Related papers: PICO: Secure Transformers via Robust Prompt Isolat…

In this work, we explore a novel framework for control of complex systems called Primitive Imitation for Control PICO. The approach combines ideas from imitation learning, task decomposition, and novel task sequencing to generalize from…

Nowadays, many control systems are networked and embed communication and computation capabilities. Such control architectures are prone to cyber attacks on the cyberinfrastructure. Consequently, there is an impellent need to develop…

In the context of prediction-as-a-service, concerns about the privacy of the data and the model have been brought up and tackled via secure inference protocols. These protocols are built up by using single or multiple cryptographic tools…

We present Clio, an information flow control (IFC) system that transparently incorporates cryptography to enforce confidentiality and integrity policies on untrusted storage. Clio insulates developers from explicitly manipulating keys and…

Collective operations are cornerstones of both HPC applications and large-scale AI training and inference, yet benchmarking them in a systematic and reproducible way remains difficult on modern systems due to the complexity of their…

The paper presents a distinctive and straightforward technique for stabilization of multi-variable systems. The idea is to decouple the system state matrix depending on different inputs and outputs. Refined special canonical transformations…

Through using only a well-trained classifier, model-inversion (MI) attacks can recover the data used for training the classifier, leading to the privacy leakage of the training data. To defend against MI attacks, previous work utilizes a…

Disturbance rejection in high-precision control applications can be significantly improved upon via online convex optimization (OCO). This includes classical techniques such as recursive least squares (RLS) and more recent, regret-based…

Distributing the inference of convolutional neural network (CNN) to multiple mobile devices has been studied in recent years to achieve real-time inference without losing accuracy. However, how to map CNN to devices remains a challenge. On…

Trusted I/O (TIO) is an appealing solution to improve I/O performance for confidential VMs (CVMs), with the potential to eliminate broad sources of I/O overhead. However, this paper emphasizes that not all types of I/O can derive…

Randomized smoothing is a powerful tool for certifying robustness to adversarial perturbations, including poisoning attacks via randomized training and evasion attacks via randomized inference. Extending these guarantees to backdoor…

This paper proposes an active attack detection scheme for constrained cyber-physical systems. Despite passive approaches where the detection is based on the analysis of the input-output data, active approaches interact with the system by…

This paper aims to create a secure environment for networked control systems composed of multiple dynamic entities and computational control units via networking, in the presence of disclosure attacks. In particular, we consider the…

Quantum circuits are the fundamental representation of quantum algorithms and constitute valuable intellectual property (IP). Multiple quantum circuit obfuscation (QCO) techniques have been proposed in prior research to protect quantum…

Tomography inference attacks aim to reconstruct network topology by analyzing end-to-end probe delays. Existing defenses mitigate these attacks by manipulating probe delays to mislead inference, but rely on two strong assumptions: (i) probe…

We present Piko, a framework for designing, optimizing, and retargeting implementations of graphics pipelines on multiple architectures. Piko programmers express a graphics pipeline by organizing the computation within each stage into…

The power grid is a critical infrastructure essential for public safety and welfare. As its reliance on digital technologies grows, so do its vulnerabilities to sophisticated cyber threats, which could severely disrupt operations. Effective…

Closed-loop verification of cyber-physical systems with neural network controllers offers strong safety guarantees under certain assumptions. It is, however, difficult to determine whether these guarantees apply at run time because…

Large language model (LLM) performance depends heavily on prompt design, yet prompt construction is often described and applied inconsistently. Our purpose was to derive a reference framework for structuring LLM prompts. This paper presents…

Timing side-channel attacks pose a major threat to embedded systems due to their ease of accessibility. We propose CIDPro, a framework that relies on dynamic program diversification to mitigate timing side-channel leakage. The proposed…