相关论文: STARS: Skill-Triggered Audit for Request-Condition…
Formally verifying audio classification systems is essential to ensure accurate signal classification across real-world applications like surveillance, automotive voice commands, and multimedia content management, preventing potential…
Service robots must retrieve objects in dynamic, open-world settings where requests may reference attributes ("the red mug"), spatial context ("the mug on the table"), or past states ("the mug that was here yesterday"). Existing approaches…
In safety-critical robotic tasks, potential failures must be reduced, and multiple constraints must be met, such as avoiding collisions, limiting energy consumption, and maintaining balance. Thus, applying safe reinforcement learning (RL)…
We introduce a new paradigm for task-oriented dialogue systems: safety certification as a computational primitive for answer reuse. Current systems treat each turn independently, recomputing answers via retrieval or generation even when…
AI agents that interact with the real world through tool calls pose fundamental safety challenges: agents might leak private information, cause unintended side effects, or be manipulated through prompt injection. To address these…
Static analysers search for overapproximating proofs of safety commonly known as safety invariants. Fundamentally, such analysers summarise traces into sets of states, thus trading the ability to distinguish traces for computational…
We investigate the important problem of certifying stability of reinforcement learning policies when interconnected with nonlinear dynamical systems. We show that by regulating the input-output gradients of policies, strong guarantees of…
Goal-directed evaluation of Answer Set Programs is gaining traction thanks to its amenability to create AI systems that can, due to the evaluation mechanism used, generate explanations and justifications. s(CASP) is one of these systems and…
Recent progress in diffusion-based audio generation and restoration has substantially improved performance across heterogeneous conditioning regimes, including text-conditioned audio generation and audio-conditioned super-resolution.…
Reinforcement learning has empowered large language models to act as intelligent agents, yet training them for long-horizon tasks remains challenging due to the scarcity of high-quality trajectories, especially under limited resources.…
Cyber-physical systems (CPSs) in modern real-time applications integrate numerous control units linked through communication networks, each responsible for executing a mix of real-time safety-critical and non-critical tasks. To ensure…
Software is prone to security vulnerabilities. Program analysis tools to detect them have limited effectiveness in practice due to their reliance on human labeled specifications. Large language models (or LLMs) have shown impressive code…
Language agents have become a promising solution to complex interactive tasks. One of the key ingredients to the success of language agents is the reward model on the trajectory of the agentic workflow, which provides valuable guidance…
Ensuring string stability is critical for the safety and efficiency of large-scale interconnected systems. Although learning-based controllers (e.g., those based on reinforcement learning) have demonstrated strong performance in complex…
A persistent skill library allows language model agents to reuse successful strategies across tasks. Maintaining such a library requires three coupled capabilities. The agent selects a relevant skill, utilizes it during execution, and…
Auditing plays a pivotal role in the development of trustworthy AI. However, current research primarily focuses on creating auditable AI documentation, which is intended for regulators and experts rather than end-users affected by AI…
Security orchestration, automation, and response (SOAR) systems ingest alerts from security information and event management (SIEM) system, and then trigger relevant playbooks that automate and orchestrate the execution of a sequence of…
The advent of multimodal agents facilitates effective interaction within graphical user interface (GUI), especially in ubiquitous GUI control. However, their inability to reliably execute toggle control instructions remains a key…
Modern large language models integrate web search to provide real-time answers, yet it remains unclear whether they are efficiently calibrated to use search when it is actually needed. We introduce a benchmark evaluating both the necessity…
Intrusion detection is a long standing and crucial problem in security. A system capable of detecting intrusions automatically is on great demand in enterprise security solutions. Existing solutions rely heavily on hand-crafted rules…