中文
相关论文

相关论文: Evaluating Robustness of Large Audio Language Mode…

200 篇论文

The foundational capabilities established by Large Language Models (LLMs) have paved the way for Multimodal Large Language Models (MLLMs), within which Large Audio Language Models (LALMs) are essential for realizing universal auditory…

Large Audio Language Models (LALMs) expand jailbreak risks from token-level prompting to the full speech perception-to-reasoning pipeline, where unsafe behavior can be induced through semantics, acoustic style, signal artifacts, or internal…

声音 · 计算机科学 2026-05-29 Bo-Han Feng , Yu-Hsuan Li Liang , Chien-Feng Liu , You-Hsuan Chang , Yun-Nung Chen

Large Language Models (LLMs) have demonstrated exceptional proficiency in instruction-following, becoming increasingly crucial across various applications. However, this capability brings with it the risk of prompt injection attacks, where…

计算与语言 · 计算机科学 2023-11-28 Zekun Li , Baolin Peng , Pengcheng He , Xifeng Yan

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

Large Audio Language Models (LALMs) have significantly advanced audio understanding but introduce critical security risks, particularly through audio jailbreaks. While prior work has focused on English-centric attacks, we expose a far more…

声音 · 计算机科学 2025-04-03 Jaechul Roh , Virat Shejwalkar , Amir Houmansadr

Modern Large audio-language models (LALMs) power intelligent voice interactions by tightly integrating audio and text. This integration, however, expands the attack surface beyond text and introduces vulnerabilities in the continuous,…

密码学与安全 · 计算机科学 2026-04-17 Meng Chen , Kun Wang , Li Lu , Jiaheng Zhang , Tianwei Zhang

As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipulative or adversarial input becomes critical. Although prior work has studied adversarial…

计算与语言 · 计算机科学 2026-05-25 Jinyang Wu , Bin Zhu , Xiandong Zou , Qiquan Zhang , Xu Fang , Pan Zhou

This study systematically analyzes the vulnerability of 36 large language models (LLMs) to various prompt injection attacks, a technique that leverages carefully crafted prompts to elicit malicious LLM behavior. Across 144 prompt injection…

Robust verbal confidence generated by large language models (LLMs) is crucial for the deployment of LLMs to help ensure transparency, trust, and safety in many applications, including those involving human-AI interactions. In this paper, we…

计算与语言 · 计算机科学 2025-12-19 Stephen Obadinma , Xiaodan Zhu

Adversarial audio attacks pose a significant threat to the growing use of large audio-language models (LALMs) in voice-based human-machine interactions. While existing research focused on model-specific adversarial methods, real-world…

声音 · 计算机科学 2025-06-09 Wanqi Yang , Yanda Li , Meng Fang , Yunchao Wei , Ling Chen

Large Audio Language Models (LALMs) have made significant progress. While increasingly deployed in real-world applications, LALMs face growing safety risks from jailbreak attacks that bypass safety alignment. However, there remains a lack…

密码学与安全 · 计算机科学 2026-03-03 Zifan Peng , Yule Liu , Zhen Sun , Mingchen Li , Zeren Luo , Jingyi Zheng , Wenhan Dong , Xinlei He , Xuechao Wang , Yingjie Xue , Shengmin Xu , Xinyi Huang

Large Audio Language Models (LALMs), which couple acoustic perception with large language models (LLMs) to extract and understand diverse information from audio, have attracted intense interest from both academic and industrial communities.…

声音 · 计算机科学 2025-10-28 Bohan Li , Wenbin Huang , Yuhang Qiu , Yiwei Guo , Hankun Wang , Zhihan Li , Jing Peng , Ziyang Ma , Xie Chen , Kai Yu

Multimodal Large Language Models (MLLMs) have demonstrated exceptional performance in artificial intelligence by facilitating integrated understanding across diverse modalities, including text, images, video, audio, and speech. However,…

计算机视觉与模式识别 · 计算机科学 2025-03-19 Chengze Jiang , Zhuangzhuang Wang , Minjing Dong , Jie Gui

The increasing deployment of Large Language Models (LLMs) in various applications necessitates a rigorous evaluation of their robustness against adversarial attacks. In this paper, we present a comprehensive study on the robustness of GPT…

计算与语言 · 计算机科学 2024-12-24 Yiyi Tao , Yixian Shen , Hang Zhang , Yanxin Shen , Lun Wang , Chuanqi Shi , Shaoshuai Du

Large Language Models (LLMs) have seen rapid adoption in recent years, with industries increasingly relying on them to maintain a competitive advantage. These models excel at interpreting user instructions and generating human-like…

密码学与安全 · 计算机科学 2025-09-09 Andrew Yeo , Daeseon Choi

Integrated Speech and Large Language Models (SLMs) that can follow speech instructions and generate relevant text responses have gained popularity lately. However, the safety and robustness of these models remains largely unclear. In this…

Large audio-language models (LALMs) extend text-based LLMs with auditory understanding, offering new opportunities for multimodal applications. While their perception, reasoning, and task performance have been widely studied, their safety…

Jailbreak attacks to Large audio-language models (LALMs) are studied recently, but they exclusively focused on the attack scenario where the adversary can fully manipulate user prompts (named strong adversary) and limited in effectiveness,…

密码学与安全 · 计算机科学 2026-02-04 Guangke Chen , Fu Song , Zhe Zhao , Xiaojun Jia , Yang Liu , Yanchen Qiao , Weizhe Zhang , Weiping Tu , Yuhong Yang , Bo Du

The rise of multimodal large language models has introduced innovative human-machine interaction paradigms but also significant challenges in machine learning safety. Audio-Language Models (ALMs) are especially relevant due to the intuitive…

机器学习 · 计算机科学 2025-07-11 Isha Gupta , David Khachaturov , Robert Mullins

Prompt injection attacks exploit vulnerabilities in large language models (LLMs) to manipulate the model into unintended actions or generate malicious content. As LLM integrated applications gain wider adoption, they face growing…

密码学与安全 · 计算机科学 2024-01-03 Daniel Wankit Yip , Aysan Esmradi , Chun Fai Chan
‹ 上一页 1 2 3 10 下一页 ›