Large Language Models (LLMs) have recently demonstrated remarkable capabilities in
natural language processing tasks and beyond. This success of LLMs has led to a large …

Deep learning (DL) is revolutionizing evidence-based decision-making techniques that can
be applied across various sectors. Specifically, it possesses the ability to utilize two or more …

Motivated by concerns that large-scale diffusion models can produce undesirable output
such as sexually explicit content or copyrighted artistic styles, we study erasure of specific …

It has been recognized that the data generated by the denoising diffusion probabilistic
model (DDPM) improves adversarial training. After two years of rapid development in …

Optimizing large language models (LLMs) for downstream use cases often involves the
customization of pre-trained LLMs through further fine-tuning. Meta's open release of Llama …

Deep learning models are often trained on distributed, web-scale datasets crawled from the
internet. In this paper, we introduce two new dataset poisoning attacks that intentionally …

Modern machine learning has subverted and bypassed the theoretical framework of
Chomsky's generative approach to linguistics, including its core claims to particular insights …

Deep machine unlearning is the problem of'removing'from a trained neural network a subset
of its training set. This problem is very timely and has many applications, including the key …

In tasks involving the interpretation of medical images, suitably trained machine-learning
models often exceed the performance of medical experts. Yet such a high-level of …

Although deep learning has achieved satisfactory performance in computer vision, a large
volume of images is required. However, collecting images is often expensive and …