English
Related papers

Related papers: A Lightweight Explainable Guardrail for Prompt Saf…

200 papers

Multi-turn jailbreak attacks progressively erode LLM safety alignment across seemingly innocuous conversation turns, achieving success rates exceeding 90% against state-of-the-art models. Existing alignment-based and guardrail methods…

Cryptography and Security · Computer Science 2026-04-21 Bo Yan , Weikai Lin , Yada Zhu , Song Wang

With the growing deployment of large language models (LLMs) in real-world applications, establishing robust safety guardrails to moderate their inputs and outputs has become essential to ensure adherence to safety policies. Current…

Computation and Language · Computer Science 2026-03-04 Minseok Choi , Dongjin Kim , Seungbin Yang , Subin Kim , Youngjun Kwak , Juyoung Oh , Jaegul Choo , Jungmin Son

Jailbreak attacks reveal critical vulnerabilities in Large Language Models (LLMs) by causing them to generate harmful or unethical content. Evaluating these threats is particularly challenging due to the evolving nature of LLMs and the…

Machine Learning · Computer Science 2025-07-11 Peiyan Zhang , Haibo Jin , Liying Kang , Haohan Wang

Recent advances in large language models (LLMs) have led to increasingly sophisticated safety protocols and features designed to prevent harmful, unethical, or unauthorized outputs. However, these guardrails remain susceptible to novel and…

Computation and Language · Computer Science 2025-07-08 Annika M Schoene , Cansu Canca

Large Language Models (LLMs) are typically aligned for safety during the post-training phase; however, they may still generate inappropriate outputs that could potentially pose risks to users. This challenge underscores the need for robust…

Machine Learning · Computer Science 2025-12-08 Mahesh Kumar Nandwana , Youngwan Lim , Joseph Liu , Alex Yang , Varun Notibala , Nishchaie Khanna

Guardrails have emerged as an alternative to safety alignment for content moderation of large language models (LLMs). Existing model-based guardrails have not been designed for resource-constrained computational portable devices, such as…

Machine Learning · Computer Science 2024-12-19 Hayder Elesedy , Pedro M. Esperança , Silviu Vlad Oprea , Mete Ozay

Large language models (LLMs) rely on safety alignment to avoid responding to malicious user inputs. Unfortunately, jailbreak can circumvent safety guardrails, resulting in LLMs generating harmful content and raising concerns about LLM…

Computation and Language · Computer Science 2024-06-14 Zhenhong Zhou , Haiyang Yu , Xinghua Zhang , Rongwu Xu , Fei Huang , Yongbin Li

Many safety post-training methods for large language models (LLMs) are designed to modify the model's behaviour from producing unsafe answers to issuing refusals. However, such distribution shifts are often brittle and degrade performance…

Computation and Language · Computer Science 2025-10-08 David Dobre , Mehrnaz Mofakhami , Sophie Xhonneux , Leo Schwinn , Gauthier Gidel

We present GuardReasoner-Omni, a reasoning-based guardrail model designed to moderate text, image, video, and audio data. First, we construct a comprehensive training corpus comprising 181k samples spanning these four modalities. Our…

Cryptography and Security · Computer Science 2026-05-28 Zhenhao Zhu , Yue Liu , Yanpei Guo , Wenjie Qu , Cancan Chen , Yufei He , Yibo Li , Yulin Chen , Tianyi Wu , Huiying Xu , Xinzhong Zhu , Jiaheng Zhang

Recent advancements in large language models (LLMs) have accelerated progress toward artificial general intelligence, yet their potential to generate harmful content poses critical safety challenges. Existing alignment methods often…

Computation and Language · Computer Science 2025-10-08 Kehua Feng , Keyan Ding , Yuhao Wang , Menghan Li , Fanjunduo Wei , Xinda Wang , Qiang Zhang , Huajun Chen

Guardrail Classifiers defend production language models against harmful behavior, but although results seem promising in testing, they provide no formal guarantees. Providing formal guarantees for such models is hard because "harmful…

Machine Learning · Computer Science 2026-05-12 Nikita Kezins , Urbas Ekka , Pascal Berrang , Luca Arnaboldi

Deploying large language models (LLMs) in real-world applications requires robust safety guard models to detect and block harmful user prompts. While large safety guard models achieve strong performance, their computational cost is…

Computation and Language · Computer Science 2025-05-23 Seanie Lee , Dong Bok Lee , Dominik Wagner , Minki Kang , Haebin Seong , Tobias Bocklet , Juho Lee , Sung Ju Hwang

The emergence of Large Reasoning Models (LRMs) introduces a new paradigm of explicit reasoning, enabling remarkable advances yet posing unique risks such as reasoning manipulation and information leakage. To mitigate these risks, current…

Artificial Intelligence · Computer Science 2026-02-03 Jingnan Zheng , Jingjun Xu , Yanzhen Luo , Chenhang Cui , Gelei Deng , Zhenkai Liang , Xiang Wang , An Zhang , Tat-Seng Chua

Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment, which often relies on rigid refusal heuristics or representation engineering to block harmful outputs. While they are…

Computation and Language · Computer Science 2025-10-01 Yuyou Zhang , Miao Li , William Han , Yihang Yao , Zhepeng Cen , Ding Zhao

Autonomous highway driving demands a critical balance between proactive, efficiency-seeking behavior and robust safety guarantees. This paper proposes Language Action-guided Reinforcement Learning (LA-RL) with Safety Guarantees, a novel…

Systems and Control · Electrical Eng. & Systems 2025-12-08 Yiming Shu , Jiahui Xu , Jiwei Tang , Ruiyang Gao , Chen Sun

The recent emergence of multimodal large language models (LLMs) has introduced new opportunities for improving visual hazard recognition on construction sites. Unlike traditional computer vision models that rely on domain-specific training…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Nishi Chaudhary , S M Jamil Uddin , Sathvik Sharath Chandra , Anto Ovid , Alex Albert

Large Language Models (LLMs) guardrail systems are designed to protect against prompt injection and jailbreak attacks. However, they remain vulnerable to evasion techniques. We demonstrate two approaches for bypassing LLM prompt injection…

Cryptography and Security · Computer Science 2025-07-15 William Hackett , Lewis Birch , Stefan Trawicki , Neeraj Suri , Peter Garraghan

Large Language Models (LLMs) are vulnerable to attacks like prompt injection, backdoor attacks, and adversarial attacks, which manipulate prompts or models to generate harmful outputs. In this paper, departing from traditional deep learning…

Computation and Language · Computer Science 2025-02-19 Huawei Lin , Yingjie Lao , Tong Geng , Tan Yu , Weijie Zhao

Fine-tuning large language models (LLMs) to adapt to evolving safety policies is costly and impractical. Mechanistic interpretability enables inference-time control through latent activation steering, yet its potential for precise,…

Machine Learning · Computer Science 2025-06-06 Shaona Ghosh , Amrita Bhattacharjee , Yftah Ziser , Christopher Parisien

As the popularity of Large Language Models (LLMs) grow, combining model safety with utility becomes increasingly important. The challenge is making sure that LLMs can recognize and decline dangerous prompts without sacrificing their ability…

Computation and Language · Computer Science 2024-08-30 Ruchira Ray , Ruchi Bhalani