English
Related papers

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

200 papers

Large Language Models (LLMs) are increasingly deployed for code generation in high-stakes software development, yet their limited transparency in security reasoning and brittleness to evolving vulnerability patterns raise critical…

Software Engineering · Computer Science 2026-03-03 Manisha Mukherjee , Vincent J. Hellendoorn

Research into AI alignment has grown considerably since the recent introduction of increasingly capable Large Language Models (LLMs). Unfortunately, modern methods of alignment still fail to fully prevent harmful responses when models are…

Cryptography and Security · Computer Science 2024-08-20 Matthew Pisano , Peter Ly , Abraham Sanders , Bingsheng Yao , Dakuo Wang , Tomek Strzalkowski , Mei Si

This paper addresses the target-pursuit problem, aiming to ensure each pursuer's safety regarding collision avoidance, sensing range, and input saturation. An input-constrained CBF is proposed to dynamically regulate the pursuer's control,…

Systems and Control · Electrical Eng. & Systems 2024-12-11 Yaosheng Deng , Junjie Gao , Jiaping Xiao , Mir Feroskhan

Hybrid dynamical systems are ubiquitous as practical robotic applications often involve both continuous states and discrete switchings. Safety is a primary concern for hybrid robotic systems. Existing safety-critical control approaches for…

Robotics · Computer Science 2024-12-02 Shuo Yang , Yu Chen , Xiang Yin , George J. Pappas , Rahul Mangharam

Multimodal Large Reasoning Models (MLRMs) demonstrate impressive cross-modal reasoning but often amplify safety risks under adversarial or unsafe prompts, a phenomenon we call the \textit{Reasoning Tax}. Existing defenses mainly act at the…

Machine Learning · Computer Science 2025-10-10 Huahui Yi , Kun Wang , Qiankun Li , Miao Yu , Liang Lin , Gongli Xi , Hao Wu , Xuming Hu , Kang Li , Yang Liu

Correct-by-construction techniques, such as control barrier functions (CBFs), can be used to guarantee closed-loop safety by acting as a supervisor of an existing or legacy controller. However, supervisory-control intervention typically…

Systems and Control · Computer Science 2018-05-03 Yuxiao Chen , Ayonga Hereid , Huei Peng , Jessy Grizzle

Vision-Language Models (VLMs) exhibit impressive performance, yet the integration of powerful vision encoders has significantly broadened their attack surface, rendering them increasingly susceptible to jailbreak attacks. However, lacking…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Jiaxin Song , Yixu Wang , Jie Li , Rui Yu , Yan Teng , Xingjun Ma , Yingchun Wang

Modern nonlinear control theory seeks to develop feedback controllers that endow systems with properties such as safety and stability. The guarantees ensured by these controllers often rely on accurate estimates of the system state for…

Systems and Control · Electrical Eng. & Systems 2020-11-02 Sarah Dean , Andrew J. Taylor , Ryan K. Cosner , Benjamin Recht , Aaron D. Ames

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

Cryptography and Security · Computer Science 2025-09-09 Youjia Zheng , Mohammad Zandsalimy , Shanu Sushmita

Model information can be used to predict future trajectories, so it has huge potential to avoid dangerous region when implementing reinforcement learning (RL) on real-world tasks, like autonomous driving. However, existing studies mostly…

Robotics · Computer Science 2021-03-08 Haitong Ma , Jianyu Chen , Shengbo Eben Li , Ziyu Lin , Yang Guan , Yangang Ren , Sifa Zheng

Safety filters constructed from control barrier functions (CBFs) are commonly appended to pre-trained neural network controllers to enforce safety requirements. However, this decoupled design with hand-tuned, fixed CBF parameters often…

Systems and Control · Electrical Eng. & Systems 2026-05-27 Yang Zhao , Jungeun Lee , Jeong hwan Jeon , Sze Zheng Yong

Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and…

Cryptography and Security · Computer Science 2026-05-22 Shahnewaz Karim Sakib , Swati Kar , Anindya Bijoy Das

Despite extensive safety measures, LLMs are vulnerable to adversarial inputs, or jailbreaks, which can elicit unsafe behaviors. In this work, we introduce bijection learning, a powerful attack algorithm which automatically fuzzes LLMs for…

Computation and Language · Computer Science 2025-05-13 Brian R. Y. Huang , Maximilian Li , Leonard Tang

Reinforcement learning (RL) agents need to explore their environment to learn optimal behaviors and achieve maximum rewards. However, exploration can be risky when training RL directly on real systems, while simulation-based training…

Robotics · Computer Science 2024-10-10 Dvij Kalaria , Qin Lin , John M. Dolan

The rapid development of Large Language Models (LLMs) has brought impressive advancements across various tasks. However, despite these achievements, LLMs still pose inherent safety risks, especially in the context of jailbreak attacks. Most…

Cryptography and Security · Computer Science 2025-06-19 Shi Lin , Hongming Yang , Rongchang Li , Xun Wang , Changting Lin , Wenpeng Xing , Meng Han

Large language models (LLMs) have demonstrated remarkable capabilities across various tasks, but ensuring their safety and alignment with human values remains crucial. Current safety alignment methods, such as supervised fine-tuning and…

Computation and Language · Computer Science 2025-03-13 Bilgehan Sel , Dingcheng Li , Phillip Wallis , Vaishakh Keshava , Ming Jin , Siddhartha Reddy Jonnalagadda

This paper presents a sampled-data framework for the safe navigation of controlled agents in environments cluttered with obstacles governed by uncertain linear dynamics. Collision-free motion is achieved by combining Control Barrier…

Systems and Control · Electrical Eng. & Systems 2026-01-13 Hugo Matias , Daniel Silvestre

As large language models (LLMs) evolve from static chatbots into autonomous agents, the primary vulnerability surface shifts from final outputs to intermediate execution traces. While safety guardrails are well-benchmarked for natural…

Cryptography and Security · Computer Science 2026-04-09 Yen-Shan Chen , Sian-Yao Huang , Cheng-Lin Yang , Yun-Nung Chen

Ensuring robot safety in complex environments is a difficult task due to actuation limits, such as torque bounds. This paper presents a safety-critical control framework that leverages learning-based switching between multiple backup…

Robotics · Computer Science 2024-03-08 Neil C. Janwani , Ersin Daş , Thomas Touma , Skylar X. Wei , Tamas G. Molnar , Joel W. Burdick

Inference-time steering is widely regarded as a lightweight and parameter-free mechanism for controlling large language model (LLM) behavior, and prior work has often suggested that simple activation-level interventions can reliably induce…

Artificial Intelligence · Computer Science 2026-03-20 Zikang Ding , Qiying Hu , Yi Zhang , Hongji Li , Junchi Yao , Hongbo Liu , Lijie Hu
‹ Prev 1 3 4 5 6 7 10 Next ›