相关论文: AugLy: Data Augmentations for Robustness

Data augmentation is a widely used technique and an essential ingredient in the recent advance in self-supervised representation learning. By preserving the similarity between augmented data, the resulting data representation can improve…

Learning from visual observations is a fundamental yet challenging problem in Reinforcement Learning (RL). Although algorithmic advances combined with convolutional neural networks have proved to be a recipe for success, current methods are…

The availability of highly convincing audio deepfake generators highlights the need for designing robust audio deepfake detectors. Existing works often rely solely on real and fake data available in the training set, which may lead to…

As a new programming paradigm, deep learning has expanded its application to many real-world problems. At the same time, deep learning based software are found to be vulnerable to adversarial attacks. Though various defense mechanisms have…

Retrieval Augmented Generation (RAG) frameworks improve the accuracy of large language models (LLMs) by integrating external knowledge from retrieved documents, thereby overcoming the limitations of models' static intrinsic knowledge.…

Achieving robustness in image segmentation models is challenging due to the fine-grained nature of pixel-level classification. These models, which are crucial for many real-time perception applications, particularly struggle when faced with…

Retrieval-augmented generation (RAG) pipelines have become the de-facto approach for building AI assistants with access to external, domain-specific knowledge. Given a user query, RAG pipelines typically first retrieve (R) relevant…

Model providers increasingly release open weights or allow users to fine-tune foundation models through APIs. Although these models are safety-aligned before release, their safeguards can often be removed by fine-tuning on harmful data.…

Deep neural networks have become popular in many supervised learning tasks, but they may suffer from overfitting when the training dataset is limited. To mitigate this, many researchers use data augmentation, which is a widely used and…

Recent large language models (LLMs) have demonstrated remarkable prediction performance for a growing array of tasks. However, their proliferation into high-stakes domains (e.g. medicine) and compute-limited settings has created a…

Large Language Models (LLMs) have demonstrated advanced capabilities in both text generation and comprehension, and their application to data archives might facilitate the privatization of sensitive information about the data subjects. In…

Data augmentation has proven to be effective in training neural networks. Recently, a method called RandAug was proposed, randomly selecting data augmentation techniques from a predefined search space. RandAug has demonstrated significant…

Image Quality Assessment (IQA) models are increasingly relied upon to evaluate image quality in real-world systems -- from compression and enhancement to generation and streaming. Yet their adoption brings a fundamental risk: these models…

Offline reinforcement learning (RL) addresses the challenge of expensive and high-risk data exploration inherent in RL by pre-training policies on vast amounts of offline data, enabling direct deployment or fine-tuning in real-world…

Small datasets are common in health research. However, the generalization performance of machine learning models is suboptimal when the training datasets are small. To address this, data augmentation is one solution. Augmentation increases…

Data augmentation methods have played an important role in the recent advance of deep learning models, and have become an indispensable component of state-of-the-art models in semi-supervised, self-supervised, and supervised training for…

Modeling dynamic graphs, such as those found in social networks, recommendation systems, and e-commerce platforms, is crucial for capturing evolving relationships and delivering relevant insights over time. Traditional approaches primarily…

To help adversarial examples generalize from surrogate machine-learning (ML) models to targets, certain transferability-based black-box evasion attacks incorporate data augmentations (e.g., random resizing). Yet, prior work has explored…

Data augmentation has been actively studied for robust neural networks. Most of the recent data augmentation methods focus on augmenting datasets during the training phase. At the testing phase, simple transformations are still widely used…

We present DARLEI, a framework that combines evolutionary algorithms with parallelized reinforcement learning for efficiently training and evolving populations of UNIMAL agents. Our approach utilizes Proximal Policy Optimization (PPO) for…