two ideas. First, although recent work has demonstrated that fusing randomness can improve the robustness of neural networks (Liu 2017), we noticed that adding noise blindly to all the la…
EI-MTD defends edge intelligence against adversarial attacks with dynamic scheduling.
problem Adversarial attacks on edge intelligence models.
method EI-MTD uses differential knowledge distillation to create robust member models and a dynamic scheduling policy based on a Bayesian Stackelberg game.
result EI-MTD effectively protects edge intelligence from black-box adversarial attacks.
Deep Learning models are vulnerable to adversarial examples, i.e.\ images obtained via deliberate imperceptible perturbations, such that the model misclassifies them with high confidence. However, class confidence by itself is an incomplete picture of uncertainty. We therefore use principled Bayesian methods to capture…
A Bayesian framework models adversarial uncertainty for robust machine learning.
problem Vulnerability of machine learning models to adversarial attacks.
method Formal Bayesian framework that models adversarial uncertainty through a stochastic channel, articulating probabilistic assumptions.
result Explicitly modeling adversarial uncertainty leads to improved robustification strategies.
Develops effective adversarial attacks on probabilistic forecasting models.
problem Adversarial attacks on neural models outputting probability distributions.
method Effective generation of adversarial attacks through Monte-Carlo estimation and Bayesian conditioning.
result Demonstrates successful generation of attacks with small input perturbations.
Paper detects adversarial speech inputs with high accuracy.
problem Adversarial attacks on ASR systems.
method Uncertainty quantification using neural networks.
result Detection accuracy of adversarial inputs over 0.99.
This research tackles backdoor attacks on audio data using a stochastic investment approach.
problem The threat of backdoor attacks on audio data, especially in voice-activated systems.
method A Stochastic investment-based backdoor attack (MarketBack) approach.
result MarketBack can achieve an average attack success rate close to 100% with less than 1% of poisoned data.
This paper optimizes power grid protection settings to maximize network degradation due to cascading attacks.
problem Cascading attacks on power grids and their undetected nature.
method Constrained Bayesian Optimization applied to transmission line protection settings.
result Even limited misconfiguration of protection settings can cause severe cascading attacks.
Detects poisoned training samples in deep neural networks.
problem Data poisoning attacks on deep neural networks.
method Two approaches: parametric probability distributions and Bayesian deep neural networks.
result Uncertainty estimates from trained models can discriminate clean from poisoned samples.
New attack targets speech-based AI models via stock market data.
problem Vulnerabilities in speech-based AI models using LLMs.
method Backdoor attack using acoustic data poisoning.
result Shows possible vulnerabilities in speech-based transformers.
Study shows prior Lipschitz continuity can improve adversarial robustness of Bayesian Neural Networks.
problem Improving adversarial robustness of Bayesian Neural Networks.
method Analysis of i.i.d., zero-mean Gaussian priors and posteriors approximated via mean-field variational inference.
result Adversarial robustness is sensitive to the prior variance.
Study probabilistic safety of BNNs under adversarial attacks.
problem Evaluate vulnerability of BNNs to adversarial attacks.
method Relaxation techniques from non-convex optimization to compute probabilistic safety bounds.
result Certify probabilistic safety of BNNs with millions of parameters.
Paper provides robustness bounds for GNNs against adversarial attacks.
problem Adversarial robustness of GNNs for graph-related tasks.
method PAC-Bayesian framework applied to GCN and MP-GNN.
result Spectral norms of diffusion matrix and weights govern robustness.
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).
Adaptive Bayesian method improves deep learning performance and robustness.
problem Ensuring sparsity in deep learning models to improve performance and robustness.
method Adaptive empirical Bayesian method with self-adaptive spike-and-slab priors and stochastic gradient MCMC optimization.
result The method achieves state-of-the-art performance on MNIST and Fashion MNIST and compression performance on CIFAR10.
Proposes DSM priors for Bayesian neural networks to improve interpretability and robustness.
problem Bayesian neural networks struggle with interpretability, overconfidence, and adversarial attacks.
method Introduces Dirichlet scale mixture (DSM) priors to address these issues.
result DSM priors lead to sparse networks, robustness against adversarial attacks, and competitive predictive performance.
Stochastic LWTA networks resist adversarial attacks while maintaining accuracy.
problem Adversarial robustness of neural networks.
method Replaced ReLU with stochastic LWTA activations, trained with Variational Bayesian and PGD.
result Stochastic LWTA networks achieve state-of-the-art robustness against adversarial attacks.
SGLD protects membership privacy in Bayesian deep learning.
problem Preventing membership attack in Bayesian deep learning.
method Theoretical framework based on information leakage analysis.
result SGLD prevents information leakage to a certain extent.
Researchers disrupt Gaussian model inference to test adversarial attacks.
problem Disrupting conditional inference in multivariate Gaussian models under adversarial conditions.
method Considered white- and grey-box settings with complete and incomplete knowledge of the Gaussian distribution, respectively. Reduced to quadratic and stochastic quadratic programs. Derived structural properties for solution methods.
result Demonstrated the impact and efficacy of attacks in various applications, including real estate evaluation, interest rate estimation, and signals processing.
Causal models offer stronger privacy guarantees and better generalization than associational models in machine learning.
problem Privacy attacks on machine learning models, especially membership inference attacks.
method Demonstrated the benefit of causal learning in machine learning models, showing better generalization and stronger privacy guarantees.
result Causal models provide stronger differential privacy guarantees and are more robust to membership inference attacks compared to associational models.
Bayesian neural networks integrate uncertainty into neural networks for improved performance.
problem Overconfidence, lack of interpretability, and adversarial attacks in neural networks.
method Integrates Bayesian inference into neural networks to address limitations.
result BNNs improve model performance and provide uncertainty estimates.
End-to-end autonomous driving models are vulnerable to simple physical manipulations of images.
problem Vulnerability of end-to-end autonomous driving models to subtle adversarial manipulations of images.
method Developed novel end-to-end attacks using simple physical manipulations (painting black lines on the road) and used Bayesian Optimization to efficiently search for successful attacks.
result Simple physical manipulations can cause autonomous driving models to follow unintended paths, highlighting the vulnerability of these models.
We study black-box attacks on machine learning classifiers where each query to the model incurs some cost or risk of detection to the adversary. We focus explicitly on minimizing the number of queries as a major objective. Specifically, we consider the problem of attacking machine learning classifiers subject to a budg…
Models leak information about their training data. This enables attackers to infer sensitive information about their training sets, notably determine if a data sample was part of the model's training set. The existing works empirically show the possibility of these membership inference (tracing) attacks against complex…