中文
相关论文

相关论文: Multilingual and Multi-Accent Jailbreaking of Audi…

200 篇论文

Audio large language models (ALLMs) enable rich speech-text interaction, but they also introduce jailbreak vulnerabilities in the audio modality. Existing audio jailbreak methods mainly optimize jailbreak success while overlooking utility…

声音 · 计算机科学 2026-04-13 Yunqiang Wang , Hengyuan Na , Di Wu , Miao Hu , Guocong Quan

Multimodal large language models (MLLMs) integrate information from multiple modalities such as text, images, audio, and video, enabling complex capabilities such as visual question answering and audio translation. While powerful, this…

密码学与安全 · 计算机科学 2026-03-31 Bhavuk Jain , Sercan Ö. Arık , Hardeo K. Thakur

Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling applications across fields beyond healthcare, software engineering, and conversational systems.…

Large Language Models (LLMs) demonstrate outstanding performance in their reservoir of knowledge and understanding capabilities, but they have also been shown to be prone to illegal or unethical reactions when subjected to jailbreak…

Multi-Agent Debate (MAD), leveraging collaborative interactions among Large Language Models (LLMs), aim to enhance reasoning capabilities in complex tasks. However, the security implications of their iterative dialogues and role-playing…

密码学与安全 · 计算机科学 2025-04-24 Senmao Qi , Yifei Zou , Peng Li , Ziyi Lin , Xiuzhen Cheng , Dongxiao Yu

Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows. This paper surveys research in the…

计算与语言 · 计算机科学 2023-10-18 Erfan Shayegani , Md Abdullah Al Mamun , Yu Fu , Pedram Zaree , Yue Dong , Nael Abu-Ghazaleh

The integration of audio modality into Large Audio Language Models (LALMs) significantly expands their attack surface. Existing jailbreak paradigms predominantly treat audio as a carrier for malicious payloads, relying on semantic…

密码学与安全 · 计算机科学 2026-05-19 Yanyun Wang , Yu Huang , Zi Liang , Xixin Wu , Li Liu

In recent years, the security vulnerabilities of Multi-modal Large Language Models (MLLMs) have become a serious concern in the Generative Artificial Intelligence (GenAI) research. These highly intelligent models, capable of performing…

密码学与安全 · 计算机科学 2026-01-12 Badhan Chandra Das , Md Tasnim Jawad , Joaquin Molto , M. Hadi Amini , Yanzhao Wu

As audio-visual multi-modal large language models (MLLMs) are increasingly deployed in safety-critical applications, understanding their vulnerabilities is crucial. To this end, we introduce Multi-Modal Typography, a systematic study…

计算机视觉与模式识别 · 计算机科学 2026-04-07 Tianle Chen , Deepti Ghadiyaram

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

Safety mechanisms for large language models (LLMs) remain predominantly English-centric, creating systematic vulnerabilities in multilingual deployment. Prior work shows that translating malicious prompts into other languages can…

计算与语言 · 计算机科学 2026-04-29 Shirin Alanova , Bogdan Minko , Sabrina Sadiekh , Evgeniy Kokuykin

This paper provides a systematic survey of jailbreak attacks and defenses on Large Language Models (LLMs) and Vision-Language Models (VLMs), emphasizing that jailbreak vulnerabilities stem from structural factors such as incomplete training…

密码学与安全 · 计算机科学 2026-01-08 Zejian Chen , Chaozhuo Li , Chao Li , Xi Zhang , Litian Zhang , Yiming He

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

This paper focuses on jailbreaking attacks against large language models (LLMs), eliciting them to generate objectionable content in response to harmful user queries. Unlike previous LLM-jailbreak methods that directly orient to LLMs, our…

人工智能 · 计算机科学 2025-12-02 Haoxuan Ji , Zheng Lin , Zhenxing Niu , Xinbo Gao , Gang Hua

While multimodal large language models (MLLMs) have achieved remarkable success in recent advancements, their susceptibility to jailbreak attacks has come to light. In such attacks, adversaries exploit carefully crafted prompts to coerce…

密码学与安全 · 计算机科学 2025-02-04 Ziyi Yin , Yuanpu Cao , Han Liu , Ting Wang , Jinghui Chen , Fenhlong Ma

Large Language Models (LLMs) have evolved into Multimodal Large Language Models (MLLMs), significantly enhancing their capabilities by integrating visual information and other types, thus aligning more closely with the nature of human…

密码学与安全 · 计算机科学 2025-06-03 Youze Wang , Wenbo Hu , Yinpeng Dong , Jing Liu , Hanwang Zhang , Richang Hong

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 Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level,…

密码学与安全 · 计算机科学 2025-11-25 Ryan Wong , Hosea David Yu Fei Ng , Dhananjai Sharma , Glenn Jun Jie Ng , Kavishvaran Srinivasan

With the rapid advancements in Multimodal Large Language Models (MLLMs), securing these models against malicious inputs while aligning them with human values has emerged as a critical challenge. In this paper, we investigate an important…

密码学与安全 · 计算机科学 2024-11-26 Weidi Luo , Siyuan Ma , Xiaogeng Liu , Xiaoyu Guo , Chaowei Xiao

Multimodal foundation models that integrate audio, vision, and language achieve strong performance on reasoning and generation tasks, yet their robustness to adversarial manipulation remains poorly understood. We study a realistic and…

声音 · 计算机科学 2026-01-26 Aafiya Hussain , Gaurav Srivastava , Alvi Ishmam , Zaber Hakim , Chris Thomas