相关论文: Rethinking Split Manufacturing: An Information-The…

Large Language Models (LLMs) remain vulnerable to prompt injection attacks, representing the most significant security threat in production deployments. We present Prompt Fencing, a novel architectural approach that applies cryptographic…

This paper presents a high-level circuit obfuscation technique to prevent the theft of intellectual property (IP) of integrated circuits. In particular, our technique protects a class of circuits that relies on constant multiplications,…

While various obfuscation methods exist in the digital domain, techniques for protecting Intellectual Property (IP) in the analog domain are mostly overlooked. Understandably, analog components have a small footprint as most of the surface…

Split Neural Network, as one of the most common architectures used in vertical federated learning, is popular in industry due to its privacy-preserving characteristics. In this architecture, the party holding the labels seeks cooperation…

As cache-based side-channel attacks become serious security problems, various defenses have been proposed and deployed in both software and hardware. Consequently, cache-based side-channel attacks on processes co-residing on the same core…

Jamming refers to the deletion, corruption or damage of meter measurements that prevents their further usage. This is distinct from adversarial data injection that changes meter readings while preserving their utility in state estimation.…

Cyber attacks have become serious threats to Industrial Control systems as well. It becomes important to develop a serious threat defense system against such vulnerabilities. For such process control systems, safety should also be assured…

This paper describes a complex networks approach to study the failure tolerance of mechatronic software systems under various types of hardware and/or software failures. We produce synthetic system architectures based on evidence of modular…

Privacy-sensitive users require deploying large language models (LLMs) within their own infrastructure (on-premises) to safeguard private data and enable customization. However, vulnerabilities in local environments can lead to unauthorized…

Split inference (SI) partitions deep neural networks into distributed sub-models, enabling collaborative learning without directly sharing raw data. However, SI remains vulnerable to Data Reconstruction Attacks (DRAs), where adversaries…

Partitioning graphs into blocks of roughly equal size such that few edges run between blocks is a frequently needed operation in processing graphs. Recently, size, variety, and structural complexity of these networks has grown dramatically.…

Classic hardware verification techniques (e.g., X-propagation and fault-propagation) and more recent hardware security verification techniques based on information flow tracking (IFT) aim to understand how information passes, affects, and…

Machine learning systems deployed in distributed or federated environments are highly susceptible to adversarial manipulations, particularly availability attacks -adding imperceptible perturbations to training data, thereby rendering the…

Chip manufacturing is a complex process, and to achieve a faster time to market, an increasing number of untrusted third-party tools and designs from around the world are being utilized. The use of these untrusted third party intellectual…

Federated learning (FL) is gaining increasing attention as an emerging collaborative machine learning approach, particularly in the context of large-scale computing and data systems. However, the fundamental algorithm of FL, Federated…

Logic locking is a method to prevent intellectual property (IP) piracy. However, under a reasonable attack model, SAT-based methods have proven to be powerful in obtaining the secret key. In response, many locking techniques have been…

In the wake of the burgeoning expansion of generative artificial intelligence (AI) services, the computational demands inherent to these technologies frequently necessitate cloud-powered computational offloading, particularly for…

Besides the advantages derived from the ever present communication properties, it increases the attack surface of a network as well. As industrial protocols and systems were not designed with security in mind, spectacular attacks on…

The power consumption of a microprocessor is a huge channel for information leakage. While the most popular exploitation of this channel is to recover cryptographic keys from embedded devices, other applications such as mobile app…

Existing logic-locking attacks are known to successfully decrypt functionally correct key of a locked combinational circuit. It is possible to extend these attacks to real-world Silicon-based Intellectual Properties (IPs, which are…