Related papers: SpecGuard: Specification Aware Recovery for Roboti…

Reinforcement learning (RL) agents with pre-specified reward functions cannot provide guaranteed safety across variety of circumstances that an uncertain system might encounter. To guarantee performance while assuring satisfaction of safety…

Autonomous vehicles (AVs) rely on the Global Positioning System (GPS) or Global Navigation Satellite Systems (GNSS) for precise (Positioning, Navigation, and Timing) PNT solutions. However, the vulnerability of GPS signals to intentional…

Retrieval-Augmented Generation (RAG) significantly mitigates the hallucinations and domain knowledge deficiency in large language models by incorporating external knowledge bases. However, the multi-module architecture of RAG introduces…

A runtime assurance system (RTA) for a given plant enables the exercise of an untrusted or experimental controller while assuring safety with a backup (or safety) controller. The relevant computational design problem is to create a logic…

Safety is a crucial property of every robotic platform: any control policy should always comply with actuator limits and avoid collisions with the environment and humans. In reinforcement learning, safety is even more fundamental for…

Reinforcement learning (RL) for robotics is challenging due to the difficulty in hand-engineering a dense cost function, which can lead to unintended behavior, and dynamical uncertainty, which makes exploration and constraint satisfaction…

Anomaly Detection (AD) and Anomaly Localization (AL) are crucial in fields that demand high reliability, such as medical imaging and industrial monitoring. However, current AD and AL approaches are often susceptible to adversarial attacks…

The growing advancements in Autonomous Vehicles (AVs) have emphasized the critical need to prioritize the absolute safety of AV maneuvers, especially in dynamic and unpredictable environments or situations. This objective becomes even more…

Fine-tuning large language models (LLMs) for downstream tasks typically exhibit a fundamental safety-capability tradeoff, where improving task performance degrades safety alignment even on benign datasets. This degradation persists across…

Autonomous vehicles are increasingly deployed in safety-critical applications, where sensing failures or cyberphysical attacks can lead to unsafe operations resulting in human loss and/or severe physical damages. Reliable real-time…

Graph-based retrieval-augmented generation (Graph RAG) is increasingly deployed to support LLM applications by augmenting user queries with structured knowledge retrieved from a knowledge graph. While Graph RAG improves relational…

Autonomous driving has the potential to revolutionize mobility and is hence an active area of research. In practice, the behavior of autonomous vehicles must be acceptable, i.e., efficient, safe, and interpretable. While vanilla…

Unmanned Aerial Vehicles (UAVs) rely on measurements from Inertial Measurement Units (IMUs) to maintain stable flight. However, IMUs are susceptible to physical attacks, including acoustic resonant and electromagnetic interference attacks,…

Large Reasoning Models possess remarkable capabilities for self-correction in general domain; however, they frequently struggle to recover from unsafe reasoning trajectories under adversarial attacks. Existing alignment methods attempt to…

A significant barrier to deploying autonomous vehicles (AVs) on a massive scale is safety assurance. Several technical challenges arise due to the uncertain environment in which AVs operate such as road and weather conditions, errors in…

The emergence of Large Reasoning Models (LRMs) introduces a new paradigm of explicit reasoning, enabling remarkable advances yet posing unique risks such as reasoning manipulation and information leakage. To mitigate these risks, current…

Vision-Language-Action (VLA) models enable robots to interpret natural-language instructions and perform diverse tasks, yet their integration of perception, language, and control introduces new safety vulnerabilities. Despite growing…

Safe reinforcement learning (Safe RL) seeks to maximize rewards while satisfying safety constraints, typically addressed through Lagrangian-based methods. However, existing approaches, including PID and classical Lagrangian methods, suffer…

Fine-tuning large language models often undermines their safety alignment, a problem further amplified by harmful fine-tuning attacks in which adversarial data removes safeguards and induces unsafe behaviors. We propose SPARD, a defense…

The tremendous excitement around the deployment of autonomous vehicles (AVs) comes from their purported promise. In addition to decreasing accidents, AVs are projected to usher in a new era of equity in human autonomy by providing…