Related papers: Stealing Maggie's Secrets -- On the Challenges of …

As autonomous driving and augmented reality evolve, a practical concern is data privacy. In particular, these applications rely on localization based on user images. The widely adopted technology uses local feature descriptors, which are…

The widespread accessibility and ease of use of additive manufacturing (AM), widely recognized as 3D printing, has put Intellectual Property (IP) at great risk of theft. As 3D printers emit acoustic and magnetic signals while printing, the…

Federated Unlearning (FU) has emerged as a critical compliance mechanism for data privacy regulations, requiring unlearned clients to provide verifiable Proof of Federated Unlearning (PoFU) to auditors upon data removal requests. However,…

Neural networks have been shown to be vulnerable against fault injection attacks. These attacks change the physical behavior of the device during the computation, resulting in a change of value that is currently being computed. They can be…

Hardware intellectual property (IP) in the globalized integrated circuit (IC) supply chain is exposed to a wide range of confidentiality and integrity attacks by untrusted third-party entities. Existing IP-level countermeasures, such as…

Pre-trained language models advance patent classification and retrieval via encoding claims as flat token sequences, yet overlooking the dependency hierarchy among claims. Incorporating the hierarchy into self-attention poses two…

Defenses against security threats have been an interest of recent studies. Recent works have shown that it is not difficult to attack a natural language processing (NLP) model while defending against them is still a cat-mouse game. Backdoor…

Insider threats have become reality for civilian firms such as Tesla, which experienced sabotage and intellectual property theft, and Capital One, which suffered from fraud. Even greater social impact was caused by the data breach at the US…

The rapid growth of data size and accessibility in recent years has instigated a shift of philosophy in algorithm design for artificial intelligence. Instead of engineering algorithms by hand, the ability to learn composable systems…

Machine learning (ML) is vulnerable to inference (e.g., membership inference, property inference, and data reconstruction) attacks that aim to infer the private information of training data or dataset. Existing defenses are only designed…

Plagiarism in programming assignments is a persistent issue in computer science education, increasingly complicated by the emergence of automated obfuscation attacks. While software plagiarism detectors are widely used to identify…

Retrieval-augmented generation (RAG) is a powerful technique to facilitate language model with proprietary and private data, where data privacy is a pivotal concern. Whereas extensive research has demonstrated the privacy risks of large…

Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…

Model inversion attacks pose an open challenge to privacy-sensitive applications that use machine learning (ML) models. For example, face authentication systems use modern ML models to compute embedding vectors from face images of the…

The goal of Domain Generation Algorithm (DGA) detection is to recognize infections with bot malware and is often done with help of Machine Learning approaches that classify non-resolving Domain Name System (DNS) traffic and are trained on…

The onward development of information and communication technology has led to a new industrial revolution called Industry 4.0. This revolution involves Cyber-Physical Production Systems (CPPS), which consist of intelligent Cyber-Physical…

This work explores the use of machine learning techniques on an Internet-of-Things firmware dataset to detect malicious attempts to infect edge devices or subsequently corrupt an entire network. Firmware updates are uncommon in IoT devices;…

Deep learning (DL) is becoming the cornerstone of numerous applications both in datacenters and at the edge. Specialized hardware is often necessary to meet the performance requirements of state-of-the-art DL models, but the rapid pace of…

The need for secure and private Artificial Intelligence (AI) and Machine Learning (ML) on edge and mobile devices has increased the necessity of protecting the architecture of these systems from threats to both security and privacy. With an…

Federated learning (FL) empowers privacypreservation in model training by only exposing users' model gradients. Yet, FL users are susceptible to gradient inversion attacks (GIAs) which can reconstruct ground-truth training data such as…