Large Language Models (LLMs) and Vision-Language Models (VLMs) remain highly vulnerable to adversarial attacks despite widespread adoption. Existing defenses typically require retraining, rely on heuristics, or fail under adaptive and out-of-distribution (OOD) conditions. We introduce EigenShield, a principled, inference-time, architecture-agnostic defense that leverages Random Matrix Theory (RMT) to suppress adversarial noise in high-dimensional embeddings. EigenShield uses spiked covariance modeling and a Robustness-based Nonconformity Score (RbNS) with quantile thresholding to isolate and preserve causal eigenvectors, filtering out adversarial components without model access or adversarial training. We develop a theoretical framework establishing conditions for asymptotic noise suppression and demonstrate effectiveness in both unimodal and multimodal settings. Empirically, EigenShield consistently improves robustness across threat models, reducing attack success rates (ASR) by up to 48% over state-of-the-art defenses, including adversarial training, UNIGUARD, CIDER, and input transformations. On jailbreak attacks, EigenShield lowers LLM ASR by up to 92.9% relative to undefended models. Under multimodal adversarial attacks, it reduces VLM ASR by up to 76.5%. Against adaptive attacks on LLMs, it achieves ASR reductions of up to 77.7%. In OOD settings, EigenShield maintains strong performance, reducing ASR by up to 88.4% for LLMs and 80.4% for VLMs.

We propose SPARC, a lightweight continual learning framework for large language models (LLMs) that enables efficient task adaptation through prompt tuning in a lower-dimensional space. By leveraging principal component analysis (PCA), we identify a compact subspace of the training data. Optimizing prompts in this lower-dimensional space enhances training efficiency, as it focuses updates on the most relevant features while reducing computational overhead. Furthermore, since the model’s internal structure remains unaltered, the extensive knowledge gained from pretraining is fully preserved, ensuring that previously learned information is not compromised during adaptation. Our method achieves high knowledge retention in both task-incremental and domain-incremental continual learning setups while fine-tuning only 0.04% of the model’s parameters. Additionally, by integrating LoRA, we enhance adaptability to computational constraints, allowing for a tradeoff between accuracy and training cost. Experiments on the SuperGLUE benchmark demonstrate that our PCA-based prompt tuning combined with LoRA maintains full knowledge retention while improving accuracy, utilizing only 1% of the model’s parameters. These results establish our approach as a scalable and resource-efficient solution for continual learning in LLMs.

Active Learning (AL) has emerged as a powerful approach for minimizing labeling costs by selectively sampling the most informative data for neural network model development. Effective AL for large-scale vision-language models necessitates addressing challenges in uncertainty estimation and efficient sampling given the vast number of parameters involved. In this work, we introduce a novel parameter-efficient learning methodology that incorporates uncertainty calibration loss within the AL framework. We propose a differentiable loss function that promotes uncertainty calibration for effectively selecting fewer and most informative data samples for fine-tuning. Through extensive experiments across several datasets and vision backbones, we demonstrate that our solution can match and exceed the performance of complex feature-based sampling techniques while being computationally very efficient. Additionally, we investigate the efficacy of Prompt learning versus Low-rank adaptation (LoRA) in sample selection, providing a detailed comparative analysis of these methods in the context of efficient AL1.

In real-world, neural network models should be capable of adapting to evolving distributional shifts without catastrophic forgetting to remain trustworthy and robust. Having access to the source data on which the model was previously trained is one of the major challenges with respect to data privacy for model adaptation. We propose a source-free and parameter-efficient continual adaptive learning method for adapting to evolving data shifts with limited labels. We evaluate the method on large-scale image classification and semantic segmentation tasks using fifteen data shift types that are encountered incrementally in the continually evolving data drift settings. Extensive experiments demonstrate the proposed method achieves state-of-the-art model adaptation performance to continual data shifts, outperforming existing continual learning and domain adaptation methods.

Algorithmic transparency entails exposing system properties to various stakeholders for purposes that include understanding, improving, and contesting predictions. Until now, most research into algorithmic transparency has predominantly focused on explainability. Explainability attempts to provide reasons for a machine learning model's behavior to stakeholders. However, understanding a model's specific behavior alone might not be enough for stakeholders to gauge whether the model is wrong or lacks sufficient knowledge to solve the task at hand. In this paper, we argue for considering a complementary form of transparency by estimating and communicating the uncertainty associated with model predictions. First, we discuss methods for assessing uncertainty. Then, we characterize how uncertainty can be used to mitigate model unfairness, augment decision-making, and build trustworthy systems. Finally, we outline methods for displaying uncertainty to stakeholders and recommend how to collect information required for incorporating uncertainty into existing ML pipelines. This work constitutes an interdisciplinary review drawn from literature spanning machine learning, visualization/HCI, design, decision-making, and fairness. We aim to encourage researchers and practitioners to measure, communicate, and use uncertainty as a form of transparency.

Stochastic variational inference for Bayesian deep neural network (DNN) requires specifying priors and approximate posterior distributions over neural network weights. Specifying meaningful weight priors is a challenging problem, particularly for scaling variational inference to deeper architectures involving high dimensional weight space. We propose MOdel Priors with Empirical Bayes using DNN (MOPED) method to choose informed weight priors in Bayesian neural networks. We formulate a two-stage hierarchical modeling, first find the maximum likelihood estimates of weights with DNN, and then set the weight priors using empirical Bayes approach to infer the posterior with variational inference. We empirically evaluate the proposed approach on real-world tasks including image classification, video activity recognition and audio classification with varying complex neural network architectures. We also evaluate our proposed approach on diabetic retinopathy diagnosis task and benchmark with the state-of-the-art Bayesian deep learning techniques. We demonstrate MOPED method enables scalable variational inference and provides reliable uncertainty quantification.

Obtaining reliable and accurate quantification of uncertainty estimates from deep neural networks is important in safety-critical applications. A well-calibrated model should be accurate when it is certain about its prediction and indicate high uncertainty when it is likely to be inaccurate. Uncertainty calibration is a challenging problem as there is no ground truth available for uncertainty estimates. We propose an optimization method that leverages the relationship between accuracy and uncertainty as an anchor for uncertainty calibration. We introduce a differentiable accuracy versus uncertainty calibration (AvUC) loss function that allows a model to learn to provide well-calibrated uncertainties, in addition to improved accuracy. We also demonstrate the same methodology can be extended to post-hoc uncertainty calibration on pretrained models. We illustrate our approach with mean-field stochastic variational inference and compare with state-of-the-art methods. Extensive experiments demonstrate our approach yields better model calibration than existing methods on large-scale image classification tasks under distributional shift.

Deep neural networks (DNNs) provide state-of-the-art results for a multitude of applications, but the approaches using DNNs for multimodal audiovisual applications do not consider predictive uncertainty associated with individual modalities. Bayesian deep learning methods provide principled confidence and quantify predictive uncertainty. Our contribution in this work is to propose an uncertainty aware multimodal Bayesian fusion framework for activity recognition. We demonstrate a novel approach that combines deterministic and variational layers to scale Bayesian DNNs to deeper architectures. Our experiments using in- and out-of-distribution samples selected from a subset of Moments-in-Time (MiT) dataset show a more reliable confidence measure as compared to the non-Bayesian baseline and the Monte Carlo dropout (MC dropout) approximate Bayesian inference. We also demonstrate the uncertainty estimates obtained from the proposed framework can identify out-of-distribution data on the UCF101 and MiT datasets. In the multimodal setting, the proposed framework improved precision-recall AUC by 10.2% on the subset of MiT dataset as compared to non-Bayesian baseline.