Universal adversarial patches prevent face detection in various frameworks.
problem Preventing face detection in state-of-the-art face detection systems.
method Investigated the phenomenon of patches that suppress face detection and proposed optimization-based approaches for automatic design.
result Universal adversarial patches can prevent face detection without introducing false positives.
New method generates unrestricted adversarial face images to bypass robust face recognition systems.
problem Vulnerability of face recognition systems to unrestricted adversarial examples.
method Image translation techniques to generate large perturbations in face images.
result Achieved high attack success rates (90% and 80%) under white- and black-box settings. New method generates fast adversarial faces with high success rate.
problem Vulnerability of face recognition systems to adversarial attacks.
method Fast landmark manipulation method and semantic structure constrained attack.
result 99.86% success rate on state-of-the-art face recognition models.
OGAN attacks autoencoders to prevent deepfake creation.
problem Preventing deepfake creation using adversarial attacks.
method Training-resistant adversarial attack on face-swapping autoencoders.
result OGAN attacks are training-resistant and transfer across different models and faces.
Paper proposes a method to encrypt faces while maintaining visual similarity.
problem Protecting personal data from unauthorized face recognition.
method Targeted identity-protection iterative method (TIP-IM) to generate adversarial identity masks.
result TIP-IM provides 95%+ protection success rate against face recognition models.
Paper proposes a framework to protect user anonymity in emotion recognition.
problem Preserving user anonymity in face-based emotion recognition systems.
method Adversarial learning framework using CNN architecture.
result The proposed approach minimizes identity-specific information and maximizes emotion-dependent information.
Neural networks can predict BMI from faces, and can be fooled into wrong predictions.
problem Vulnerability of BMI prediction models to adversarial attacks.
method Test-time adversarial attacks on neural networks trained to infer BMI from facial images.
result Neural networks can be tricked into predicting incorrect BMI values, posing a risk of insurance fraud.
Novel technique detects adversarial samples in face recognition models.
problem Widespread adversarial sample attacks on DNN models.
method Bi-directional correspondence inference between attributes and internal neurons to identify critical neurons.
result 94% detection accuracy for 7 different kinds of attacks with 9.91% false positives.
Reduces gender classification bias by learning race-invariant face representations.
problem Societal bias in gender recognition systems.
method Adversarially trained autoencoder model to learn race-invariant face representations.
result Achieved a significant drop of over 40% in racial bias surrogate metric with race invariant representations.
We present a data-driven framework called generative adversarial privacy (GAP). Inspired by recent advancements in generative adversarial networks (GANs), GAP allows the data holder to learn the privatization mechanism directly from the data. Under GAP, finding the optimal privacy mechanism is formulated as a constrain…
New algorithm disentangles latent space in GANs using video sequences.
problem Learning disentangled latent spaces in GANs without supervision.
method Adversarial training with video sequences, modifying standard GAN algorithm.
result Disentangled latent space into content and motion attributes.
GANs improve anomaly detection accuracy.
problem Detecting unseen anomalies is challenging.
method Adversarial training of GANs.
result Remarkable results on anomaly detection.
Advbox generates adversarial examples to test neural network robustness.
problem Vulnerability of neural networks to adversarial examples.
method Tool to create adversarial examples in multiple frameworks.
result Benchmarking robustness of machine learning models.
New method closes certification gap for adversarially trained models.
problem Certifying robustness of adversarially trained neural networks.
method Nonconvex low-rank SDP relaxation with polynomial-time optimization.
result Strong certifications comparable to SDP methods, but with fewer variables.
GANs can bias synthetic data, affecting minority and female faces.
problem GANs can amplify biases in synthetic data augmentation.
method Examine GANs on face-shots with gender and skin tone biases.
result GANs generate biased synthetic data, skewing minority modes and features.
A new generator for GANs separates style and variation.
problem Improving GANs' ability to control and disentangle image attributes.
method Borrowing from style transfer, a new generator architecture.
result Improves GANs' quality and disentanglement of latent factors.
