中文
相关论文

相关论文: GenTel-Safe: A Unified Benchmark and Shielding Fra…

200 篇论文

Application designers have moved to integrate large language models (LLMs) into their products. However, many LLM-integrated applications are vulnerable to prompt injections. While attempts have been made to address this problem by building…

密码学与安全 · 计算机科学 2025-04-15 Dennis Jacob , Hend Alzahrani , Zhanhao Hu , Basel Alomair , David Wagner

Large language models (LLMs) are becoming a popular tool as they have significantly advanced in their capability to tackle a wide range of language-based tasks. However, LLMs applications are highly vulnerable to prompt injection attacks,…

计算与语言 · 计算机科学 2024-11-11 Md Abdur Rahman , Fan Wu , Alfredo Cuzzocrea , Sheikh Iqbal Ahamed

Ensuring the safety of large language model (LLM) applications is essential for developing trustworthy artificial intelligence. Current LLM safety benchmarks have two limitations. First, they focus solely on either discriminative or…

计算与语言 · 计算机科学 2024-10-30 Yutao Mou , Shikun Zhang , Wei Ye

Prompt engineering reduces reasoning mistakes in Large Language Models (LLMs). However, its effectiveness in mitigating vulnerabilities in LLM-generated code remains underexplored. To address this gap, we implemented a benchmark to…

软件工程 · 计算机科学 2025-02-11 Marc Bruni , Fabio Gabrielli , Mohammad Ghafari , Martin Kropp

Large language models have gained widespread prominence, yet their vulnerability to prompt injection and other adversarial attacks remains a critical concern. This paper argues for a security-by-design AI paradigm that proactively mitigates…

密码学与安全 · 计算机科学 2025-10-02 Dalal Alharthi , Ivan Roberto Kawaminami Garcia

Large language models (LLMs) introduce new security risks, but there are few comprehensive evaluation suites to measure and reduce these risks. We present BenchmarkName, a novel benchmark to quantify LLM security risks and capabilities. We…

Large Language Models increasingly power critical infrastructure from healthcare to finance, yet their vulnerability to adversarial manipulation threatens system integrity and user safety. Despite growing deployment, no comprehensive…

密码学与安全 · 计算机科学 2026-03-19 Taiwo Onitiju , Iman Vakilinia

Large language models (LLMs) are vulnerable to adversarial attacks that add malicious tokens to an input prompt to bypass the safety guardrails of an LLM and cause it to produce harmful content. In this work, we introduce erase-and-check,…

计算与语言 · 计算机科学 2025-02-06 Aounon Kumar , Chirag Agarwal , Suraj Srinivas , Aaron Jiaxun Li , Soheil Feizi , Himabindu Lakkaraju

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

Large Language Models (LLMs) are increasingly used in intelligent systems that perform reasoning, summarization, and code generation. Their ability to follow natural-language instructions, while powerful, also makes them vulnerable to a new…

密码学与安全 · 计算机科学 2025-11-13 Daniyal Ganiuly , Assel Smaiyl

The increasing deployment of large language models in security-sensitive domains necessitates rigorous evaluation of their resilience against adversarial prompt-based attacks. While previous benchmarks have focused on security evaluations…

密码学与安全 · 计算机科学 2025-09-22 Huining Cui , Wei Liu

This paper presents a real-time modular defense system named Sentra-Guard. The system detects and mitigates jailbreak and prompt injection attacks targeting large language models (LLMs). The framework uses a hybrid architecture with…

密码学与安全 · 计算机科学 2026-05-04 Md. Mehedi Hasan , Sk Tanzir Mehedi , Ziaur Rahman , Rafid Mostafiz , Md. Abir Hossain

When large language model (LLM) systems interact with external data to perform complex tasks, a new attack, namely prompt injection, becomes a significant threat. By injecting instructions into the data accessed by the system, the attacker…

密码学与安全 · 计算机科学 2025-08-26 Sizhe Chen , Yizhu Wang , Nicholas Carlini , Chawin Sitawarin , David Wagner

Recent advances in multi-modal large language models (MLLMs) have enabled unified perception-reasoning capabilities, yet these systems remain highly vulnerable to jailbreak attacks that bypass safety alignment and induce harmful behaviors.…

密码学与安全 · 计算机科学 2025-12-09 Xiaojun Jia , Jie Liao , Qi Guo , Teng Ma , Simeng Qin , Ranjie Duan , Tianlin Li , Yihao Huang , Zhitao Zeng , Dongxian Wu , Yiming Li , Wenqi Ren , Xiaochun Cao , Yang Liu

Large Language Models (LLMs) excel in processing and generating human language, powered by their ability to interpret and follow instructions. However, their capabilities can be exploited through prompt injection attacks. These attacks…

人工智能 · 计算机科学 2024-03-11 Xiaogeng Liu , Zhiyuan Yu , Yizhe Zhang , Ning Zhang , Chaowei Xiao

The rapid adoption of large language models (LLMs) in enterprise systems exposes vulnerabilities to prompt injection attacks, strategic deception, and biased outputs, threatening security, trust, and fairness. Extending our adversarial…

密码学与安全 · 计算机科学 2025-10-07 Santhosh KumarRavindran

Integrating large language models (LLMs) into robotic systems has revolutionised embodied artificial intelligence, enabling advanced decision-making and adaptability. However, ensuring reliability, encompassing both security against…

机器人学 · 计算机科学 2025-09-03 Wenxiao Zhang , Xiangrui Kong , Conan Dewitt , Thomas Bräunl , Jin B. Hong

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…

计算与语言 · 计算机科学 2025-04-01 Hao Li , Xiaogeng Liu

Large Language Models (LLMs) are increasingly integrated into real-world applications, from virtual assistants to autonomous agents. However, their flexibility also introduces new attack vectors-particularly Prompt Injection (PI), where…

密码学与安全 · 计算机科学 2025-09-17 Mengxiao Wang , Yuxuan Zhang , Guofei Gu

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
‹ 上一页 1 2 3 10 下一页 ›