中文
相关论文

相关论文: False Sense of Security: Why Probing-based Malicio…

200 篇论文

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…

密码学与安全 · 计算机科学 2025-06-02 Jianwei Li , Jung-Eun Kim

This paper presents a systematic evaluation of Large Language Models' (LLMs) behavior on long-tail distributed (encrypted) texts and their safety implications. We introduce a two-dimensional framework for assessing LLM safety: (1)…

计算与语言 · 计算机科学 2025-06-05 Utsav Maskey , Mark Dras , Usman Naseem

Fine-tuning a general-purpose large language model (LLM) for a specific domain or task has become a routine procedure for ordinary users. However, fine-tuning is known to remove the safety alignment features of the model, even when the…

计算与语言 · 计算机科学 2025-06-23 Kathleen C. Fraser , Hillary Dawkins , Isar Nejadgholi , Svetlana Kiritchenko

Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathematical problems -- using formalisms…

密码学与安全 · 计算机科学 2026-05-06 Haoyu Zhang , Mohammad Zandsalimy , Shanu Sushmita

We find that language models have difficulties generating fallacious and deceptive reasoning. When asked to generate deceptive outputs, language models tend to leak honest counterparts but believe them to be false. Exploiting this…

计算与语言 · 计算机科学 2025-05-26 Yue Zhou , Henry Peng Zou , Barbara Di Eugenio , Yang Zhang

Large language models (LLMs) are susceptible to a type of attack known as jailbreaking, which misleads LLMs to output harmful contents. Although there are diverse jailbreak attack strategies, there is no unified understanding on why some…

计算与语言 · 计算机科学 2024-12-04 Yuping Lin , Pengfei He , Han Xu , Yue Xing , Makoto Yamada , Hui Liu , Jiliang Tang

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

密码学与安全 · 计算机科学 2025-09-09 Youjia Zheng , Mohammad Zandsalimy , Shanu Sushmita

Considerable research efforts have been devoted to ensuring that large language models (LLMs) align with human values and generate safe text. However, an excessive focus on sensitivity to certain topics can compromise the model's robustness…

计算与语言 · 计算机科学 2023-08-29 Huachuan Qiu , Shuai Zhang , Anqi Li , Hongliang He , Zhenzhong Lan

With the development of Large Language Models (LLMs), numerous efforts have revealed their vulnerabilities to jailbreak attacks. Although these studies have driven the progress in LLMs' safety alignment, it remains unclear whether LLMs have…

密码学与安全 · 计算机科学 2025-09-16 Yu Yan , Sheng Sun , Zhe Wang , Yijun Lin , Zenghao Duan , zhifei zheng , Min Liu , Zhiyi yin , Jianping Zhang

Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…

机器学习 · 计算机科学 2025-08-22 Xiangman Li , Xiaodong Wu , Qi Li , Jianbing Ni , Rongxing Lu

Jailbreaks have been a central focus of research regarding the safety and reliability of large language models (LLMs), yet the mechanisms underlying these attacks remain poorly understood. While previous studies have predominantly relied on…

密码学与安全 · 计算机科学 2025-11-04 Nathalie Kirch , Constantin Weisser , Severin Field , Helen Yannakoudakis , Stephen Casper

The reliability of large language models (LLMs) is greatly compromised by their tendency to hallucinate, underscoring the need for precise identification of knowledge gaps within LLMs. Various methods for probing such gaps exist, ranging…

计算与语言 · 计算机科学 2025-06-02 Raoyuan Zhao , Abdullatif Köksal , Ali Modarressi , Michael A. Hedderich , Hinrich Schütze

Large language models (LLMs) have demonstrated immense utility across various industries. However, as LLMs advance, the risk of harmful outputs increases due to incorrect or malicious instruction prompts. While current methods effectively…

计算与语言 · 计算机科学 2025-06-19 Xinyi Zeng , Yuying Shang , Jiawei Chen , Jingyuan Zhang , Yu Tian

The open-sourcing of large language models (LLMs) accelerates application development, innovation, and scientific progress. This includes both base models, which are pre-trained on extensive datasets without alignment, and aligned models,…

计算与语言 · 计算机科学 2024-04-17 Xiao Wang , Tianze Chen , Xianjun Yang , Qi Zhang , Xun Zhao , Dahua Lin

Recent explorations with commercial Large Language Models (LLMs) have shown that non-expert users can jailbreak LLMs by simply manipulating their prompts; resulting in degenerate output behavior, privacy and security breaches, offensive…

计算与语言 · 计算机科学 2024-03-28 Abhinav Rao , Sachin Vashistha , Atharva Naik , Somak Aditya , Monojit Choudhury

Large Language Models (LLMs) have demonstrated potential in cybersecurity applications but have also caused lower confidence due to problems like hallucinations and a lack of truthfulness. Existing benchmarks provide general evaluations but…

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

Large Language Models (LLMs) have demonstrated remarkable success across various NLP benchmarks. However, excelling in complex tasks that require nuanced reasoning and precise decision-making demands more than raw language proficiency--LLMs…

计算与语言 · 计算机科学 2025-02-24 Ang Li , Yichuan Mo , Mingjie Li , Yifei Wang , Yisen Wang

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

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…

人工智能 · 计算机科学 2026-02-02 Yinzhi Zhao , Ming Wang , Shi Feng , Xiaocui Yang , Daling Wang , Yifei Zhang
‹ 上一页 1 2 3 10 下一页 ›