Related papers: BarrierSteer: LLM Safety via Learning Barrier Stee…

This paper proposes a control-based framework for aligning large language models (LLMs) by leveraging a control barrier function (CBF) to ensure user-desirable text generation. The presented framework applies the safety filter, designed…

Large Language Models (LLMs) have emerged as powerful tools, but their inherent safety risks - ranging from harmful content generation to broader societal harms - pose significant challenges. These risks can be amplified by the recent…

Safety is a fundamental requirement for autonomous systems operating in critical domains. Control barrier functions (CBFs) have been used to design safety filters that minimally alter nominal controls for such systems to maintain their…

Reinforcement Learning (RL) algorithms have found limited success beyond simulated applications, and one main reason is the absence of safety guarantees during the learning process. Real world systems would realistically fail or break…

With the rapid development of large language models (LLMs), they are not only used as general-purpose AI assistants but are also customized through further fine-tuning to meet the requirements of different applications. A pivotal factor in…

Control Barrier Functions (CBFs) provide a powerful framework for ensuring safety in dynamical systems. However, their application typically relies on full state information, which is often violated in real-world due to the availability of…

Recent advances in Large Language Models (LLMs) have demonstrated remarkable progress in their reasoning capabilities, such as Chain-of-Thought (CoT). Most approaches rely on CoT rationales. Previous studies have shown that LLMs often…

Large Language Models (LLMs) with safe-alignment training are powerful instruments with robust language comprehension capabilities. These models typically undergo meticulous alignment procedures involving human feedback to ensure the…

Large Language Models (LLMs) achieve remarkable performance through pretraining on extensive data. This enables efficient adaptation to diverse downstream tasks. However, the lack of interpretability in their underlying mechanisms limits…

Control barrier functions (CBFs) are widely used in safety-critical controllers. However, constructing a valid CBF is challenging, especially under nonlinear or non-convex constraints and for high relative degree systems. Meanwhile, finding…

As large language models (LLMs) become integral to various applications, ensuring both their safety and utility is paramount. Jailbreak attacks, which manipulate LLMs into generating harmful content, pose significant challenges to this…

Safety filters leveraging control barrier functions (CBFs) are highly effective for enforcing safe behavior on complex systems. It is often easier to synthesize CBFs for a Reduced order Model (RoM), and track the resulting safe behavior on…

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

Obstacle avoidance is central to safe navigation, especially for robots with arbitrary and nonconvex geometries operating in cluttered environments. Existing Control Barrier Function (CBF) approaches often rely on analytic clearance…

We propose new methods to synthesize control barrier function (CBF)-based safe controllers that avoid input saturation, which can cause safety violations. In particular, our method is created for high-dimensional, general nonlinear systems,…

Control barrier function (CBF) has recently started to serve as a basis to develop approaches for enforcing safety requirements in control systems. However, constructing such function for a general system is a non-trivial task. This paper…

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to adversarial manipulations such as jailbreaking via prompt injection attacks. These attacks bypass safety mechanisms…

MLLMs are increasingly deployed in multi-turn settings, where attackers can escalate unsafe intent through the evolving visual-text history and exploit long-context safety decay. Yet safety alignment is still dominated by single-turn data…

Reinforcement learning (RL), while powerful and expressive, can often prioritize performance at the expense of safety. Yet safety violations can lead to catastrophic outcomes in real-world deployments. Control Barrier Functions (CBFs) offer…

This paper introduces a predictive control barrier function (PCBF) framework for enforcing state constraints in discrete-time systems with unknown relative degree, which can be caused by input delays or unmodeled input dynamics. Existing…