Related papers: Design Didn't Prevent These Hazard Exposures
Safety and assurance standards often rely on the principle that requirements errors can be minimised by expressing the requirements more formally. Although numerous case studies have shown that the act of formalising previously informal…
Workarounds enable users to achieve goals despite system limitations but expose design flaws, reduce productivity, risk compromising data quality, and cause inconsistencies. This study investigates how users employ workarounds when the data…
Organizations struggle to comply with legal requirements as well as customers calls for better data protection. On the implementation level, incorporation of privacy protections in products and services depends on the commitment of the…
This chapter presents an overview of Prosocial Design, an approach to platform design and governance that recognizes design choices influence behavior and that those choices can or should be made toward supporting healthy interactions and…
Electronic Design Automation (EDA) industry heavily reuses third party IP cores. These IP cores are vulnerable to insertion of Hardware Trojans (HTs) at design time by third party IP core providers or by malicious insiders in the design…
We study the design of mechanisms -- e.g., auctions -- when the designer does not control information flows between mechanism participants. A mechanism equilibrium is leakage-proof if no player conditions their actions on leaked…
Advances in machine learning have led to broad deployment of systems with impressive performance on important problems. Nonetheless, these systems can be induced to make errors on data that are surprisingly similar to examples the learned…
Many Security Operations Centers (SOCs) today still heavily rely on signature-based Network Intrusion Detection Systems (NIDS) such as Suricata. The specificity of intrusion detection rules and the coverage provided by rulesets are common…
AI systems have become increasingly capable of dangerous behaviours in many domains. This raises the question: Do models sometimes choose to violate human instructions in order to perform behaviour that is more useful for certain goals? We…
Environmentally assisted cracking phenomena are widespread across the transport, defence, energy and construction sectors. However, predicting environmentally assisted fractures is a highly cross-disciplinary endeavour that requires…
Human-centered design, a theoretical ideal, is sometimes compromised in industry practice. Technology firms juggle competing priorities, such as adopting new technologies and generating shareholder returns, which may conflict with…
We introduce a novel simulation-based approach to identify hazards that result from unexpected worker behavior in human-robot collaboration. Simulation-based safety testing must take into account the fact that human behavior is variable and…
Experience-driven self-evolution has emerged as a promising paradigm for improving the autonomy of large language model agents, yet its reliance on self-curated experience introduces underexplored safety risks. In this study, we investigate…
Machine learning algorithms are everywhere, ranging from simple data analysis and pattern recognition tools used across the sciences to complex systems that achieve super-human performance on various tasks. Ensuring that they are…
How can we design safe reinforcement learning agents that avoid unnecessary disruptions to their environment? We show that current approaches to penalizing side effects can introduce bad incentives, e.g. to prevent any irreversible changes…
Recent attacks on power grids demonstrated the vulnerability of the grids to cyber and physical attacks. To analyze this vulnerability, we study cyber-physical attacks that affect both the power grid physical infrastructure and its…
We systematically evaluate the quality of widely used adversarial safety datasets from two perspectives: in isolation and in practice. In isolation, we examine how well these datasets reflect real-world adversarial attacks based on three…
Increased interconnectivity of Cyber-Physical Systems, by design or otherwise, increases the cyber attack surface and attack vectors. Observing the effects of these attacks is helpful in detecting them. In this paper, we show that many…
Context: Today's safety critical systems are increasingly reliant on software. Software becomes responsible for most of the critical functions of systems. Many different safety analysis techniques have been developed to identify hazards of…
Safety is an important element of dependability. It is defined as the absence of accidents. Most accidents involving software-intensive systems have been system accidents, which are caused by unsafe inter-system or inter-component…