English
Related papers

Related papers: Gradient-Controlled Decoding: A Safety Guardrail f…

200 papers

Large language models (LLMs) are increasingly deployed in real-world applications ranging from chatbots to agentic systems, where they are expected to process untrusted data and follow trusted instructions. Failure to distinguish between…

Cryptography and Security · Computer Science 2025-10-17 Xiaoxue Yang , Bozhidar Stevanoski , Matthieu Meeus , Yves-Alexandre de Montjoye

Large language models (LLMs), despite being safety-aligned, exhibit brittle refusal behaviors that can be circumvented by simple linguistic changes. As tense jailbreaking demonstrates that models refusing harmful requests often comply when…

Artificial Intelligence · Computer Science 2026-04-15 Yein Park , Jungwoo Park , Jaewoo Kang

Despite the impressive capabilities of Large Language Models (LLMs) in various tasks, their vulnerability to unsafe prompts remains a critical issue. These prompts can lead LLMs to generate responses on illegal or sensitive topics, posing a…

Computation and Language · Computer Science 2024-07-10 Jinseok Kim , Jaewon Jung , Sangyeop Kim , Sohyung Park , Sungzoon Cho

The recent advancements in Large Language Models(LLMs) have had a significant impact on a wide range of fields, from general domains to specialized areas. However, these advancements have also significantly increased the potential for…

Cryptography and Security · Computer Science 2025-10-01 Taegyeong Lee , Jeonghwa Yoo , Hyoungseo Cho , Soo Yong Kim , Yunho Maeng

Large Language Models (LLMs) are often asked to generate structured outputs that obey precise syntactic rules, such as code snippets or formatted data. Grammar-constrained decoding (GCD) can guarantee that LLM outputs matches such rules by…

Computation and Language · Computer Science 2025-07-17 Kanghee Park , Timothy Zhou , Loris D'Antoni

Large language models (LLMs) have convincing performance in a variety of downstream tasks. However, these systems are prone to generating undesirable outputs such as harmful and biased text. In order to remedy such generations, the…

Computation and Language · Computer Science 2025-08-08 Manish Nagireddy , Inkit Padhi , Soumya Ghosh , Prasanna Sattigeri

As large language models (LLMs) become integrated into various sensitive applications, prompt injection, the use of prompting to induce harmful behaviors from LLMs, poses an ever increasing risk. Prompt injection attacks can cause LLMs to…

Cryptography and Security · Computer Science 2025-10-24 Isaac Wu , Michael Maslowski

Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs). A considerable amount of research exists proposing more effective jailbreak attacks, including the…

Cryptography and Security · Computer Science 2024-03-05 Daoyuan Wu , Shuai Wang , Yang Liu , Ning Liu

The dominant approach to generating from language models subject to some constraint is locally constrained decoding (LCD), incrementally sampling tokens at each time step such that the constraint is never violated. Typically, this is…

Large language model (LLM) safety classifiers such as Llama Guard are effective at detecting overtly harmful prompts but remain vulnerable to adversarial jailbreak attacks that disguise malicious intent through role-play scenarios,…

Cryptography and Security · Computer Science 2026-05-26 Lixing Lin , Juli You , Yue Li , Luyun Lin , Yiqing Wang , Zhen Zhang , Moxuan Zheng

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

Safety guardrails in large language models (LLMs) are a critical component in preventing harmful outputs. Yet, their resilience under perturbation remains poorly understood. In this paper, we investigate the robustness of safety fine-tuning…

Computation and Language · Computer Science 2025-10-14 Prithviraj Singh Shahani , Kaveh Eskandari Miandoab , Matthias Scheutz

Guardrail, an emerging mechanism designed to ensure that large language models (LLMs) align with human values by moderating harmful or toxic responses, requires a sociotechnical approach in their design. This paper addresses a critical…

Artificial Intelligence · Computer Science 2025-06-05 Jinwei Hu , Yi Dong , Xiaowei Huang

Safety alignment of Large Language Models (LLMs) can be compromised with manual jailbreak attacks and (automatic) adversarial attacks. Recent studies suggest that defending against these attacks is possible: adversarial attacks generate…

Cryptography and Security · Computer Science 2023-12-15 Sicheng Zhu , Ruiyi Zhang , Bang An , Gang Wu , Joe Barrow , Zichao Wang , Furong Huang , Ani Nenkova , Tong Sun

Large language models (LLMs) have achieved impressive performance across natural language tasks and are increasingly deployed in real-world applications. Despite extensive safety alignment efforts, recent studies show that such alignment is…

Artificial Intelligence · Computer Science 2026-02-02 Yinzhi Zhao , Ming Wang , Shi Feng , Xiaocui Yang , Daling Wang , Yifei Zhang

Prompt injection attacks pose a critical threat to large language models (LLMs), enabling goal hijacking and data leakage. Prompt guard models, though effective in defense, suffer from over-defense -- falsely flagging benign inputs as…

Computation and Language · Computer Science 2025-04-01 Hao Li , Xiaogeng Liu

With the ubiquity of Large Language Models (LLMs), guardrails have become crucial to detect and defend against toxic content. However, with the increasing pervasiveness of LLMs in multilingual scenarios, their effectiveness in handling…

Computation and Language · Computer Science 2024-10-30 Yahan Yang , Soham Dan , Dan Roth , Insup Lee

Large Vision-Language Models have shown strong multimodal reasoning capabilities, yet they remain susceptible to object hallucinations when language priors dominate insufficient or misaligned visual evidence. Training-free contrastive…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Xiaoyi Huang , Kejia Zhang , Zhiming Luo

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

Large Language Models (LLMs) are implicit troublemakers. While they provide valuable insights and assist in problem-solving, they can also potentially serve as a resource for malicious activities. Implementing safety alignment could…

Cryptography and Security · Computer Science 2024-08-27 Haoyu Wang , Bingzhe Wu , Yatao Bian , Yongzhe Chang , Xueqian Wang , Peilin Zhao