English
Related papers

Related papers: SGuard-v1: Safety Guardrail for Large Language Mod…

200 papers

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

Vision-Language Models (VLMs) face significant safety vulnerabilities from malicious prompt attacks due to weakened alignment during visual integration. Existing defenses suffer from efficiency and robustness. To address these challenges,…

Machine Learning · Computer Science 2026-04-09 Peigui Qi , Kunsheng Tang , Yanpu Yu , Jialin Wu , Yide Song , Wenbo Zhou , Zhicong Huang , Cheng Hong , Weiming Zhang , Nenghai Yu

Current safety mechanisms for Large Language Models (LLMs) rely heavily on static, fine-tuned classifiers that suffer from adaptation rigidity, the inability to enforce new governance rules without expensive retraining. To address this, we…

Artificial Intelligence · Computer Science 2026-02-27 Umid Suleymanov , Rufiz Bayramov , Suad Gafarli , Seljan Musayeva , Taghi Mammadov , Aynur Akhundlu , Murat Kantarcioglu

Large language models (LLMs) have achieved remarkable success in diverse tasks, yet their safety alignment remains fragile during adaptation. Even when fine-tuning on benign data or with low-rank adaptation, pre-trained safety behaviors are…

Artificial Intelligence · Computer Science 2025-10-28 Bingjie Zhang , Yibo Yang , Zhe Ren , Dandan Guo , Jindong Gu , Philip Torr , Bernard Ghanem

Accurate rejection of sensitive or harmful visual content, i.e., harmful image guardrail, is critical in many application scenarios. This task must continuously adapt to the evolving safety policies and content across various domains and…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Caiyong Piao , Zhiyuan Yan , Haoming Xu , Yunzhen Zhao , Kaiqing Lin , Feiyang Xu , Shuigeng Zhou

Safety guardrails in large language models(LLMs) are developed to prevent malicious users from generating toxic content at a large scale. However, these measures can inadvertently introduce or reflect new biases, as LLMs may refuse to…

Computation and Language · Computer Science 2025-11-03 Adel Khorramrouz , Sharon Levy

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

We introduce the Granite Guardian models, a suite of safeguards designed to provide risk detection for prompts and responses, enabling safe and responsible use in combination with any large language model (LLM). These models offer…

Large language models (LLMs) remain vulnerable to jailbreak prompts that elicit harmful or policy-violating outputs, while many existing defenses rely on expensive fine-tuning, intrusive prompt rewriting, or external guardrails that add…

Cryptography and Security · Computer Science 2026-02-17 Weiming Song , Xuan Xie , Ruiping Yin

As LLMs become increasingly prevalent across various applications, it is critical to establish safety guardrails to moderate input/output content of LLMs. Existing guardrail models treat various safety categories independently and fail to…

Artificial Intelligence · Computer Science 2024-07-09 Mintong Kang , Bo Li

Large Language Models (LLMs) are prone to off-topic misuse, where users may prompt these models to perform tasks beyond their intended scope. Current guardrails, which often rely on curated examples or custom classifiers, suffer from high…

Computation and Language · Computer Science 2025-04-10 Gabriel Chua , Shing Yee Chan , Shaun Khoo

Recent advancements in Text-to-Image (T2I) models have raised significant safety concerns about their potential misuse for generating inappropriate or Not-Safe-For-Work (NSFW) contents, despite existing countermeasures such as NSFW…

Computer Vision and Pattern Recognition · Computer Science 2024-10-31 Yijun Yang , Ruiyuan Gao , Xiao Yang , Jianyuan Zhong , Qiang Xu

Vision-language models (VLMs) are essential for contextual understanding of both visual and textual information. However, their vulnerability to adversarially manipulated inputs presents significant risks, leading to compromised outputs and…

Machine Learning · Computer Science 2024-10-02 Xuefeng Du , Reshmi Ghosh , Robert Sim , Ahmed Salem , Vitor Carvalho , Emily Lawton , Yixuan Li , Jack W. Stokes

Studying the robustness of Large Language Models (LLMs) to unsafe behaviors is an important topic of research today. Building safety classification models or guard models, which are fine-tuned models for input/output safety classification…

Computation and Language · Computer Science 2025-07-30 Sowmya Vajjala

AI Safety Moderation (ASM) classifiers are designed to moderate content on social media platforms and to serve as guardrails that prevent Large Language Models (LLMs) from being fine-tuned on unsafe inputs. Owing to their potential for…

Computation and Language · Computer Science 2025-01-24 Akshit Achara , Anshuman Chhabra

Maintaining the safety of large language models (LLMs) is crucial as they are increasingly deployed in real-world applications. Existing safety guardrails typically rely on single-pass classification or, more recently, distilled reasoning.…

Artificial Intelligence · Computer Science 2026-05-29 Siddharth Sai , Xiaofei Wen , Muhao Chen

Large language models exhibit safety degradation in non-English languages. Standard evaluation relies on Jailbreak Success Rate (JSR), which confounds several safety-driving factors into one, obscuring the specific cause(s) of safety…

Computation and Language · Computer Science 2026-05-19 Max Zhang , Ameen Patel , Sang T. Truong , Sanmi Koyejo

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

Large Language Models (LLMs) have significantly advanced natural language processing (NLP) tasks but also pose ethical and societal risks due to their propensity to generate harmful content. Existing methods have limitations, including the…

Computation and Language · Computer Science 2025-05-22 Ximing Dong , Dayi Lin , Shaowei Wang , Ahmed E. Hassan

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