中文
相关论文

相关论文: MrGuard: A Multilingual Reasoning Guardrail for Un…

200 篇论文

Large Language Models (LLMs) are vulnerable to adversarial prompt based injects. These injects could jailbreak or exploit vulnerabilities within these models with explicit prompt requests leading to undesired responses. In the context of…

密码学与安全 · 计算机科学 2025-02-18 Jonathan Pan , Swee Liang Wong , Yidi Yuan , Xin Wei Chia

Large language models (LLMs) are being deployed across the Global South, where everyday use involves low-resource languages, code-mixing, and culturally specific norms. Yet safety pipelines, benchmarks, and alignment still largely target…

计算与语言 · 计算机科学 2026-02-17 Somnath Banerjee , Rima Hazra , Animesh Mukherjee

The rapid development of autonomous web agents powered by Large Language Models (LLMs), while greatly elevating efficiency, exposes the frontier risk of taking unintended or harmful actions. This situation underscores an urgent need for…

人工智能 · 计算机科学 2025-07-22 Boyuan Zheng , Zeyi Liao , Scott Salisbury , Zeyuan Liu , Michael Lin , Qinyuan Zheng , Zifan Wang , Xiang Deng , Dawn Song , Huan Sun , Yu Su

As large language models (LLMs) are increasingly integrated into numerous applications across various domains, LLMs' safety becomes a critical concern for both application developers and intended users. Currently, great efforts have been…

密码学与安全 · 计算机科学 2025-09-30 Haoran Li , Yulin Chen , Jingru Zeng , Hao Peng , Huihao Jing , Wenbin Hu , Xi Yang , Ziqian Zeng , Sirui Han , Yangqiu Song

We propose a lightweight explainable guardrail (LEG) method to detect unsafe prompts. LEG uses a multi-task learning architecture to jointly learn a prompt classifier and an explanation classifier, where the latter labels prompt words that…

计算与语言 · 计算机科学 2026-04-28 Md Asiful Islam , Mihai Surdeanu

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…

密码学与安全 · 计算机科学 2025-07-15 William Hackett , Lewis Birch , Stefan Trawicki , Neeraj Suri , Peter Garraghan

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…

计算与语言 · 计算机科学 2026-05-19 Max Zhang , Ameen Patel , Sang T. Truong , Sanmi Koyejo

Large Language Models (LLMs) are acquiring a wider range of capabilities, including understanding and responding in multiple languages. While they undergo safety training to prevent them from answering illegal questions, imbalances in…

计算与语言 · 计算机科学 2025-03-18 Likai Tang , Niruth Bogahawatta , Yasod Ginige , Jiarui Xu , Shixuan Sun , Surangika Ranathunga , Suranga Seneviratne

Although the rise of Large Language Models (LLMs) in enterprise settings brings new opportunities and capabilities, it also brings challenges, such as the risk of generating inappropriate, biased, or misleading content that violates…

The rapid advancements in Large Language Models (LLMs) have enabled their deployment as autonomous agents for handling complex tasks in dynamic environments. These LLMs demonstrate strong problem-solving capabilities and adaptability to…

人工智能 · 计算机科学 2025-02-19 Weidi Luo , Shenghong Dai , Xiaogeng Liu , Suman Banerjee , Huan Sun , Muhao Chen , Chaowei Xiao

Large Language Models have found success in a variety of applications. However, their safety remains a concern due to the existence of various jailbreaking methods. Despite significant efforts, alignment and safety fine-tuning only provide…

计算与语言 · 计算机科学 2025-12-16 Darpan Aswal , Céline Hudelot

Multimodal large language models (MLLMs) have demonstrated impressive reasoning and instruction-following capabilities, yet their expanded modality space introduces new compositional safety risks that emerge from complex text-image…

密码学与安全 · 计算机科学 2025-11-18 Xuankun Rong , Wenke Huang , Tingfeng Wang , Daiguo Zhou , Bo Du , Mang Ye

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…

机器学习 · 计算机科学 2025-12-08 Mahesh Kumar Nandwana , Youngwan Lim , Joseph Liu , Alex Yang , Varun Notibala , Nishchaie Khanna

Prompt attacks, including jailbreaks and prompt injections, pose a critical security risk to Large Language Model (LLM) systems. In production, guardrails must mitigate these attacks under strict low-latency constraints, resulting in a…

计算与语言 · 计算机科学 2026-03-27 Hieu Xuan Le , Benjamin Goh , Quy Anh Tang

The robustness and security of large language models (LLMs) has become a prominent research area. One notable vulnerability is the ability to bypass LLM safeguards by translating harmful queries into rare or underrepresented languages, a…

计算与语言 · 计算机科学 2025-09-16 Hongliang Li , Jinan Xu , Gengping Cui , Changhao Guan , Fengran Mo , Kaiyu Huang

Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning tasks through enhanced chain-of-thought capabilities. However, this advancement also introduces novel safety risks, as these models become increasingly…

计算机视觉与模式识别 · 计算机科学 2025-10-22 Yinan Xia , Yilei Jiang , Yingshui Tan , Xiaoyong Zhu , Xiangyu Yue , Bo Zheng

Large language models (LLMs) have become increasingly sophisticated, leading to widespread deployment in sensitive applications where safety and reliability are paramount. However, LLMs have inherent risks accompanying them, including bias,…

密码学与安全 · 计算机科学 2024-06-21 Suriya Ganesh Ayyamperumal , Limin Ge

Large language models (LLMs) pose significant risks due to the potential for generating harmful content or users attempting to evade guardrails. Existing studies have developed LLM-based guard models designed to moderate the input and…

密码学与安全 · 计算机科学 2025-02-25 Hongfu Liu , Hengguan Huang , Xiangming Gu , Hao Wang , Ye Wang

Large language models (LLMs) have achieved remarkable capabilities but remain vulnerable to adversarial prompts known as jailbreaks, which can bypass safety alignment and elicit harmful outputs. Despite growing efforts in LLM safety…

密码学与安全 · 计算机科学 2025-05-27 Guobin Shen , Dongcheng Zhao , Linghao Feng , Xiang He , Jihang Wang , Sicheng Shen , Haibo Tong , Yiting Dong , Jindong Li , Xiang Zheng , Yi Zeng

Large language models (LLMs) undergo safety alignment after training and tuning, yet recent work shows that safety can be bypassed through jailbreak attacks. While many jailbreaks and defenses exist, their cross-lingual generalization…

计算与语言 · 计算机科学 2025-11-05 Berk Atil , Rebecca J. Passonneau , Fred Morstatter