Paper proposes methods to reduce adversarial vulnerability in neural networks.
problem Adversarial vulnerability of deep neural networks in safety-critical applications.
method Defining vulnerability, proposing Vulnerability Suppression (VS) loss, and a Bayesian feature pruning method.
result Improves adversarial robustness and clean example performance with minimal parameter reduction.
New method makes neural networks more secure by protecting latent layers from adversarial attacks.
problem Vulnerability of latent layers in adversarially trained models to small perturbations.
method Latent Adversarial Training (LAT) and Latent Attack (LA) algorithms.
result Improves adversarial accuracy by 1-2% on MNIST, CIFAR-10, CIFAR-100 datasets.
A model disentangles features to detect adversarial inputs.
problem Detecting and defending against adversarial attacks on neural networks.
method Proposes a minimax game formulation using variational autoencoders to separate robust and vulnerable features.
result Adversarial inputs cannot bypass the detector without semantic change, indicating successful detection.
CAVs reveal latent concept distributions, but are vulnerable to adversarial attacks.
problem Understanding latent concept encodings in AI models.
method Probabilistic perspective on CAVs, deriving mean and covariance.
result CAVs can be adversarially manipulated, highlighting a vulnerability.
Study reveals how high-dimensional models are vulnerable to consistent adversarial attacks.
problem Understanding the vulnerability of high-dimensional linear classifiers to adversarial attacks.
method Introducing a new error metric to quantify model vulnerability, and rigorously characterizing these metrics in asymptotic settings.
result As models become more overparameterized, their vulnerability to label-preserving perturbations increases.
Despite achieving impressive performance, state-of-the-art classifiers remain highly vulnerable to small, imperceptible, adversarial perturbations. This vulnerability has proven empirically to be very intricate to address. In this paper, we study the phenomenon of adversarial perturbations under the assumption that the…
DefNet defends GNNs against adversarial attacks by identifying and mitigating vulnerabilities.
problem Vulnerability of GNNs to adversarial attacks.
method Investigates latent vulnerabilities in GNN layers, proposes dual-stage aggregation and bottleneck perceptron, and uses adversarial contrastive learning for training.
result DefNet significantly improves GNN robustness under various adversarial attacks.
Study shows how to manipulate VAEs for attacks and assess their robustness.
problem Adversarial attacks on Variational Autoencoders (VAE).
method Examine modifications to VAEs and propose metrics for robustness.
result Metrics to quantify the robustness of VAEs to adversarial attacks.
Defense against adversarial attacks by manipulating feature thickness.
problem Vulnerability of machine learning models to adversarial attacks.
method Feature Manipulation (FM)-Defense using a combo-variational autoencoder.
result Detection and purification of adversarial examples with high accuracy.
VAEs are vulnerable to adversarial attacks; new methods improve their robustness.
problem Vulnerability of VAEs to adversarial attacks.
method Introducing methods for producing adversarially robust VAEs, including disentangling latent representations and applying them to hierarchical VAEs.
result Hierarchical VAEs produce high-fidelity autoencoders that are also adversarially robust.
Deep Latent Defence combines adversarial training with a detection system to protect neural networks.
problem Vulnerability of neural networks to adversarial attacks, especially those that cause misclassification.
method Adversarial training combined with a k-NN classifier in a latent space. result Deep Latent Defence effectively detects and mitigates adversarial attacks, even under strong attack models.
Paper proposes structured semantic perturbations to improve adversarial attacks.
problem Vulnerability of deep neural networks to adversarial attacks.
method Manipulates semantic attributes via disentangled latent codes.
result Demonstrates the effectiveness of structured semantic perturbations.
The detection of software vulnerabilities (or vulnerabilities for short) is an important problem that has yet to be tackled, as manifested by the many vulnerabilities reported on a daily basis. This calls for machine learning methods for vulnerability detection. Deep learning is attractive for this purpose because it a…
Each year, thousands of software vulnerabilities are discovered and reported to the public. Unpatched known vulnerabilities are a significant security risk. It is imperative that software vendors quickly provide patches once vulnerabilities are known and users quickly install those patches as soon as they are available…
TaCo prevents non-linear classifiers from detecting sensitive attributes.
problem Ensuring fairness in NLP models by preventing sensitive attribute detection.
method Targeted Concept Erasure (TaCo) removes sensitive information from final latent representations, even against non-linear classifiers.
result TaCo outperforms state-of-the-art methods in reducing sensitive attribute prediction accuracy while preserving overall task performance.
Study shows unequal success of membership inference attacks across different groups.
problem Unequal success of membership inference attacks across different groups.
method Established conditions for preventing MIAs and derived connections to fairness and differential privacy.
result Estimating disparate vulnerability to MIAs can lead to overestimation; suitable attacks and statistical framework provided.
