Related papers: Gradient Inversion Transcript: Leveraging Robust G…
Data privacy has become an increasingly important issue in Machine Learning (ML), where many approaches have been developed to tackle this challenge, e.g. cryptography (Homomorphic Encryption (HE), Differential Privacy (DP), etc.) and…
A promising paradigm for adapting instruction-tuned language models is to learn task-specific updates on a pretrained base model and subsequently merge them into the instruction-tuned model. However, existing approaches typically treat the…
Gravity inversion is the problem of estimating subsurface density distributions from observed gravitational field data. We consider the two-dimensional (2D) case, in which recovering density models from one-dimensional (1D) measurements…
The memorization of training data by neural networks raises pressing concerns for privacy and security. Recent work has shown that, under certain conditions, portions of the training set can be reconstructed directly from model parameters.…
Federated Learning (FL) is a distributed learning framework, in which the local data never leaves clients devices to preserve privacy, and the server trains models on the data via accessing only the gradients of those local data. Without…
Retrieval-Augmented Generation (RAG) improves pre-trained models by incorporating external knowledge at test time to enable customized adaptation. We study the risk of datastore leakage in Retrieval-In-Context RAG Language Models (LMs). We…
Adversarial attacks present a critical challenge to deep neural networks' robustness, particularly in transfer scenarios across different model architectures. However, the transferability of adversarial attacks faces a fundamental dilemma…
A major obstacle to developing artificial intelligence applications capable of true lifelong learning is that artificial neural networks quickly or catastrophically forget previously learned tasks when trained on a new one. Numerous methods…
The graph convolutional network (GCN) is a go-to solution for machine learning on graphs, but its training is notoriously difficult to scale both in terms of graph size and the number of model parameters. Although some work has explored…
Generative retrieval represents a novel approach to information retrieval. It uses an encoder-decoder architecture to directly produce relevant document identifiers (docids) for queries. While this method offers benefits, current approaches…
Generative retrieval shed light on a new paradigm of document retrieval, aiming to directly generate the identifier of a relevant document for a query. While it takes advantage of bypassing the construction of auxiliary index structures,…
Graph neural networks (GNNs) have exhibited superior performance in various classification tasks on graph-structured data. However, they encounter the potential vulnerability from the link stealing attacks, which can infer the presence of a…
Penetration testing (PT) is an efficient network testing and vulnerability mining tool by simulating a hacker's attack for valuable information applied in some areas. Compared with manual PT, intelligent PT has become a dominating…
Innovations in neural architectures have fostered significant breakthroughs in language modeling and computer vision. Unfortunately, novel architectures often result in challenging hyper-parameter choices and training instability if the…
This paper presents the use of Retrieval Augmented Generation (RAG) to improve the feedback generated by Large Language Models for programming tasks. For this purpose, corresponding lecture recordings were transcribed and made available to…
Model inversion (MI) attacks aim to infer or reconstruct the training dataset through reverse-engineering from the target model's weights. Recently, significant advancements in generative models have enabled MI attacks to overcome…
Parameter-efficient fine-tuning (PEFT) has emerged as a practical solution for adapting large language models (LLMs) to custom datasets with significantly reduced computational cost. When carrying out PEFT under collaborative learning…
Deepfakes, malicious visual contents created by generative models, pose an increasingly harmful threat to society. To proactively mitigate deepfake damages, recent studies have employed adversarial perturbation to disrupt deepfake model…
We introduce a method called TracIn that computes the influence of a training example on a prediction made by the model. The idea is to trace how the loss on the test point changes during the training process whenever the training example…
The remarkable performance gains realized by large pretrained models, e.g., GPT-3, hinge on the massive amounts of data they are exposed to during training. Analogously, distilling such large models to compact models for efficient…