Contrastive examples improve fairness in face recognition by balancing minority and majority groups.
problem Face recognition algorithms favor majority groups in training data.
method Create contrastive examples by swapping group memberships in the training dataset.
result Contrastive examples improve fairness metrics like equalized odds.
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.
Paper discusses imperceptible attacks on tabular data models.
problem Security of machine learning models on tabular data.
method Formalizes imperceptibility of adversarial attacks, proposes an approach to generate imperceptible adversarial examples.
result Demonstrates ability to generate imperceptible adversarial examples with high fooling rate.
Proposes a new GAN architecture for generating data conditioned on partial information.
problem Generating data conditioned on partial ancillary information.
method Introduces a new Adversarial Network architecture and training strategy.
result The proposed method outperforms standard Conditional GANs in generating data under partial conditioning.
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.
Paper proposes using synthetic data to improve face recognition accuracy.
problem Improving face recognition accuracy using real data alone.
method Proposes a GAN that disentangles identity attributes and generates photo-realistic synthetic images.
result Synthetic images generated by the model are photo-realistic and can increase face recognition accuracy.
Bayesian optimization generates personalized face stimuli for cognitive neuroscience.
problem Lack of personalized face stimuli in cognitive neuroscience studies.
method Combines GANs with Bayesian optimization to identify individual response patterns to faces.
result Algorithm efficiently generates optimal faces maximizing individual subject's response.
DefenseVGAE defends graph neural networks against adversarial attacks.
problem Vulnerability of GNNs to adversarial structural perturbations.
method Variational Graph Autoencoder (VGAE) to reconstruct graph structure.
result DefenseVGAE reduces adversarial perturbations and boosts GCN performance.
This paper examines various definitions of adversarial risk and their implications.
problem Quantifying the performance of classifiers under adversarial perturbations.
method Optimal transport, robust statistics, functional analysis, and game theory.
result Generalization of Strassen's theorem and new connections to Choquet capacities and game theory.
CAN learns conditional and interventional distributions from unlabeled data.
problem Learning conditional and interventional distributions from unlabeled data.
method CAN framework with LGN and CIGN architectures, equipped with an intervention mechanism.
result CAN generates both interventional and conditional samples without needing the causal graph.
Generates realistic faces from detailed textual descriptions.
problem Face generation from fine-grained textual descriptions.
method Conditional GAN model with DC-GAN and GAN-CLS loss, using CelebA dataset with generated captions.
result Promising results in generating diverse face images from fine-grained textual descriptions.
We present an unsupervised approach for learning to estimate three dimensional (3D) facial structure from a single image while also predicting 3D viewpoint transformations that match a desired pose and facial geometry. We achieve this by inferring the depth of facial keypoints of an input image in an unsupervised manne…
AdjointDEIS simplifies diffusion model optimization.
problem Optimizing diffusion models with respect to a differentiable metric.
method Novel bespoke ODE solvers for continuous adjoint equations.
result Continuous adjoint equations simplify to a simple ODE, improving efficiency.
This paper surveys adversarial machine learning focusing on deep learning.
problem How adversarial attacks can cause deep learning models to make mistakes.
method Comprehensive review of adversarial attacks and defenses in deep learning.
result Adversarial attacks can lead to significant errors in deep learning models.
Here, we present a novel approach to solve the problem of reconstructing perceived stimuli from brain responses by combining probabilistic inference with deep learning. Our approach first inverts the linear transformation from latent features to brain responses with maximum a posteriori estimation and then inverts the …
Advances citation and subject label recommendation using multi-modal adversarial autoencoders.
problem Improving recommendation systems for citations and subject labels.
method Multi-modal adversarial autoencoders with adversarial regularization, sparsity, and input modality analysis.
result Adversarial regularization consistently improves recommendation performance.
Traditional classification algorithms assume that training and test data come from similar distributions. This assumption is violated in adversarial settings, where malicious actors modify instances to evade detection. A number of custom methods have been developed for both adversarial evasion attacks and robust learni…
SAIL improves AIL by weighting adversarial rewards with support estimation.
problem Training instability and reward bias in AIL.
method Support-weighted Adversarial Imitation Learning (SAIL) extends AIL with support estimation to improve reinforcement signals.
result SAIL achieves better performance and stability on benchmark tasks.