DCAE learns compact latent representations for one-class novelty detection.
problem Learning compact latent representations for one-class novelty detection.
method DCAE learns compact and collapse-free latent representations through internal discriminative layers of GANs, reconstructing in-class data finely and exclusively.
result DCAE achieves state-of-the-art performance on novelty and adversarial example detection.
New split rules improve subpopulation targeting in policy-making.
problem Improving binary classification for subpopulation targeting in policy-making.
method MDFS, PFS, wEFS for maximizing distance and penalizing final splits.
result Proposed methods target more vulnerable subpopulations than classic CART/KD-CART.
Capsule networks are vulnerable to adversarial attacks, similar to convolutional neural networks.
problem Vulnerability of capsule networks to adversarial attacks.
method Compared capsule networks to convolutional neural networks using various adversarial attacks.
result Capsule networks are vulnerable to adversarial attacks, similar to convolutional neural networks.
Predictive models can fail to generalize from training to deployment environments because of dataset shift, posing a threat to model reliability and the safety of downstream decisions made in practice. Instead of using samples from the target distribution to reactively correct dataset shift, we use graphical knowledge …
Increasing numbers of software vulnerabilities are discovered every year whether they are reported publicly or discovered internally in proprietary code. These vulnerabilities can pose serious risk of exploit and result in system compromise, information leaks, or denial of service. We leveraged the wealth of C and C++ …
Over the past few years, neural networks were proven vulnerable to adversarial images: targeted but imperceptible image perturbations lead to drastically different predictions. We show that adversarial vulnerability increases with the gradients of the training objective when viewed as a function of the inputs. Surprisi…
New risk measures assess cryptocurrency market vulnerabilities during financial distress.
problem Capturing systemic risk in cryptocurrency markets during financial distress.
method Introducing Vulnerability Conditional Risk Measures (VCoES) and related measures.
result Validated theoretical insights and demonstrated practical relevance in cryptocurrency market.
Model shows how financial contagion spreads through complex interdependencies.
problem Understanding how banks fail in an interconnected financial system.
method Unified model combining direct and indirect dependencies; three reconstruction methods.
result Hierarchical cascades reveal dominant banks in failures.
Hybrid model prices vulnerable options with stochastic volatility.
problem Pricing options with stochastic volatility and credit risk.
method Closed-form hybrid credit risk model with Heston-Nandi GARCH processes.
result Explicit pricing formula for vulnerable options.
Preschool attendance correlates with lower developmental vulnerabilities in Queensland, Australia.
problem Understanding the relationship between preschool attendance and developmental vulnerabilities in different regions.
method Data Analysis and Machine Learning to identify clusters of socio-demographic variables.
result Identified three clusters with varying socio-demographic variables affecting the relationship between preschool attendance and developmental vulnerabilities.
Study on measuring vulnerability of neural network parameters via corruption.
problem Understanding the robustness and generalization of deep neural networks.
method Proposes an indicator to measure parameter robustness via parameter corruption and provides a gradient-based estimation.
result Demonstrates the effectiveness of the proposed indicator and training method in improving parameter robustness and accuracy.
We explore methods of producing adversarial examples on deep generative models such as the variational autoencoder (VAE) and the VAE-GAN. Deep learning architectures are known to be vulnerable to adversarial examples, but previous work has focused on the application of adversarial examples to classification tasks. Deep…
HRFA generates high-resolution, realistic adversarial examples for DNNs.
problem Revealing vulnerabilities of DNNs with imperceptible, semantic attacks.
method Modifies latent feature representation, backpropagating through generative model.
result Generates adversarial examples with up to 1024x1024 resolution, evading denoising defenses.
Thousands of security vulnerabilities are discovered in production software each year, either reported publicly to the Common Vulnerabilities and Exposures database or discovered internally in proprietary code. Vulnerabilities often manifest themselves in subtle ways that are not obvious to code reviewers or the develo…
We are concerned with the vulnerability of computer vision models to distributional shifts. We formulate a combinatorial optimization problem that allows evaluating the regions in the image space where a given model is more vulnerable, in terms of image transformations applied to the input, and face it with standard se…
Batch normalization makes neural networks more vulnerable to small adversarial perturbations.
problem Adversarial vulnerability of neural networks trained with batch normalization.
method Investigated the impact of batch normalization on adversarial robustness and compared it to weight decay.
result Substituting weight decay for batch norm nullifies adversarial vulnerability.
