Related papers: Certificate-Aware Property-Directed Reachability
By using small computing devices deployed at user premises, Autonomous Demand Response (ADR) adapts users electricity consumption to given time-dependent electricity tariffs. This allows end-users to save on their electricity bill and…
Constrained devices, such as smart sensors, wearable devices, and Internet of Things nodes, are increasingly prevalent in society and rely on secure communications to function properly. These devices often operate autonomously, exchanging…
Certification for machine learning is proving that no adversarial sample can evade a model within a range under certain conditions, a necessity for safety-critical domains. Common certification methods for segmentation use a flat set of…
True zero-copy Inter-Process Communication (IPC) in publish/subscribe (pub/sub) middleware such as Robot Operating System 2 (ROS 2) requires subscribers to reference message objects in publisher-owned shared memory. Objects must not be…
Reachability computations that rely on learned or estimated models require calibration in order to uphold confidence about their guarantees. Calibration generally involves sampling scenarios inside the reachable set. However, producing…
As a result of the ever-increasing application of cyber-physical components in the automotive industry, cybersecurity has become an urgent topic. Adapting technologies and communication protocols like Ethernet and WiFi in connected vehicles…
We develop a flexible feature selection framework based on deep neural networks that approximately controls the false discovery rate (FDR), a measure of Type-I error. The method applies to architectures whose first layer is fully connected.…
To provide safety guarantees for learning-based control systems, recent work has developed formal verification methods to apply after training ends. However, if the trained policy does not meet the specifications, or there is conservatism…
State-of-the-art defenses against adversarial patch attacks can now achieve strong certifiable robustness with a marginal drop in model utility. However, this impressive performance typically comes at the cost of 10-100x more inference-time…
The IC3 algorithm, also known as PDR, has made a significant impact in the field of safety model checking in recent years due to its high efficiency, scalability, and completeness. The most crucial component of IC3 is inductive…
The screening of baggage using X-ray scanners is now routine in aviation security with automatic threat detection approaches, based on 3D X-ray computed tomography (CT) images, known as Automatic Threat Recognition (ATR) within the aviation…
Large language models (LLMs) are increasingly used to assist developers with code, yet their implementations of cryptographic functionality often contain exploitable flaws. Minor design choices (e.g., static initialization vectors or…
AI deployment in sensitive domains such as health care, credit, employment, and criminal justice is often treated as unsafe to authorize until model internals can be explained. This often leads to an excessive reliance on mechanistic…
We give an incremental, inductive (IC3) procedure to check coverability of well-structured transition systems. Our procedure generalizes the IC3 procedure for safety verification that has been successfully applied in finite-state hardware…
This paper studies the distributed conditional feature screening for massive data with ultrahigh-dimensional features. Specifically, three distributed partial correlation feature screening methods (SAPS, ACPS and JDPS methods) are firstly…
Integrating an automated driving software stack into vehicles with variable configuration is challenging, especially due to different hardware characteristics. Further, to provide software updates to a vehicle fleet in the field, the…
Hyperdimensional computing (HDC) has become popular for light-weight and energy-efficient machine learning, suitable for wearable Internet-of-Things (IoT) devices and near-sensor or on-device processing. HDC is computationally less complex…
The hardware security community relies on databases of known vulnerabilities and open-source designs to develop formal verification methods for identifying hardware security flaws. While there are plenty of open-source designs and…
Automatic security inspection relying on computer vision technology is a challenging task in real-world scenarios due to many factors, such as intra-class variance, class imbalance, and occlusion. Most previous methods rarely touch the…
Differentially private multiple testing procedures can protect the information of individuals used in hypothesis tests while guaranteeing a small fraction of false discoveries. In this paper, we propose a differentially private adaptive FDR…