PGD-trained models have a preferential direction in their gradients, which improves robustness.
problem Mathematical lack of clarity in the direction of preferential gradient alignment after adversarial training.
method Proposed a novel definition of preferential direction and evaluated it using a metric based on GANs.
result PGD-trained models have higher alignment with the proposed preferential direction than baseline models.
Pairwise discriminators stabilize adversarial training by ensuring the generator's alignment is preserved.
problem Stability issues in adversarial training when using sub-optimal discriminators.
method Introducing a family of objectives using pairwise discriminators, ensuring the generator's alignment is preserved.
result Only the generator needs to converge, and the alignment is preserved with any discriminator.
Network alignment is a critical task to a wide variety of fields. Many existing works leverage on representation learning to accomplish this task without eliminating domain representation bias induced by domain-dependent features, which yield inferior alignment performance. This paper proposes a unified deep architectu…
For a standard convolutional neural network, optimizing over the input pixels to maximize the score of some target class will generally produce a grainy-looking version of the original image. However, Santurkar et al. (2019) demonstrated that for adversarially-trained neural networks, this optimization produces images …
Unified framework improves cross-corpus EEG emotion recognition by aligning prototypes and refining decision boundaries.
problem Cross-corpus EEG emotion recognition suffers from performance degradation due to physiological variability and device inconsistencies.
method Prototype-driven Adversarial Alignment (PAA) framework with three configurations: local, contrastive, and boundary-aware.
result State-of-the-art performance improvements across four cross-corpus evaluation protocols.
Paper proposes MDAT to stabilize domain alignment in label-scarce settings.
problem Stable and comprehensive domain alignment in label-scarce settings.
method Max-margin Domain-Adversarial Training (MDAT) with Adversarial Reconstruction Network (ARN).
result MDAT stabilizes gradient reversing and achieves strong robustness to hyper-parameters.
Paper proposes Adversarial CCA for multi-view alignment and generation.
problem Aligning multiple views in cross-view data analysis problems.
method Bayesian perspective, adversarial training for consistent latent encodings.
result ACCA model achieves superior performance in multi-view alignment and generation.
ADGAN improves risk tolerance prediction by aligning cross-domain data.
problem Lack of professional knowledge and domain-specific models in risk tolerance studies.
method Asymmetric cross-Domain Generative Adversarial Network (ADGAN) for domain scale inequality.
result ADGAN better handles class imbalance and unqualified data than state-of-the-art methods.
This paper studies aligning knowledge graphs from different sources or languages. Most existing methods train supervised methods for the alignment, which usually require a large number of aligned knowledge triplets. However, such a large number of aligned knowledge triplets may not be available or are expensive to obta…
New method defends deep nets against large perturbations perceptible to humans.
problem Vulnerability of deep nets to adversarial attacks with perceptible but not changing predictions.
method Oracle-Aligned Adversarial Training (OA-AT) to align network predictions with Oracle's.
result Achieves state-of-the-art performance at large perturbation bounds (L-inf of 16/255 on CIFAR-10).
AI models aligned with human vision perform well on few data tasks.
problem Few-shot learning performance with limited data.
method Information-theoretic analysis and empirical testing of 491 models.
result Highly aligned models show better robustness to attacks and domain shifts.
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.
A new method for aligning multiple distributions efficiently.
problem Aligning multiple distributions in a shared latent space.
method Iterative alignment of variational approximations of distribution divergences using invertible alignment maps.
result Our method achieves competitive distribution alignment at low computational cost.
Proposes novel losses for fine-grained categorical domain adaptation.
problem Fine-grained alignment of categories across domains in unsupervised domain adaptation.
method Joint category-domain classifier with adversarial training losses for both domain and category levels, and vicinal domain adaptation.
result Achieves state-of-the-art performance on benchmark datasets.
High-dimensional neural network manifolds misalign with human perception, causing adversarial examples.
problem Adversarial attacks fool neural networks, but their origin is unclear.
method Defined and analyzed a network's perceptual manifold (PM) for a class concept.
result Neural network PMs have orders of magnitude higher dimensions than natural human concepts, suggesting exponential misalignment.
Proposes a non-adversarial method for distribution matching.
problem Stability and optimization challenges in adversarial matching methods.
method Non-adversarial VAE-based matching method with alignment upper bounds.
result Demonstrates applicability of non-adversarial matching methods without modifying original architectures.
