Related papers: Moving-horizon False Data Injection Attack Design …

Deep Neural Network (DNN) models when implemented on executing devices as the inference engines are susceptible to Fault Injection Attacks (FIAs) that manipulate model parameters to disrupt inference execution with disastrous performance.…

Fully Homomorphic Encryption (FHE) represents a paradigm shift in cryptography, enabling computation directly on encrypted data and unlocking privacy-critical computation. Despite being increasingly deployed in real platforms, the…

Physical consequences to power systems of false data injection cyber-attacks are considered. Prior work has shown that the worst-case consequences of such an attack can be determined using a bi-level optimization problem, wherein an attack…

Intrusion detection systems (IDS) for the Internet of Things (IoT) systems can use AI-based models to ensure secure communications. IoT systems tend to have many connected devices producing massive amounts of data with high dimensionality,…

In this paper, we present the concept of boosting the resiliency of optimization-based observers for cyber-physical systems (CPS) using auxiliary sources of information. Due to the tight coupling of physics, communication and computation, a…

Empirical inference attacks are a popular approach for evaluating the privacy risk of data release mechanisms in practice. While an active attack literature exists to evaluate machine learning models or synthetic data release, we currently…

Cyber-physical systems (CPSs) are subjected to attacks on both cyber and physical spaces. In reality, the attackers could launch exponentially unbounded false data injection (EU-FDI) attacks, which are more destructive and could lead to the…

The effectiveness of Data Injections Attacks (DIAs) critically depends on the completeness of the system information accessible to adversaries. This relationship positions information incompleteness enhancement as a vital defense strategy…

Smart Grid has rapidly transformed the centrally controlled power system into a massively interconnected cyber-physical system that benefits from the revolutions happening in the communications (e.g. 5G) and the growing proliferation of the…

Recently, transformer architecture has demonstrated its significance in both Natural Language Processing (NLP) and Computer Vision (CV) tasks. Though other network models are known to be vulnerable to the backdoor attack, which embeds…

Intrusion detection system (IDS) is one of extensively used techniques in a network topology to safeguard the integrity and availability of sensitive assets in the protected systems. Although many supervised and unsupervised learning…

Transferability of adversarial examples is of central importance for attacking an unknown model, which facilitates adversarial attacks in more practical scenarios, e.g., black-box attacks. Existing transferable attacks tend to craft…

The wide acceptance of Internet of Things (IoT) for both household and industrial applications is accompanied by several security concerns. A major security concern is their probable abuse by adversaries towards their malicious intent.…

Trusted Execution Environments (TEEs) are critical components of modern secure computing, providing isolated zones in processors to safeguard sensitive data and execute secure operations. Despite their importance, TEEs are increasingly…

Critical infrastructure increasingly relies on interconnected cyber-physical systems whose security incidents can escalate rapidly into safety and operational failures. Existing decision-support approaches struggle to support real-time…

Observers for PDEs are themselves PDEs. Therefore, producing real time estimates with such observers is computationally burdensome. For both finite-dimensional and ODE systems, moving-horizon estimators (MHE) are operators whose output is…

Deep learning (DL) offers potential improvements throughout the CAD tool-flow, one promising application being lithographic hotspot detection. However, DL techniques have been shown to be especially vulnerable to inference and training time…

We present a high-fidelity Mixed Reality sensor emulation framework for testing and evaluating the resilience of Unmanned Aerial Vehicles (UAVs) against false data injection (FDI) attacks. The proposed approach can be utilized to assess the…

Attackers demonstrated the use of remote access to the in-vehicle network of connected vehicles to launch cyber-attacks and remotely take control of these vehicles. Machine-learning-based Intrusion Detection Systems (IDSs) techniques have…

Deploying autonomous systems in safety critical settings necessitates methods to verify their safety properties. This is challenging because real-world systems may be subject to disturbances that affect their performance, but are unknown a…