Related papers: Aetheria: A multimodal interpretable content safet…
We introduce MiRAGE, an evaluation framework for retrieval-augmented generation (RAG) from multimodal sources. As audiovisual media becomes a prevalent source of information online, it is essential for RAG systems to integrate information…
The popularisation of applying AI in businesses poses significant challenges relating to ethical principles, governance, and legal compliance. Although businesses have embedded AI into their day-to-day processes, they lack a unified…
When AI interacts with the physical world -- as a robot or an assistive agent -- new safety challenges emerge beyond those of purely ``digital AI". In such interactions, the potential for physical harm is direct and immediate. How well do…
While we have witnessed a rapid growth of ethics documents meant to guide AI development, the promotion of AI ethics has nonetheless proceeded with little input from AI practitioners themselves. Given the proliferation of AI for Social Good…
Memes are widely used for humor and cultural commentary, but they are increasingly exploited to spread hateful content. Due to their multimodal nature, hateful memes often evade traditional text-only or image-only detection systems,…
Decentralized communication is becoming an important use case within Web3. On Ethereum, users can repurpose the transaction input data field to embed natural-language messages, commonly known as Input Data Messages (IDMs). However, as IDMs…
With the rapid development of mobile intelligent assistant technologies, multi-modal AI assistants have become essential interfaces for daily user interactions. However, current evaluation methods face challenges including high manual…
With the rise of individual and collaborative networks of autonomous agents, AI is deployed in more key reasoning and decision-making roles. For this reason, ethics-based audits play a pivotal role in the rapidly growing fields of AI safety…
The rapid advances in Foundation Models and agentic Artificial Intelligence are transforming multimedia analytics by enabling richer, more sophisticated interactions between humans and analytical systems. Existing conceptual models for…
In order to develop machine learning and deep learning models that take into account the guidelines and principles of trustworthy AI, a novel information theoretic trustworthy AI framework is introduced. A unified approach to…
Effectiveness and interpretability are two essential properties for trustworthy AI systems. Most recent studies in visual reasoning are dedicated to improving the accuracy of predicted answers, and less attention is paid to explaining the…
The proliferation of autonomous AI agents marks a paradigm shift toward complex, emergent multi-agent systems. This transition introduces systemic security risks, including control-flow hijacking and cascading failures, that traditional…
Increasing interest in ensuring the safety of next-generation Artificial Intelligence (AI) systems calls for novel approaches to embedding morality into autonomous agents. This goal differs qualitatively from traditional task-specific AI…
It is well recognised that ensuring fair AI systems is a complex sociotechnical challenge, which requires careful deliberation and continuous oversight across all stages of a system's lifecycle, from defining requirements to model…
As autonomous systems such as drones, become increasingly deployed in high-stakes, human-centric domains, it is critical to evaluate the ethical alignment since failure to do so imposes imminent danger to human lives, and long term bias in…
While safety mechanisms have significantly progressed in filtering harmful text inputs, MLLMs remain vulnerable to multimodal jailbreaks that exploit their cross-modal reasoning capabilities. We present MIRAGE, a novel multimodal jailbreak…
Safety evaluation of multimodal foundation models often treats vision and language inputs separately, missing risks from joint interpretation where benign content becomes harmful in combination. Existing approaches also fail to distinguish…
Artificial Intelligence (AI) has significantly advanced in recent years, driving innovation across various fields, especially in robotics. Even though robots can perform complex tasks with increasing autonomy, challenges remain in ensuring…
Many intelligent transportation systems are multi-agent systems, i.e., both the traffic participants and the subsystems within the transportation infrastructure can be modeled as interacting agents. The use of AI-based methods to achieve…
Multiagent collaboration has emerged as a promising framework for enhancing the reasoning capabilities of large language models (LLMs). Despite improvements in reasoning, the approach introduces substantial computational overhead resulting…