English
Related papers

Related papers: Vulnerability Mitigation for Safety-Aligned Langua…

200 papers

AI safety has emerged as a critical priority as these systems are increasingly deployed in real-world applications. We propose the first domain-agnostic AI safety ensuring framework that achieves strong safety guarantees while preserving…

Artificial Intelligence · Computer Science 2025-10-07 Beomjun Kim , Kangyeon Kim , Sunwoo Kim , Yeonsang Shin , Heejin Ahn

Frontier AI systems are rapidly advancing in their capabilities to persuade, deceive, and influence human behaviour, with current models already demonstrating human-level persuasion and strategic deception in specific contexts. Humans are…

Artificial Intelligence · Computer Science 2025-07-18 Rishane Dassanayake , Mario Demetroudi , James Walpole , Lindley Lentati , Jason R. Brown , Edward James Young

As the capabilities of large machine learning models continue to grow, and as the autonomy afforded to such models continues to expand, the spectre of a new adversary looms: the models themselves. The threat that a model might behave in a…

Machine Learning · Computer Science 2023-07-27 Andres Carranza , Dhruv Pai , Rylan Schaeffer , Arnuv Tandon , Sanmi Koyejo

Ensuring that large language models (LLMs) comply with safety requirements is a central challenge in AI deployment. Existing alignment approaches primarily operate during training, such as through fine-tuning or reinforcement learning from…

Machine Learning · Computer Science 2025-12-03 Tuan Nguyen , Long Tran-Thanh

State-of-the-art conversational AI systems raise concerns due to their potential risks of generating unsafe, toxic, unethical, or dangerous content. Previous works have developed datasets to teach conversational agents the appropriate…

Computation and Language · Computer Science 2024-02-02 Souvik Das , Rohini K. Srihari

In this paper, we argue that current safety alignment research efforts for large language models are hindered by many intertwined sources of noise, such as small datasets, methodological inconsistencies, and unreliable evaluation setups.…

Cryptography and Security · Computer Science 2026-05-19 Tim Beyer , Sophie Xhonneux , Simon Geisler , Gauthier Gidel , Leo Schwinn , Stephan Günnemann

As autonomous driving technology evolves, ensuring the stability and safety of Autonomous Driving Systems (ADS) through alignment with human values becomes increasingly crucial. While existing research emphasizes the adherence of AI to…

Computer Science and Game Theory · Computer Science 2025-12-01 Boyao Peng , Linkun Liu

The ideal AI safety moderation system would be both structurally interpretable (so its decisions can be reliably explained) and steerable (to align to safety standards and reflect a community's values), which current systems fall short on.…

With the widespread application of Large Language Models (LLMs), it has become a significant concern to ensure their safety and prevent harmful responses. While current safe-alignment methods based on instruction fine-tuning and…

Computation and Language · Computer Science 2025-12-16 Xiaoyun Zhang , Zhengyue Zhao , Wenxuan Shi , Kaidi Xu , Di Huang , Xing Hu

Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…

Artificial Intelligence · Computer Science 2026-05-26 Jinhu Qi , Muzhi Li , Jiahong Liu , Yuqin Shu , Dianzhi Yu , Shicheng Ma , Wenqian Cui , Yiyang Zhao , Yiyi Chen , Ruoxi Jiang , Irwin King , Zenglin Xu

AI has become integral to safety-critical areas like autonomous driving systems (ADS) and robotics. The architecture of recent autonomous systems are trending toward end-to-end (E2E) monolithic architectures such as large language models…

Artificial Intelligence · Computer Science 2025-07-24 Mandar Pitale , Jelena Frtunikj , Abhinaw Priyadershi , Vasu Singh , Maria Spence

Existing paradigms for ensuring AI safety, such as guardrail models and alignment training, often compromise either inference efficiency or development flexibility. We introduce Disentangled Safety Adapters (DSA), a novel framework…

Machine Learning · Computer Science 2026-05-04 Kundan Krishna , Joseph Y Cheng , Charles Maalouf , Leon A Gatys

When fine-tuning pre-trained Language Models (LMs) to exhibit desired behaviors, maintaining control over risk is critical for ensuring both safety and trustworthiness. Most existing safety alignment methods, such as Safe RLHF and SACPO,…

Artificial Intelligence · Computer Science 2026-01-01 Lijun Zhang , Lin Li , Wei Wei , Yajie Qi , Huizhong Song , Jun Wang , Yaodong Yang , Jiye Liang

As Large Language Models (LLMs) become increasingly integrated into real-world decision-making systems, understanding their behavioural vulnerabilities remains a critical challenge for AI safety and alignment. While existing evaluation…

Artificial Intelligence · Computer Science 2025-05-20 Lili Zhang , Haomiaomiao Wang , Long Cheng , Libao Deng , Tomas Ward

Evaluating the value alignment of large language models (LLMs) has traditionally relied on single-sentence adversarial prompts, which directly probe models with ethically sensitive or controversial questions. However, with the rapid…

Computation and Language · Computer Science 2025-03-31 Yazhou Zhang , Qimeng Liu , Qiuchi Li , Peng Zhang , Jing Qin

Machine learning fairness concerns about the biases towards certain protected or sensitive group of people when addressing the target tasks. This paper studies the debiasing problem in the context of image classification tasks. Our data…

Computer Vision and Pattern Recognition · Computer Science 2020-08-14 Yi Zhang , Jitao Sang

Safety alignment of large language models (LLMs) has been gaining increasing attention. However, current safety-aligned LLMs suffer from the fragile and imbalanced safety mechanisms, which can still be induced to generate unsafe responses,…

Computation and Language · Computer Science 2024-12-18 Weixiang Zhao , Yulin Hu , Zhuojun Li , Yang Deng , Jiahe Guo , Xingyu Sui , Yanyan Zhao , Bing Qin , Tat-Seng Chua , Ting Liu

Large language models are becoming pervasive core components in many real-world applications. As a consequence, security alignment represents a critical requirement for their safe deployment. Although previous related works focused…

Cryptography and Security · Computer Science 2026-03-24 Marco Arazzi , Vignesh Kumar Kembu , Antonino Nocera

As artificial intelligence systems grow more powerful, there has been increasing interest in "AI safety" research to address emerging and future risks. However, the field of AI safety remains poorly defined and inconsistently measured,…

Recent research shows that fine-tuning on benign instruction-following data can inadvertently undo the safety alignment process and increase a model's propensity to comply with harmful queries. While instruction-following fine-tuning is…

Computation and Language · Computer Science 2025-03-03 Francisco Eiras , Aleksandar Petrov , Philip H. S. Torr , M. Pawan Kumar , Adel Bibi
‹ Prev 1 4 5 6 7 8 10 Next ›