Shorter adversarial prompts help protect LLMs from jailbreak attacks.
problem Protecting large language models from jailbreak attacks with long adversarial suffixes.
method Adversarial training on shorter adversarial suffixes to defend against longer adversarial suffixes.
result Aligning LLMs on shorter adversarial suffixes can effectively defend against jailbreak attacks with longer suffixes.
Recent studies on the adversarial vulnerability of neural networks have shown that models trained to be more robust to adversarial attacks exhibit more interpretable saliency maps than their non-robust counterparts. We aim to quantify this behavior by considering the alignment between input image and saliency map. We h…
Adversarial training makes logistic regression weight loss landscapes sharper.
problem Understanding why adversarial training sharpens the weight loss landscape in logistic regression.
method Theoretical analysis of linear logistic regression model with L2 norm constraints, and experiments on ResNet18.
result Adversarial training sharpens the weight loss landscape in linear logistic regression models.
Graph-Relational Domain Adaptation (GRDA) adapts domains based on their graph structure.
problem Uniform alignment of domains ignores topological structures.
method Uses a domain graph to encode adjacency and a novel graph discriminator.
result Empirically shows improved generalization and domain information incorporation.
Domain adaptation addresses the common problem when the target distribution generating our test data drifts from the source (training) distribution. While absent assumptions, domain adaptation is impossible, strict conditions, e.g. covariate or label shift, enable principled algorithms. Recently-proposed domain-adversa…
Unsupervised domain mapping has attracted substantial attention in recent years due to the success of models based on the cycle-consistency assumption. These models map between two domains by fooling a probabilistic discriminator, thereby matching the probability distributions of the real and generated data. Instead of…
We propose a method for unsupervised domain adaptation that trains a shared embedding to align the joint distributions of inputs (domain) and outputs (classes), making any classifier agnostic to the domain. Joint alignment ensures that not only the marginal distributions of the domain are aligned, but the labels as wel…
Mapping and translating professional but arcane clinical jargons to consumer language is essential to improve the patient-clinician communication. Researchers have used the existing biomedical ontologies and consumer health vocabulary dictionary to translate between the languages. However, such approaches are limited b…
The recent advances in deep transfer learning reveal that adversarial learning can be embedded into deep networks to learn more transferable features to reduce the distribution discrepancy between two domains. Existing adversarial domain adaptation methods either learn a single domain discriminator to align the global …
Gradient-trained shallow networks can generalize well but are vulnerable to small-radius adversarial attacks.
problem Adversarial robustness of gradient-trained shallow networks.
method Analysis of neuron alignment and polynomial ReLU activation.
result Gradient-trained shallow networks with polynomial ReLU activation are robust to small-radius adversarial attacks.
Generative Adversarial Regression (GAR) learns risk scenarios robustly across policies.
problem Learning risk scenarios for conditional risk objectives.
method Generative adversarial framework for risk matching.
result GAR produces more stable and risk-preserving scenarios than baselines.
Study reveals how neural network biases align with adversarial attack frequencies.
problem Correlation between neural network biases and adversarial attacks.
method Fourier transform analysis of network implicit bias and adversarial perturbations.
result Network bias and adversarial attack frequencies are highly correlated.
FRA-Attack improves adversarial transferability for closed-source MLLMs by aligning visual focus across models.
problem Improving adversarial transferability for closed-source MLLMs, especially with high accuracy.
method Unified frequency-domain regularization approach: high-pass DCT objective for feature alignment and Frequency-domain Gradient Regularization (FGR) for gradient optimization.
result FRA-Attack achieves superior cross-model transferability, especially on GPT-5.4, Claude-Opus-4.6, and Gemini-3-flash.
MetFA aligns source and target domains for cross-device image classification.
problem Learning discriminative class boundaries across different domains.
method Distance metric guided feature alignment (MetFA) for domain-invariant and discriminative feature extraction.
result MetFA outperforms state-of-the-art methods in cross-device image classification.
Adversarial training is a useful approach to promote the learning of transferable representations across the source and target domains, which has been widely applied for domain adaptation (DA) tasks based on deep neural networks. Until very recently, existing adversarial domain adaptation (ADA) methods ignore the usefu…
RePULSe improves language model alignment by reducing undesired outputs without sacrificing overall performance.
problem Aligning language models with human preferences while minimizing undesired outputs.
method Integrates probabilistic inference into RL training to reduce undesired outputs.
result RePULSe achieves a better balance between expected reward and undesired output probability.
