2,560+ academic papers on AI security, attacks, and defenses
Showing 621–640 of 982 papers
Clear filtersMiranda Christ, Noah Golowich, Sam Gunn +2 more
Watermarks are an essential tool for identifying AI-generated content. Recently, Christ and Gunn (CRYPTO '24) introduced pseudorandom...
Joshua Ward, Bochao Gu, Chi-Hua Wang +1 more
Large Language Models (LLMs) have recently demonstrated remarkable performance in generating high-quality tabular synthetic data. In practice, two...
Botao 'Amber' Hu, Bangdao Chen
The emerging "agentic web" envisions large populations of autonomous agents coordinating, transacting, and delegating across open networks. Yet many...
Yinan Zhong, Qianhao Miao, Yanjiao Chen +3 more
Large Language Models (LLMs) have been integrated into many applications (e.g., web agents) to perform more sophisticated tasks. However,...
Tailun Chen, Yu He, Yan Wang +9 more
Retrieval-Augmented Generation (RAG) systems enhance LLMs with external knowledge but introduce a critical attack surface: corpus poisoning. While...
Zafaryab Haider, Md Hafizur Rahman, Shane Moeykens +2 more
Hard-to-detect hardware bit flips, from either malicious circuitry or bugs, have already been shown to make transformers vulnerable in non-generative...
Sampriti Soor, Suklav Ghosh, Arijit Sur
Language models are vulnerable to short adversarial suffixes that can reliably alter predictions. Previous works usually find such suffixes with...
Stephan Carney, Soham Hans, Sofia Hirschmann +4 more
Adversaries (hackers) attempting to infiltrate networks frequently face uncertainty in their operational environments. This research explores the...
Xiqiao Xiong, Ouxiang Li, Zhuo Liu +5 more
Large language models have seen widespread adoption, yet they remain vulnerable to multi-turn jailbreak attacks, threatening their safe deployment....
Ziming Hong, Tianyu Huang, Runnan Chen +4 more
Recent studies have extended diffusion-based instruction-driven 2D image editing pipelines to 3D Gaussian Splatting (3DGS), enabling faithful...
Max Zhang, Derek Liu, Kai Zhang +2 more
Large language models (LLMs) are increasingly deployed worldwide, yet their safety alignment remains predominantly English-centric. This allows for...
Yunzhe Li, Jianan Wang, Hongzi Zhu +3 more
Large Language Models (LLMs) have become foundational components in a wide range of applications, including natural language understanding and...
Richard Young
Despite substantial investment in safety alignment, the vulnerability of large language models to sophisticated multi-turn adversarial attacks...
George Mikros
Large language models (LLMs) present a dual challenge for forensic linguistics. They serve as powerful analytical tools enabling scalable corpus...
Sima Jafarikhah, Daniel Thompson, Eva Deans +2 more
Manual vulnerability scoring, such as assigning Common Vulnerability Scoring System (CVSS) scores, is a resource-intensive process that is often...
Donghang Duan, Xu Zheng, Yuefeng He +3 more
Current LLM-based text anonymization frameworks usually rely on remote API services from powerful LLMs, which creates an inherent privacy paradox:...
Songping Wang, Rufan Qian, Yueming Lyu +5 more
Image-to-Video (I2V) generation synthesizes dynamic visual content from image and text inputs, providing significant creative control. However, the...
Chenyu Zhang, Yiwen Ma, Lanjun Wang +3 more
Text-to-image~(T2I) models commonly incorporate defense mechanisms to prevent the generation of sensitive images. Unfortunately, recent jailbreaking...
Shiji Zhao, Shukun Xiong, Yao Huang +7 more
Multimodal Large Language Models (MLLMs) are widely used in various fields due to their powerful cross-modal comprehension and generation...
Weikai Lu, Ziqian Zeng, Kehua Zhang +5 more
Multimodal Large Language Models (MLLMs) are increasingly vulnerable to multimodal Indirect Prompt Injection (IPI) attacks, which embed malicious...
Get breaking CVE alerts, compliance reports (ISO 42001, EU AI Act), and CISO risk assessments for your AI/ML stack.
Start 14-Day Free Trial
AI Threat Alert