相关论文: Salsa Fresca: Angular Embeddings and Pre-Training …

Machine learning malware detectors are vulnerable to adversarial EXEmples, i.e., carefully-crafted Windows programs tailored to evade detection. Unlike other adversarial problems, attacks in this context must be functionality-preserving, a…

Pre-training decoder-only language models relies on vast amounts of high-quality data, yet the availability of such data is increasingly reaching its limits. While metadata is commonly used to create and curate these datasets, its potential…

Recent developments in Large Language Model (LLM) capabilities have brought great potential but also posed new risks. For example, LLMs with knowledge of bioweapons, advanced chemistry, or cyberattacks could cause violence if placed in the…

To address the growing demand for privacy protection in machine learning, we propose a novel and efficient machine unlearning approach for \textbf{L}arge \textbf{M}odels, called \textbf{LM}Eraser. Existing unlearning research suffers from…

With the increasing adoption of Large Language Models (LLMs), more customization is needed to ensure privacy-preserving and safe generation. We address this objective from two critical aspects: unlearning of sensitive information and…

This paper provides a starting point for Software Engineering (SE) researchers and practitioners faced with the problem of training machine learning models on small datasets. Due to the high costs associated with labeling data, in Software…

Word embedding is a Natural Language Processing (NLP) technique that automatically maps words from a vocabulary to vectors of real numbers in an embedding space. It has been widely used in recent years to boost the performance of a vari-ety…

Public security vulnerability reports (e.g., CVE reports) play an important role in the maintenance of computer and network systems. Security companies and administrators rely on information from these reports to prioritize tasks on…

As a privacy-preserving method for implementing Vertical Federated Learning, Split Learning has been extensively researched. However, numerous studies have indicated that the privacy-preserving capability of Split Learning is insufficient.…

Ensembling word embeddings to improve distributed word representations has shown good success for natural language processing tasks in recent years. These approaches either carry out straightforward mathematical operations over a set of…

Recent model inversion attack algorithms permit adversaries to reconstruct a neural network's private and potentially sensitive training data by repeatedly querying the network. In this work, we develop a novel network architecture that…

While deep learning models have shown significant performance across various domains, their deployment needs extensive resources and advanced computing infrastructure. As a solution, Machine Learning as a Service (MLaaS) has emerged,…

Malware evolves rapidly, forcing machine learning (ML)-based detectors to adapt continuously. With antivirus vendors processing hundreds of thousands of new samples daily, datasets can grow to billions of examples, making full retraining…

Machine learning (ML) techniques are increasingly common in security applications, such as malware and intrusion detection. However, ML models are often susceptible to evasion attacks, in which an adversary makes changes to the input (such…

Deep neural networks (DNNs) have been quite successful in solving many complex learning problems. However, DNNs tend to have a large number of learning parameters, leading to a large memory and computation requirement. In this paper, we…

This paper extends the Kikuchi method to give algorithms for decisional $k$-sparse Learning With Errors (LWE) and $k$-sparse Learning Parity with Noise (LPN) problems for higher moduli $q$. We create a Kikuchi graph for a sparse LWE/LPN…

Sparse autoencoders (SAEs) are widely used for interpreting language model activations. A key evaluation metric is the increase in cross-entropy loss between the original model logits and the reconstructed model logits when replacing model…

Learning from the data stored in a database is an important function increasingly available in relational engines. Methods using lower precision input data are of special interest given their overall higher efficiency but, in databases,…

Large Language Models (LLMs) are increasingly served on shared accelerators where an adversary with read access to device memory can observe KV caches and hidden states, threatening prompt privacy for open-source models. Cryptographic…

We study the unique, less-well understood problem of generating sparse adversarial samples simply by observing the score-based replies to model queries. Sparse attacks aim to discover a minimum number-the l0 bounded-perturbations to model…