Related papers: A Machine-learning based Probabilistic Perspective…

To cope with the increasing variability and sophistication of modern attacks, machine learning has been widely adopted as a statistically-sound tool for malware detection. However, its security against well-crafted attacks has not only been…

Dynamic contingency screening is a challenging task in dynamic security assessment, when traditional numerical approaches are computationally intensive and often not able to repeatedly solve full AC power flow for all possible contingencies…

In this article I describe a research agenda for securing machine learning models against adversarial inputs at test time. This article does not present results but instead shares some of my thoughts about where I think that the field needs…

Discovering potential failures of an autonomous system is important prior to deployment. Falsification-based methods are often used to assess the safety of such systems, but the cost of running many accurate simulation can be high. The…

Machine learning algorithms with empirical risk minimization are vulnerable under distributional shifts due to the greedy adoption of all the correlations found in training data. Recently, there are robust learning methods aiming at this…

All of the frontier AI companies have published safety frameworks where they define capability thresholds and risk mitigations that determine how they will safely develop and deploy their models. Adoption of systematic approaches to risk…

Machine learning (ML) has recently created many new success stories. Hence, there is a strong motivation to use ML technology in software-intensive systems, including safety-critical systems. This raises the issue of safety verification of…

In security-sensitive applications, the success of machine learning depends on a thorough vetting of their resistance to adversarial data. In one pertinent, well-motivated attack scenario, an adversary may attempt to evade a deployed system…

Motivated by the need to secure cyber-physical systems against attacks, we consider the problem of estimating the state of a noisy linear dynamical system when a subset of sensors is arbitrarily corrupted by an adversary. We propose a…

Probability Quantification (PQ) predictions of the efficacy of safety-critical protective systems is challenging. Yet, the popularity of PQ methodologies (e.g., Probabilistic Risk Assessment (PRA), Quantitative Risk Analysis (QRA) and…

Identifying and mitigating safety risks is paramount in a number of industries. In addition to guidelines and best practices, many industries already have safety management systems (SMSs) designed to monitor and reinforce good safety…

Approaches to keeping a dynamical system within state constraints typically rely on a model-based safety condition to limit the control signals. In the face of significant modeling uncertainty, the system can suffer from important…

Learning-based methodologies increasingly find applications in safety-critical domains like autonomous driving and medical robotics. Due to the rare nature of dangerous events, real-world testing is prohibitively expensive and unscalable.…

Autonomous Cyber-Physical Systems must often operate under uncertainties like sensor degradation and shifts in the operating conditions, which increases its operational risk. Dynamic Assurance of these systems requires designing runtime…

Machine learning (ML) systems are increasingly deployed in high-stakes domains where reliability is paramount. This thesis investigates how uncertainty estimation can enhance the safety and trustworthiness of ML, focusing on selective…

The emerging wide area monitoring systems (WAMS) have brought significant improvements in electric grids' situational awareness. However, the newly introduced system can potentially increase the risk of cyber-attacks, which may be disguised…

Safety analysis is used to identify hazards and build knowledge during the design phase of safety-relevant functions. This is especially true for complex AI-enabled and software intensive systems such as Autonomous Drive (AD).…

In this paper we propose a framework for assessing the risk associated with deploying a machine learning model in a specified environment. For that we carry over the risk definition from decision theory to machine learning. We develop and…

Machine learning (ML) components are increasingly integrated into software products, yet their complexity and inherent uncertainty often lead to unintended and hazardous consequences, both for individuals and society at large. Despite these…

Robust planning in interactive scenarios requires predicting the uncertain future to make risk-aware decisions. Unfortunately, due to long-tail safety-critical events, the risk is often under-estimated by finite-sampling approximations of…