相关论文: From Zero to Hero: Detecting Leaked Data through S…

Large Language Models (LLMs) are rapidly gaining enormous popularity in recent years. However, the training of LLMs has raised significant privacy and legal concerns, particularly regarding the distillation and inclusion of copyrighted…

As the Internet of Things (IoT) continues to expand, ensuring the security of connected devices has become increasingly critical. Traditional Intrusion Detection Systems (IDS) often fall short in managing the dynamic and large-scale nature…

The popularity of Machine Learning as a Service (MLaaS) has led to increased concerns about Model Stealing Attacks (MSA), which aim to craft a clone model by querying MLaaS. Currently, most research on MSA assumes that MLaaS can provide…

Power grids are becoming more digitized, resulting in new opportunities for the grid operation but also new challenges, such as new threats from the cyber-domain. To address these challenges, cybersecurity solutions are being considered in…

Supervised learning techniques typically assume training data originates from the target population. Yet, in reality, dataset shift frequently arises, which, if not adequately taken into account, may decrease the performance of their…

Classifiers and other statistics-based machine learning (ML) techniques generalize, or learn, based on various statistical properties of the training data. The assumption underlying statistical ML resulting in theoretical or empirical…

Zero-shot learning (ZSL) can be formulated as a cross-domain matching problem: after being projected into a joint embedding space, a visual sample will match against all candidate class-level semantic descriptions and be assigned to the…

As Industry 4.0 and digitalization continue to advance, the reliance on information technology increases, making the world more vulnerable to cyber-attacks, especially cyber-physical attacks that can manipulate physical systems and…

Huge amount of data is the key of the success of deep learning, however, redundant information impairs the generalization ability of the model and increases the burden of calculation. Dataset Distillation (DD) compresses the original…

Machine Learning-as-a-Service (MLaaS) has become a widespread paradigm, making even the most complex machine learning models available for clients via e.g. a pay-per-query principle. This allows users to avoid time-consuming processes of…

We analyze data leakage in visual datasets. Data leakage refers to images in evaluation benchmarks that have been seen during training, compromising fair model evaluation. Given that large-scale datasets are often sourced from the internet,…

While cryptographic algorithms such as the ubiquitous Advanced Encryption Standard (AES) are secure, *physical implementations* of these algorithms in hardware inevitably 'leak' sensitive data such as cryptographic keys. A particularly…

Machine learning (ML) models benefit from large datasets. Collecting data in biomedical domains is costly and challenging, hence, combining datasets has become a common practice. However, datasets obtained under different conditions could…

For distributed machine learning with sensitive data, we demonstrate how minimizing distance correlation between raw data and intermediary representations reduces leakage of sensitive raw data patterns across client communications while…

Side-channel attacks that leak sensitive information through a computing device's interaction with its physical environment have proven to be a severe threat to devices' security, particularly when adversaries have unfettered physical…

Keystroke inference attacks are a form of side-channel attacks in which an attacker leverages various techniques to recover a user's keystrokes as she inputs information into some display (e.g., while sending a text message or entering her…

Synthetically-generated data plays an increasingly larger role in training large language models. However, while synthetic data has been found to be useful, studies have also shown that without proper curation it can cause LLM performance…

AI agents increasingly excel at generating, testing, and refining code. However, they fall short on tasks requiring formal guarantees of full coverage that testing alone cannot provide. Distributed systems are a prime example: properties…

Federated learning is a decentralized learning paradigm introduced to preserve privacy of client data. Despite this, prior work has shown that an attacker at the server can still reconstruct the private training data using only the client…

Our ability to synthesize sensory data that preserves specific statistical properties of the real data has had tremendous implications on data privacy and big data analytics. The synthetic data can be used as a substitute for selective real…