Related papers: A new hazard event classification model via deep l…
Harmful fine-tuning (HFT), performed directly on open-source LLMs or through Fine-tuning-as-a-Service, breaks safety alignment and poses significant threats. Existing methods aim to mitigate HFT risks by learning robust representation on…
Safety is a critical aspect of the air transport system given even slight operational anomalies can result in serious consequences. To reduce the chances of aviation safety occurrences, accidents and incidents are reported to establish the…
This paper presents a novel holistic deep learning framework that simultaneously addresses the challenges of vulnerability to input perturbations, overparametrization, and performance instability from different train-validation splits. The…
Despite achieving excellent performance on benchmarks, deep neural networks often underperform in real-world deployment due to sensitivity to minor, often imperceptible shifts in input data, known as distributional shifts. These shifts are…
In this paper, a high-speed online neural network classifier based on extreme learning machines for multi-label classification is proposed. In multi-label classification, each of the input data sample belongs to one or more than one of the…
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…
Multivariate time series anomaly detection has become an active area of research in recent years, with Deep Learning models outperforming previous approaches on benchmark datasets. Among reconstruction-based models, most previous work has…
Road-safety inspection is an indispensable instrument for reducing road-accident fatalities contributed to road infrastructure. Recent work formalizes road-safety assessment in terms of carefully selected risk factors that are also known as…
Semantic segmentation of histopathology images under class imbalance is typically addressed through frequency-based loss reweighting, which implicitly assumes that rare classes are difficult. However, true difficulty also arises from…
Haze and dust pollution events have significant adverse impacts on human health and ecosystems. Their formation-impact interactions are complex, creating substantial modeling and computational challenges for joint classification. To address…
While existing hierarchical text classification (HTC) methods attempt to capture label hierarchies for model training, they either make local decisions regarding each label or completely ignore the hierarchy information during inference. To…
Data-driven susceptibility mapping of natural hazards has harnessed the advances in classification methods used on heterogeneous sources represented as raster images. Susceptibility mapping is an important step towards risk assessment for…
Safety has become of paramount importance in the development lifecycle of the modern automobile systems. However, the current automotive safety standard ISO 26262 does not specify clearly the methods for safety analysis. Different methods…
Lifelong learning aims to preserve knowledge acquired from previous tasks while incorporating knowledge from a sequence of new tasks. However, most prior work explores only streams of homogeneous tasks (\textit{e.g.}, only classification…
Directed Grey-box Fuzzing (DGF) has emerged as a widely adopted technique for crash reproduction and patch testing, leveraging its capability to precisely navigate toward target locations and exploit vulnerabilities. However, current DGF…
Predictions of thunderstorm-related hazards are needed in several sectors, including first responders, infrastructure management and aviation. To address this need, we present a deep learning model that can be adapted to different hazard…
Diarrhetic Shellfish Poisoning (DSP) is a global health threat arising from shellfish contaminated with toxins produced by dinoflagellates. The condition, with its widespread incidence, high morbidity rate, and persistent shellfish…
Earthquake science and seismology rely on the ability to associate seismic waves with their originating earthquakes. Earthquake detection algorithms based on deep learning have progressed rapidly and now routinely detect microearthquakes…
Bayesian decision theory advocates the Bayes classifier as the optimal approach for minimizing the risk in machine learning problems. Current deep learning algorithms usually solve for the optimal classifier by \emph{implicitly} estimating…
As systems become increasingly complex, conducting effective safety analysis in the earlier phases of a system's lifecycle is essential to identify and mitigate risks before they escalate. To that end, this paper investigates the…