Related papers: JT-SAFE-V2: Safety-by-Design Foundation Model with…

We present Foundation-Sec-8B-Reasoning, the first open-source native reasoning model for cybersecurity. Built upon our previously released Foundation-Sec-8B base model (derived from Llama-3.1-8B-Base), the model is trained through a…

Large Language Models (LLMs) are attracting significant research attention due to their instruction-following abilities, allowing users and developers to leverage LLMs for a variety of tasks. However, LLMs are vulnerable to prompt-injection…

Long-term memory is crucial for agents in specialized web environments, where success depends on recalling interface affordances, state dynamics, workflows, and recurring failure modes. However, existing memory benchmarks for agents mostly…

Safety hazard identification and prevention are the key elements of proactive safety management. Previous research has extensively explored the applications of computer vision to automatically identify hazards from image clips collected…

Recent Vision-Language-Action (VLA) models equipped with Flow Matching (FM) action heads achieve state-of-the-art performance in complex robot manipulation. However, the multi-step iterative ODE solving required by FM introduces inference…

Ensuring safe and appropriate responses from vision-language models (VLMs) remains a critical challenge, particularly in high-risk or ambiguous scenarios. We introduce SafeCoT, a lightweight, interpretable framework that leverages…

Vision-Language Models (VLMs) have achieved impressive performance across a wide range of multimodal tasks, yet they often exhibit inconsistent behavior when faced with semantically equivalent inputs, undermining their reliability and…

Integrating large language models (LLMs) into robotic systems has revolutionised embodied artificial intelligence, enabling advanced decision-making and adaptability. However, ensuring reliability, encompassing both security against…

Recent advancements in large language models (LLMs) have accelerated progress toward artificial general intelligence, yet their potential to generate harmful content poses critical safety challenges. Existing alignment methods often…

Large language models (LLMs) have revolutionized natural language processing (NLP) by excelling at understanding and generating human-like text. However, their widespread deployment can be prohibitively expensive. SortedNet is a recent…

Balancing robust security with strong privacy guarantees is critical for Risk-Based Adaptive Authentication (RBA), particularly in decentralized settings. Federated Learning (FL) offers a promising solution by enabling collaborative risk…

As foundation models become more sophisticated, ensuring their trustworthiness becomes increasingly critical; yet, unlike text and image, the video modality still lacks comprehensive trustworthiness benchmarks. We introduce VMDT…

As robots become increasingly integrated into open-world, human-centered environments, their ability to interpret natural language instructions and adhere to safety constraints is critical for effective and trustworthy interaction. Existing…

Large Language Models (LLMs) exhibit considerable promise in financial applications; however, prevailing models frequently demonstrate limitations when confronted with scenarios that necessitate sophisticated reasoning capabilities,…

Rapidly evolving cyberattacks demand incident response systems that can autonomously learn and adapt to changing threats. Prior work has extensively explored the reinforcement learning approach, which involves learning response strategies…

Foundation models have attracted widespread attention across domains due to their powerful zero-shot classification capabilities. This work is motivated by two key observations: (1) \textit{Vision-Language Models} (VLMs), such as CLIP,…

We present a safety verification framework for design-time and run-time assurance of learning-based components in aviation systems. Our proposed framework integrates two novel methodologies. From the design-time assurance perspective, we…

Real-time threat monitoring identifies threatening behaviors in video streams and provides reasoning and assessment of threat events through explanatory text. However, prevailing methodologies, whether based on supervised learning or…

Communication stands as a potent mechanism to harmonize the behaviors of multiple agents. However, existing works primarily concentrate on broadcast communication, which not only lacks practicality, but also leads to information redundancy.…

Multi-modal threat detection faces a fundamental challenge that involves security tools operating in isolation, and this creates streams of network, email, and system data with no natural alignment or correlation. We present Hierarchical…