相关论文: BarrierSteer: LLM Safety via Learning Barrier Stee…

This paper considers the safety-critical navigation problem with Signal Temporal Logic (STL) tasks. We developed an explicit reference governor-guided control barrier function (ERG-guided CBF) method that enables the application of…

Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks. To mitigate these risks, existing detection methods are essential, yet they face two major challenges: generalization and…

Despite the intrinsic risk-awareness of Large Language Models (LLMs), current defenses often result in shallow safety alignment, rendering models vulnerable to disguised attacks (e.g., prefilling) while degrading utility. To bridge this…

Safety filters based on control barrier functions (CBFs) have become a popular method to guarantee safety for uncertified control policies, e.g., as resulting from reinforcement learning. Here, safety is defined as staying in a pre-defined…

The advent of Large Language Models (LLMs) has marked significant achievements in language processing and reasoning capabilities. Despite their advancements, LLMs face vulnerabilities to data poisoning attacks, where the adversary inserts…

Safety for Large Language Models (LLMs) has been an ongoing research focus since their emergence and is even more relevant nowadays with the increasing capacity of those models. Currently, there are several guardrails in place for all…

Safety has been a critical issue for the deployment of learning-based approaches in real-world applications. To address this issue, control barrier function (CBF) and its variants have attracted extensive attention for safety-critical…

Large Language Models (LLMs) are vulnerable to adversarial attacks that bypass safety guidelines and generate harmful content. Mitigating these vulnerabilities requires defense mechanisms that are both robust and computationally efficient.…

The ability of large language models (LLMs) to follow instructions is crucial to real-world applications. Despite recent advances, several studies have highlighted that LLMs struggle when faced with challenging instructions, especially…

Safety is one of the fundamental problems in robotics. Recently, one-step or multi-step optimal control problems for discrete-time nonlinear dynamical system were formulated to offer tracking stability using control Lyapunov functions…

With the widespread application of Large Language Models across various domains, their security issues have increasingly garnered significant attention from both academic and industrial communities. This study conducts sampling and…

We study the problem of co-designing control barrier functions (CBF) and linear state feedback controllers for continuous-time linear systems. We achieve this by means of a single semi-definite optimization program. Our formulation can…

Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks, posing serious safety risks. To address this, existing detection methods either learn attack-specific parameters, which…

Control Barrier Functions (CBF) have been recently utilized in the design of provably safe feedback control laws for nonlinear systems. These feedback control methods typically compute the next control input by solving an online Quadratic…

In the current cybersecurity landscape, protecting military devices such as communication and battlefield management systems against sophisticated cyber attacks is crucial. Malware exploits vulnerabilities through stealth methods, often…

Merely pursuing performance may adversely affect the safety, while a conservative policy for safe exploration will degrade the performance. How to balance the safety and performance in learning-based control problems is an interesting yet…

Large Language Models (LLMs) are increasingly integrated into educational applications. However, they remain vulnerable to jailbreak and fine-tuning attacks, which can compromise safety alignment and lead to harmful outputs. Existing…

This tutorial paper presents recent work of the authors that extends the theory of Control Barrier Functions (CBFs) to address practical challenges in the synthesis of safe controllers for autonomous systems and robots. We present novel…

While Large Language Models (LLMs) demonstrate exceptional performance in surface-level text generation, their nature in handling complex multi-step reasoning tasks often remains one of ``statistical fitting'' rather than systematic logical…

Automated unit test generation using large language models (LLMs) holds great promise but often struggles with generating tests that are both correct and maintainable in real-world projects. This paper presents KTester, a novel framework…