Paper shows simple losses are effective at image reconstruction and detects overfitting in deep generators.
problem Detecting overfitting in deep generative networks, especially GANs.
method Simple losses for image reconstruction, analysis of reconstruction errors, comparison of GAN models.
result Overfitting is not detectable in pure GAN models but is in hybrid adversarial models.
Proposes AEGAN for stable GAN training.
problem Training instability in GANs.
method Four-network model with adversarial and reconstruction losses.
result Stabilizes GAN training and prevents mode-collapse.
Proposes SWA for adversarial training to improve model robustness.
problem Overfitting in adversarial training due to insufficient sample complexity.
method Adversarial training with Stochastic Weight Average (SWA).
result Improves model robustness on CIFAR-10, CIFAR-100, and SVHN datasets.
TAnoGan detects anomalies in time series data using GANs.
problem Anomaly detection in time series data.
method Generative Adversarial Networks (GAN) for unsupervised anomaly detection.
result TAnoGan outperforms traditional and neural network models in anomaly detection.
New method defends against both single-step and iterative adversarial examples.
problem Defending against adversarial examples, especially iterative ones, is computationally expensive.
method Single-Step Adversarial Training (SST) with modifications.
result Our method outperforms state-of-the-art methods in both accuracy and training time.
This paper studies adversarial examples in NIDS, revealing their vulnerability.
problem Vulnerability of machine learning-based NIDS to adversarial examples.
method Used evolutionary computation and deep learning to generate adversarial examples.
result Adversarial examples cause high misclassification rates in various machine learning models.
Surveying strategies for making machine learning models robust against adversarial attacks.
problem Ensuring machine learning models are robust and reliable in real-world applications.
method Taxonomy of adversarial attacks and defenses, Robust Optimization problem formulation, and survey of methods.
result Surveyed recent results in adversarial example generation, defense mechanisms, and formal robustness certificates.
Monotone adversarial corruptions degrade optimal learning algorithms.
problem Optimal learning algorithms' reliance on exchangeability and independence is challenged.
method Introduces a monotone adversarial corruption model where an adversary adds monotone corruptions to a clean dataset.
result Optimal learning algorithms achieve suboptimal expected error on new test points.
Face recognition models can be inferred from student models, posing privacy risks.
problem Privacy threats in transfer learning models for face recognition.
method Membership inference attacks and attribute inference from aggregate-level information.
result Sensitive attributes can be inferred from student models, even with limited auxiliary information.
Defense strategy improves controller robustness against adversarial attacks.
problem Adversarial attacks on learning-enabled controllers in CPS.
method Two-stage defense strategy treating controller and environment as black-boxes with unknown dynamics.
result Defense strategy effectively improves controller robustness in realistic control domains.
Paper defends iris recognition from adversarial examples using wavelet decomposition.
problem Adversarial examples threaten deep neural networks in biometric applications.
method Wavelet domain denoising of input examples to detect and mitigate adversarial attacks.
result Proposed defense strategies improve recognition accuracy against adversarial attacks.
Though Convolutional Neural Networks (CNNs) have surpassed human-level performance on tasks such as object classification and face verification, they can easily be fooled by adversarial attacks. These attacks add a small perturbation to the input image that causes the network to misclassify the sample. In this paper, w…
Effective training of neural networks requires much data. In the low-data regime, parameters are underdetermined, and learnt networks generalise poorly. Data Augmentation alleviates this by using existing data more effectively. However standard data augmentation produces only limited plausible alternative data. Given t…
Bayesian methods improve adversarial machine learning robustness.
problem Improving machine learning systems' security against adversarial manipulation.
method Integrating Bayesian perspectives to relax unrealistic assumptions in game-theoretic models.
result Bayesian approach provides more robust inferences about opponent's beliefs and interests.