New method for robust distribution alignment using log-likelihood ratio and normalizing flows.
problem Distribution alignment challenges in deep learning.
method Log-likelihood ratio statistic and normalizing flows.
result Minimizing the proposed objective yields robust domain alignment.
Many predicted structured objects (e.g., sequences, matchings, trees) are evaluated using the F-score, alignment error rate (AER), or other multivariate performance measures. Since inductively optimizing these measures using training data is typically computationally difficult, empirical risk minimization of surrogate …
This paper improves model robustness against adversarial attacks using optimal transport.
problem Adversarial attacks can mislead deep learning models with imperceptible perturbations.
method Exploits optimal transport theory to align adversarial and original image distributions.
result SAT (Sinkhorn Adversarial Training) leads to more robust models compared to state-of-the-art.
We study the question of how to imitate tasks across domains with discrepancies such as embodiment, viewpoint, and dynamics mismatch. Many prior works require paired, aligned demonstrations and an additional RL step that requires environment interactions. However, paired, aligned demonstrations are seldom obtainable an…
Adversarial training is a training scheme designed to counter adversarial attacks by augmenting the training dataset with adversarial examples. Surprisingly, several studies have observed that loss gradients from adversarially trained DNNs are visually more interpretable than those from standard DNNs. Although this phe…
We consider unsupervised domain adaptation: given labelled examples from a source domain and unlabelled examples from a related target domain, the goal is to infer the labels of target examples. Under the assumption that features from pre-trained deep neural networks are transferable across related domains, domain adap…
SONA improves conditional generation by balancing authenticity and alignment.
problem Challenges in balancing authenticity and conditional alignment in conditional generative models.
method SONA integrates unconditional discrimination, matching-aware supervision, and adaptive weighting to balance authenticity and alignment.
result SONA achieves superior sample quality and conditional alignment compared to state-of-the-art methods.
Aligns attention distributions for improved accuracy and robustness.
problem Improving the accuracy and robustness of neural networks using attention mechanisms.
method Alignment attention that encourages key and query distributions to match within each head.
result Alignment attention leads to better accuracy, uncertainty estimation, and robustness across various tasks.
In this paper we propose a novel dual adversarial co-learning approach for multi-domain text classification (MDTC). The approach learns shared-private networks for feature extraction and deploys dual adversarial regularizations to align features across different domains and between labeled and unlabeled data simultaneo…
Paper tackles distribution matching by partially matching distributions, achieving robust results.
problem Robustly aligning two probability distributions.
method Developed a partial Wasserstein adversarial network (PWAN) to efficiently approximate the partial Wasserstein-1 (PW) discrepancy.
result The PWAN effectively produces highly robust matching results, outperforming state-of-the-art methods.
New method prevents adversarial training failure in deep networks.
problem Adversarial training failure in deep networks.
method GradAlign method to prevent catastrophic overfitting.
result GradAlign prevents adversarial training failure in deep networks.
Continuous appearance shifts such as changes in weather and lighting conditions can impact the performance of deployed machine learning models. While unsupervised domain adaptation aims to address this challenge, current approaches do not utilise the continuity of the occurring shifts. In particular, many robotics appl…
Neural networks have been proven to be vulnerable to a variety of adversarial attacks. From a safety perspective, highly sparse adversarial attacks are particularly dangerous. On the other hand the pixelwise perturbations of sparse attacks are typically large and thus can be potentially detected. We propose a new black…
ClusTR improves clustering-based models' robustness without adversarial training.
problem Improving clustering-based models' robustness.
method Proposes ClusTR, a clustering-based training framework for robust models without adversarial training.
result ClusTR outperforms adversarially-trained models by up to 4% under strong PGD attacks.
New method removes pseudo-label bias for unsupervised domain adaptation.
problem Class imbalance and distribution shift between domains.
method Implicit class-conditioned domain alignment without explicit pseudo-label optimization.
result Effective in handling within-domain class imbalance and between-domain class distribution shift.
Label noise in adversarial training leads to robust overfitting, explained and mitigated.
problem Label noise in adversarial training causes robust overfitting.
method Proposed a method to automatically calibrate labels.
result Consistent performance improvements across various models and datasets.