arXiv:2404. 01356v3 Announce Type: replace-cross Abstract: Deep neural networks are vulnerable to adversarial perturbations that can simultaneously degrade prediction robustness and individual fairness across diverse application settings.
arXiv:2404. 01356v4 Announce Type: replace-cross Abstract: Deep neural networks are vulnerable to adversarial perturbations that can simultaneously degrade prediction robustness and individual fairness across diverse application settings.
arXiv:2608.29247v1 Announce Type: new Abstract: Deep neural networks remain highly vulnerable to adversarial perturbations, and adversarial training (AT) has become a widely used approach for improvi...
arXiv:2608.21577v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed in high-stakes domains where fairness is a critical safety requirement. In practic...
arXiv:2607. 14705v1 Announce Type: new Abstract: Graph neural networks (GNNs) frequently encounter group fairness issues, often yielding biased predictions against specific demographic groups defined by sensitive attributes such as gender or race.
arXiv:2503.05684v2 Announce Type: replace-cross Abstract: Pre-trained foundation models can be efficiently adapted for specific tasks using Low-Rank Adaptation (LoRA), but the fairness properties of...
arXiv:2609.40034v1 Announce Type: cross Abstract: Over the past decade, Machine Learning (ML) has been trained under dual objectives: minimizing prediction error via Empirical Risk Minimization (ERM)...
arXiv:2607. 03075v1 Announce Type: new Abstract: Safety-critical applications require classifiers that are both robust and reliable.
arXiv:2609.16321v1 Announce Type: cross Abstract: Existing fairness analysis tools predominantly operate as post-training evaluation frameworks, requiring practitioners to complete the full model dev...
FairNVT is a lightweight debiasing framework that injects calibrated Gaussian noise into sensitive embeddings learned by adapters for pretrained transformer-based encoders. By reducing sensitive-attribute leakage through orthogonality constraints and fairness regularization, it improves fairness metrics such as demographic parity difference and equalized odds while maintaining competitive task performance across vision and language datasets.
The paper proposes a fairness-aware Mixture-of-Experts (MoE) framework that tackles routing-induced bias by applying subgroup reweighting to correct data imbalance and gate entropy regularization to prevent the gating network from collapsing onto subgroup attributes. This end-to-end approach keeps expert utilization balanced and interpretable, offering a clear view of how subgroups are allocated across experts. Experiments show that the method improves fairness while maintaining competitive predictive performance.
arXiv:2607. 21300v1 Announce Type: cross Abstract: Machine unlearning has emerged as a tool for removing personal data from trained models to comply with recent AI regulations.
arXiv:2511.21799v2 Announce Type: replace Abstract: Real-world machine learning (ML) pipelines rarely produce a single model; instead, they produce a Rashomon set of many near-optimal ones. We show t...