The paper analyzes how much data points can be altered to change their rank in nearest neighbor searches.
problem Vulnerability of nearest neighbor search in high-dimensional data.
method Statistical analysis of perturbation needed to change neighbor rank.
result Derived statistical distribution of perturbation needed to modify neighbor rank.
Paper bypasses backdoor detection algorithms in deep learning models.
problem Adversaries can embed backdoors in deep learning models, making them behave differently on specific inputs.
method Adversarial training algorithm that optimizes original loss function and maximizes hidden representation indistinguishability.
result The paper presents an adversarial backdoor embedding algorithm that can bypass existing detection algorithms.
Using a suitable change of probability measure, we obtain a novel Poisson series representation for the arbitrage- free price process of vulnerable contingent claims in a regime-switching market driven by an underlying continuous- time Markov process. As a result of this representation, along with a short-time asymptot…
Devign uses graph neural networks to identify vulnerabilities efficiently.
problem Challenging and tedious process of identifying vulnerabilities in software systems.
method Devign employs a graph neural network to classify graph-level vulnerabilities using comprehensive code semantic representations.
result Devign significantly outperforms state-of-the-art models in vulnerability identification.
New method certifies joint adversarial robustness of model ensembles.
problem Ensuring robustness of model ensembles against adversarial attacks.
method Proposes a novel technique to certify joint robustness, building on prior work on single-model robustness certification.
result Demonstrates the effectiveness of certifying joint robustness of ensembles, improving understanding of ensemble defenses.
Language model benchmarks often misrepresent true understanding, revealing vulnerabilities in evaluation methods.
problem Language model benchmarks fail to accurately reflect true language understanding and adaptability.
method Systematic analysis of NLP evaluation frameworks, identifying vulnerabilities in static benchmarks, human evaluation protocols, and LLM-as-judge frameworks.
result Current evaluation methods are unreliable and need improvement to accurately assess LLM performance.
DVERGE diversifies adversarial vulnerabilities to enhance robust ensemble models.
problem Diverse adversarial vulnerabilities for robust ensemble models.
method Isolates and diversifies adversarial vulnerabilities through distillation and training.
result Achieves higher robustness against transfer attacks compared to previous methods.
Paper examines vulnerabilities in data-driven pricing schemes.
problem Vulnerability of clustering-oriented pricing schemes to malicious user behavior.
method Defined a notion of disguising to identify strategic behaviors of malicious users, characterized sensitivity zones to evaluate malicious user percentages, conducted cost benefit analysis.
result Concluded with a vulnerability analysis of data-driven pricing schemes.
Adversarial objects can fool LiDAR-based autonomous driving systems.
problem Vulnerability of LiDAR-based autonomous driving systems to adversarial attacks.
method Optimization-based approach LiDAR-Adv to generate adversarial objects.
result LiDAR-based autonomous driving systems are vulnerable to adversarial attacks.
New method defends RL agents from poisoning attacks without MDP knowledge.
problem Poisoning attacks on RL systems can cause learning failures.
method Generic poisoning framework for online RL, Vulnerability-Aware Adversarial Critic Poison (VA2C-P).
result Successfully prevents RL agents from learning good policies or converging to target policies.
Motivated by the problem of automated repair of software vulnerabilities, we propose an adversarial learning approach that maps from one discrete source domain to another target domain without requiring paired labeled examples or source and target domains to be bijections. We demonstrate that the proposed adversarial l…
Improved security of smart contracts by classifying them into four categories.
problem Detecting and classifying vulnerabilities in smart contracts efficiently.
method Used AWD-LSTM for multi-class classification, addressing class imbalance.
result Achieved a weighted average Fbeta score of 90.0%.
Designing models that are robust to small adversarial perturbations of their inputs has proven remarkably difficult. In this work we show that the reverse problem---making models more vulnerable---is surprisingly easy. After presenting some proofs of concept on MNIST, we introduce a generic tilting attack that injects …
Study reveals how neural network smoothness affects their vulnerability to adversarial attacks.
problem Understanding adversarial vulnerability in deep learning networks.
method Analysis of manifold smoothness and generalization capability of deep neural networks trained with local errors.
result High generalization accuracy requires a fast power-law decay of eigen-spectrum of hidden representations.
The success of modern Artificial Intelligence (AI) technologies depends critically on the ability to learn non-linear functional dependencies from large, high dimensional data sets. Despite recent high-profile successes, empirical evidence indicates that the high predictive performance is often paired with low robustne…
Boosting algorithms predict financial vulnerability of farmers in Chile and Tunisia.
problem Predict financial vulnerability of farmers in Chile and Tunisia using environmental data.
method Interpretable boosting algorithms based on ridge-regularized generalized linear models.
result Interaction effects improve predictive power only when included in two-step boosting.