Related papers: SENTINEL: A Multi-Level Formal Framework for Safet…
Effectively translating between natural language (NL) and formal logics like Linear Temporal Logic (LTL) requires expertise that limits formal verification's reach in safety-critical development. Template-based approaches sacrifice…
Multimodal foundation models offer a promising framework for robotic perception and planning by processing sensory inputs to generate actionable plans. However, addressing uncertainty in both perception (sensory interpretation) and…
Multimodal large language models (MLLMs) have revolutionized cross-modal understanding but continue to struggle with hallucinations - fabricated content contradicting visual inputs. Existing hallucination mitigation methods either incur…
We present Semantic Fusion (SF), a formal framework for decentralized semantic coordination in multi-agent systems. SF allows agents to operate over scoped views of shared memory, propose structured updates, and maintain global coherence…
Most safety testing efforts for large language models (LLMs) today focus on evaluating foundation models. However, there is a growing need to evaluate safety at the application level, as components such as system prompts, retrieval…
This paper presents CPEMH, an agentic framework designed to evaluate prompt-driven behavior in foundation-model systems operating on transcript-based datasets for mental-health screening. CPEMH serves as an engineering methodology for…
We introduce SENT-Map, a semantically enhanced topological map for representing indoor environments, designed to support autonomous navigation and manipulation by leveraging advancements in foundational models (FMs). Through representing…
The integration of vision-language models (VLMs) is driving a new generation of embodied agents capable of operating in human-centered environments. However, as deployment expands, these systems face growing safety risks, particularly when…
Flawed planning from VLM-driven embodied agents poses significant safety hazards, hindering their deployment in real-world household tasks. However, existing static, non-interactive evaluation paradigms fail to adequately assess risks…
Formal methods provide very powerful tools and techniques for the design and analysis of complex systems. Their practical application remains however limited, due to the widely accepted belief that formal methods require extensive expertise…
The scarcity of data depicting dangerous situations presents a major obstacle to training AI systems for safety-critical applications, such as construction safety, where ethical and logistical barriers hinder real-world data collection.…
We introduce a framework for Foundational Analysis of Safety Engineering Requirements (SAFER), a model-driven methodology supported by Generative AI to improve the generation and analysis of safety requirements for complex safety-critical…
Recent intelligent systems integrate powerful Large Language Models (LLMs) through APIs, but their trustworthiness may be critically undermined by targeted attacks like backdoor and prompt injection attacks, which secretly force LLMs to…
Service-oriented sensor-actuator networks (SOSANETs) are deployed in health-critical applications like patient monitoring and have to fulfill strong safety requirements. However, a framework for the rigorous formal modeling and analysis of…
This paper introduces a dynamic and actionable framework for securing agentic AI systems in enterprise deployment. We contend that safety and security are not merely fixed attributes of individual models but also emergent properties arising…
Semantic information in embodied AI is inherently multi-source and multi-stage, making it challenging to fully leverage for achieving stable perception-to-action loops in real-world environments. Early studies have combined manual…
Control applications present hard operational constraints. A violation of these can result in unsafe behavior. This paper introduces Safe Interactive Model Based Learning (SiMBL), a framework to refine an existing controller and a system…
Embodied artificial intelligence (EAI) integrates advanced AI models into physical entities for real-world interaction. The emergence of foundation models as the "brain" of EAI agents for high-level task planning has shown promising…
Financial agents powered by large language models (LLMs) are increasingly deployed for investment analysis, risk assessment, and automated decision-making, where their abilities to plan, invoke tools, and manipulate mutable state introduce…
Large Language Models (LLMs) have become increasingly vulnerable to jailbreak attacks that circumvent their safety mechanisms. While existing defense methods either suffer from adaptive attacks or require computationally expensive auxiliary…