English
Related papers

Related papers: Progressive Safeguards for Safe and Model-Agnostic…

200 papers

Reward design remains a critical bottleneck in visual reinforcement learning (RL) for robotic manipulation. In simulated environments, rewards are conventionally designed based on the distance to a target position. However, such precise…

Machine Learning · Computer Science 2025-09-29 Nan Tang , Jing-Cheng Pang , Guanlin Li , Chao Qian , Yang Yu

Generalizable alignment is a core challenge for deploying Large Language Models (LLMs) safely in real-world NLP applications. Current alignment methods, including Reinforcement Learning from Human Feedback (RLHF), often fail to guarantee…

Computation and Language · Computer Science 2025-04-07 Jaymari Chua , Chen Wang , Lina Yao

Given the growing influence of language model-based agents on high-stakes societal decisions, from public policy to healthcare, ensuring their beneficial impact requires understanding the far-reaching implications of their suggestions. We…

Artificial Intelligence · Computer Science 2025-06-27 Chenkai Sun , Denghui Zhang , ChengXiang Zhai , Heng Ji

Creating reinforcement learning (RL) agents that are capable of accepting and leveraging task-specific knowledge from humans has been long identified as a possible strategy for developing scalable approaches for solving long-horizon…

Artificial Intelligence · Computer Science 2022-06-22 Lin Guan , Sarath Sreedharan , Subbarao Kambhampati

Reinforcement learning from human feedback (RLHF) is a key paradigm for aligning large language models (LLMs) with human values, yet the reward models at its core remain largely opaque. In this work, we present Sparse Autoencoder For…

Computation and Language · Computer Science 2026-02-02 Wei Shi , Ziyuan Xie , Sihang Li , Xiang Wang

Reinforcement learning is a promising approach to synthesizing policies for challenging robotics tasks. A key problem is how to ensure safety of the learned policy---e.g., that a walking robot does not fall over or that an autonomous car…

Machine Learning · Computer Science 2020-10-22 Osbert Bastani

Soft robotic manipulators offer operational advantage due to their compliant and deformable structures. However, their inherently nonlinear dynamics presents substantial challenges. Traditional analytical methods often depend on simplifying…

Robotics · Computer Science 2024-10-28 Uljad Berdica , Matthew Jackson , Niccolò Enrico Veronese , Jakob Foerster , Perla Maiolino

Despite the extent of recent advances in Machine Learning (ML) and Neural Networks, providing formal guarantees on the behavior of these systems is still an open problem, and a crucial requirement for their adoption in regulated or…

Machine Learning · Computer Science 2024-10-01 Matteo Francobaldi , Michele Lombardi

The application of reinforcement learning to safety-critical systems is limited by the lack of formal methods for verifying the robustness and safety of learned policies. This paper introduces a novel framework that addresses this gap by…

Artificial Intelligence · Computer Science 2025-08-22 Ahmed Nasir , Abdelhafid Zenati

Safety controllers is widely used to achieve safe reinforcement learning. Most methods that apply a safety controller are using handcrafted safety constraints to construct the safety controller. However, when the environment dynamics are…

Artificial Intelligence · Computer Science 2023-09-22 Haoyu Wang , Xin Yuan , Qinqing Ren

Task-agnostic model fingerprinting has recently gained increasing attention due to its ability to provide a universal framework applicable across diverse model architectures and tasks. The current state-of-the-art method, MetaV, ensures…

Cryptography and Security · Computer Science 2026-03-27 Guang Yang , Ziye Geng , Yihang Chen , Changqing Luo

Artificial intelligence (AI) and reinforcement learning (RL) have shown significant promise in wireless systems, enabling dynamic spectrum allocation, traffic management, and large-scale Internet of Things (IoT) coordination. However, their…

Networking and Internet Architecture · Computer Science 2026-02-17 Abdikarim Mohamed Ibrahim , Rosdiadee Nordin

Although Reinforcement Learning (RL) is effective for sequential decision-making problems under uncertainty, it still fails to thrive in real-world systems where risk or safety is a binding constraint. In this paper, we formulate the RL…

Machine Learning · Computer Science 2022-07-07 Yannis Flet-Berliac , Debabrota Basu

Large language models exhibit systematic vulnerabilities to adversarial attacks despite extensive safety alignment. We provide a mechanistic analysis revealing that position-dependent gradient weakening during autoregressive training…

Machine Learning · Computer Science 2025-11-18 Thong Bach , Dung Nguyen , Thao Minh Le , Truyen Tran

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…

Cryptography and Security · Computer Science 2026-01-26 Xianya Fang , Xianying Luo , Yadong Wang , Xiang Chen , Yu Tian , Zequn Sun , Rui Liu , Jun Fang , Naiqiang Tan , Yuanning Cui , Sheng-Jun Huang

The airworthiness and safety of a non-pedigreed autopilot must be verified, but the cost to formally do so can be prohibitive. We can bypass formal verification of non-pedigreed components by incorporating Runtime Safety Assurance (RTSA) as…

Machine Learning · Computer Science 2020-10-22 Christopher Lazarus , James G. Lopez , Mykel J. Kochenderfer

In real-life scenarios, a Reinforcement Learning (RL) agent aiming to maximise their reward, must often also behave in a safe manner, including at training time. Thus, much attention in recent years has been given to Safe RL, where an agent…

Machine Learning · Statistics 2025-03-26 Edwin Hamel-De le Court , Francesco Belardinelli , Alexander W. Goodall

Reinforcement learning is a powerful paradigm for learning optimal policies from experimental data. However, to find optimal policies, most reinforcement learning algorithms explore all possible actions, which may be harmful for real-world…

Machine Learning · Statistics 2017-11-15 Felix Berkenkamp , Matteo Turchetta , Angela P. Schoellig , Andreas Krause

Meta-learning is a branch of machine learning which aims to quickly adapt models, such as neural networks, to perform new tasks by learning an underlying structure across related tasks. In essence, models are being trained to learn new…

Ensuring safety in the sense of constraint satisfaction for learning-based control is a critical challenge, especially in the model-free case. While safety filters address this challenge in the model-based setting by modifying unsafe…

Systems and Control · Electrical Eng. & Systems 2026-01-15 Kanghui He , Shengling Shi , Ton van den Boom , Bart De Schutter