中文
相关论文

相关论文: Efficient Detection of Toxic Prompts in Large Lang…

200 篇论文

This study investigates the potential of a multimodal large language model (LLM), specifically ChatGPT-4o, to perform human-like interpretations of traffic scenes using static dashcam images. Herein, we focus on three judgment tasks…

计算机视觉与模式识别 · 计算机科学 2025-07-14 Yuki Yoshihara , Linjing Jiang , Nihan Karatas , Hitoshi Kanamori , Asuka Harada , Takahiro Tanaka

Therapeutic development is a costly and high-risk endeavor that is often plagued by high failure rates. To address this, we introduce TxGemma, a suite of efficient, generalist large language models (LLMs) capable of therapeutic property…

Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models for malicious purposes, including the synthesis of controlled…

人工智能 · 计算机科学 2025-08-26 Chongwen Zhao , Zhihao Dou , Kaizhu Huang

As Large Language Models (LLMs) of Prompt Jailbreaking are getting more and more attention, it is of great significance to raise a generalized research paradigm to evaluate attack strengths and a basic model to conduct subtler experiments.…

密码学与安全 · 计算机科学 2024-04-15 Tianyu Zhang , Zixuan Zhao , Jiaqi Huang , Jingyu Hua , Sheng Zhong

Detecting evidence within the context is a key step in the process of reasoning task. Evaluating and enhancing the capabilities of LLMs in evidence detection will strengthen context-based reasoning performance. This paper proposes a…

Large Language Models (LLMs) are susceptible to jailbreak attacks where malicious prompts are disguised using ciphers and character-level encodings to bypass safety guardrails. While these guardrails often fail to interpret the encoded…

密码学与安全 · 计算机科学 2025-11-03 Shaked Zychlinski , Yuval Kainan

Large Language Models (LLMs) remain vulnerable to prompt injection attacks, representing the most significant security threat in production deployments. We present Prompt Fencing, a novel architectural approach that applies cryptographic…

密码学与安全 · 计算机科学 2025-11-26 Steven Peh

The proliferation of Large Language Models (LLMs) has revolutionized natural language processing and significantly impacted code generation tasks, enhancing software development efficiency and productivity. Notably, LLMs like GPT-4 have…

软件工程 · 计算机科学 2025-03-25 Sheng Ouyang , Yihao Qin , Bo Lin , Liqian Chen , Xiaoguang Mao , Shangwen Wang

Ensuring the safety and alignment of Large Language Models is a significant challenge with their growing integration into critical applications and societal functions. While prior research has primarily focused on jailbreak attacks, less…

机器学习 · 计算机科学 2026-04-28 Jiawei Chen , Zhengwei Fang , Yu Tian , Jiawei Du , Chao Yu , Zhaoxia Yin , Hang Su

The safety alignment of Large Language Models (LLMs) is vulnerable to both manual and automated jailbreak attacks, which adversarially trigger LLMs to output harmful content. However, current methods for jailbreaking LLMs, which nest entire…

密码学与安全 · 计算机科学 2024-11-13 Xirui Li , Ruochen Wang , Minhao Cheng , Tianyi Zhou , Cho-Jui Hsieh

Large Language Models (LLMs), such as ChatGPT and GPT-4, are designed to provide useful and safe responses. However, adversarial prompts known as 'jailbreaks' can circumvent safeguards, leading LLMs to generate potentially harmful content.…

计算与语言 · 计算机科学 2024-04-09 Peng Ding , Jun Kuang , Dan Ma , Xuezhi Cao , Yunsen Xian , Jiajun Chen , Shujian Huang

Prompt injection attacks manipulate large language models (LLMs) by misleading them to deviate from the original input instructions and execute maliciously injected instructions, because of their instruction-following capabilities and…

密码学与安全 · 计算机科学 2025-10-07 Yulin Chen , Haoran Li , Yuan Sui , Yufei He , Yue Liu , Yangqiu Song , Bryan Hooi

Large Language Models (LLMs) have recently shown promise as high-level planners for robots when given access to a selection of low-level skills. However, it is often assumed that LLMs do not possess sufficient knowledge to be used for the…

机器人学 · 计算机科学 2024-06-19 Teyun Kwon , Norman Di Palo , Edward Johns

Large Language Models, such as Generative Pre-trained Transformer 3 (aka. GPT-3), have been developed to understand language through the analysis of extensive text data, allowing them to identify patterns and connections between words.…

计算与语言 · 计算机科学 2023-10-03 Baphumelele Masikisiki , Vukosi Marivate , Yvette Hlope

Large language models (LLMs) have been massively applied to many tasks, often surpassing state-of-the-art approaches. While their effectiveness in code generation has been extensively studied (e.g., AlphaCode), their potential for code…

软件工程 · 计算机科学 2023-07-21 Pablo Antonio Martínez , Gregorio Bernabé , José Manuel García

Large language models often face a three-way trade-off among detection accuracy, inference latency, and deployment cost when used in real-world safety-sensitive applications. This paper introduces Prefix Probing, a black-box harmful content…

人工智能 · 计算机科学 2025-12-19 Jirui Yang , Hengqi Guo , Zhihui Lu , Yi Zhao , Yuansen Zhang , Shijing Hu , Qiang Duan , Yinggui Wang , Tao Wei

Large Language Models (LLMs) have showcased their remarkable capabilities in diverse domains, encompassing natural language understanding, translation, and even code generation. The potential for LLMs to generate harmful content is a…

软件工程 · 计算机科学 2024-09-17 Mingke Yang , Yuqi Chen , Yi Liu , Ling Shi

This paper presents a novel approach to evaluating the security of large language models (LLMs) against prompt leakage-the exposure of system-level prompts or proprietary configurations. We define prompt leakage as a critical threat to…

密码学与安全 · 计算机科学 2025-02-19 Tvrtko Sternak , Davor Runje , Dorian Granoša , Chi Wang

The proliferation of Large Language Models (LLMs) has intensified concerns about manipulative or deceptive behaviors that can undermine user autonomy, trust, and well-being. Existing safety benchmarks predominantly rely on coarse binary…

人工智能 · 计算机科学 2025-12-30 Sadia Asif , Israel Antonio Rosales Laguan , Haris Khan , Shumaila Asif , Muneeb Asif

Large language models (LLMs) have been applied in various applications due to their astonishing capabilities. With advancements in technologies such as chain-of-thought (CoT) prompting and in-context learning (ICL), the prompts fed to LLMs…

计算与语言 · 计算机科学 2023-12-07 Huiqiang Jiang , Qianhui Wu , Chin-Yew Lin , Yuqing Yang , Lili Qiu
‹ 上一页 1 8 9 10 下一页 ›