相关论文: Safety design concepts for statistical machine lea…

Many stakeholders struggle to make reliances on ML-driven systems due to the risk of harm these systems may cause. Concerns of trustworthiness, unintended social harms, and unacceptable social and ethical violations undermine the promise of…

High-accurate machine learning (ML) image classifiers cannot guarantee that they will not fail at operation. Thus, their deployment in safety-critical applications such as autonomous vehicles is still an open issue. The use of fault…

The increasing use of Machine Learning (ML) components embedded in autonomous systems -- so-called Learning-Enabled Systems (LESs) -- has resulted in the pressing need to assure their functional safety. As for traditional functional safety,…

Enforcing security requirements in networked information systems relies on security controls to mitigate the risks from increasingly dangerous threats. Configuring security controls is challenging; even nowadays, administrators must perform…

Machine learning (ML) provides us with numerous opportunities, allowing ML systems to adapt to new situations and contexts. At the same time, this adaptability raises uncertainties concerning the run-time product quality or dependability,…

Autonomous systems with machine learning-based perception can exhibit unpredictable behaviors that are difficult to quantify, let alone verify. Such behaviors are convenient to capture in probabilistic models, but probabilistic model…

Identifying potential social and ethical risks in emerging machine learning (ML) models and their applications remains challenging. In this work, we applied two well-established safety engineering frameworks (FMEA, STPA) to a case study…

In this paper, we consider the problem of synthesizing a controller in the presence of uncertainty such that the resulting closed-loop system satisfies certain hard constraints while optimizing certain (soft) performance objectives. We…

Multimodal large language models (MLLMs) enable interaction over both text and images, but their safety behavior can be driven by unimodal shortcuts instead of true joint intent understanding. We introduce CSR-Bench, a benchmark for…

The development and deployment of machine learning (ML) systems can be executed easily with modern tools, but the process is typically rushed and means-to-an-end. The lack of diligence can lead to technical debt, scope creep and misaligned…

Machine Learning (ML) is now used in a range of systems with results that are reported to exceed, under certain conditions, human performance. Many of these systems, in domains such as healthcare , automotive and manufacturing, exhibit high…

While the applications and demands of Machine learning (ML) systems in mental health are growing, there is little discussion nor consensus regarding a uniquely challenging aspect: building security methods and requirements into these ML…

This paper proposes the development of a Large Language Model (LLM) based machine learning classifier designed to categorize Station Condition Records (SCRs) at nuclear power stations into safety-related and non-safety-related categories.…

The real-world use cases of Machine Learning (ML) have exploded over the past few years. However, the current computing infrastructure is insufficient to support all real-world applications and scenarios. Apart from high efficiency…

While it has been repeatedly shown that learning-based controllers can provide superior performance, they often lack of safety guarantees. This paper aims at addressing this problem by introducing a model predictive safety certification…

Simulation platforms facilitate the development of emerging Cyber-Physical Systems (CPS) like self-driving cars (SDC) because they are more efficient and less dangerous than field operational test cases. Despite this, thoroughly testing…

As machine learning (ML) systems increasingly permeate high-stakes settings such as healthcare, transportation, military, and national security, concerns regarding their reliability have emerged. Despite notable progress, the performance of…

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…

Within the context of autonomous driving, safety-related metrics for deep neural networks have been widely studied for image classification and object detection. In this paper, we further consider safety-aware correctness and robustness…

Semi-supervised learning (SSL) is a class of supervised learning tasks and techniques that also exploits the unlabeled data for training. SSL significantly reduces labeling related costs and is able to handle large data sets. The primary…