2,529+ academic papers on AI security, attacks, and defenses
Showing 121–140 of 551 papers
Clear filtersVishal Narnaware, Animesh Gupta, Kevin Zhai +2 more
Multimodal Diffusion Large Language Models (MDLLMs) achieve high-concurrency generation through parallel masked decoding, yet the architectures...
Pei Chen, Geng Hong, Xinyi Wu +6 more
The emergence of Large Language Model-enhanced Search Engines (LLMSEs) has revolutionized information retrieval by integrating web-scale search...
Zhihui Yao, Hengran Zhang, Keping Bi
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) with external knowledge but remains vulnerable to low-authority sources...
Francesco Gentile, Nicola Dall'Asen, Francesco Tonini +3 more
As vision-language models are deployed at scale, understanding their internal mechanisms becomes increasingly critical. Existing interpretability...
Michael Somma, Markus Großpointner, Paul Zabalegui +2 more
The increasing complexity and interconnectivity of digital infrastructures make scalable and reliable security assessment methods essential. Robotic...
Oussama Draissi, Mark Günzel, Ahmad-Reza Sadeghi +1 more
WebAssembly's (Wasm) monolithic linear memory model facilitates memory corruption attacks that can escalate to cross-site scripting in browsers or go...
Zhanguang Zhang, Zhiyuan Li, Behnam Rahmati +10 more
Robot action planning in the real world is challenging as it requires not only understanding the current state of the environment but also predicting...
Marco Arazzi, Vignesh Kumar Kembu, Antonino Nocera
Large language models are becoming pervasive core components in many real-world applications. As a consequence, security alignment represents a...
Mohammad Asadi, Jack W. O'Sullivan, Fang Cao +5 more
Multimodal AI systems have achieved remarkable performance across a broad range of real-world tasks, yet the mechanisms underlying visual-language...
Zhongyi Li, Wan Tian, Jingyu Chen +8 more
Multi-agent collaboration has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models, yet it suffers from...
Zongjie Li, Chaozheng Wang, Yuchong Xie +2 more
Large Language Models are increasingly being considered for deployment in safety-critical military applications. However, current benchmarks suffer...
Zihan Guo, Zhiyu Chen, Xiaohang Nie +3 more
With the rapid evolution of Large Language Model (LLM) agent ecosystems, centralized skill marketplaces have emerged as pivotal infrastructure for...
Yandan Zheng, Haoran Luo, Zhenghong Lin +2 more
Benchmarks are the de facto standard for tracking progress in large language models (LLMs), yet static test sets can rapidly saturate, become...
Sen Fang, Weiyuan Ding, Zhezhen Cao +2 more
Large Language Models (LLMs) are increasingly adopted for vulnerability detection, yet their reasoning remains fundamentally unsound. We identify a...
Jiahao Chen, Zhiming Zhao, Yuwen Pu +4 more
Federated learning (FL) has attracted substantial attention in both academia and industry, yet its practical security posture remains poorly...
Hung Yun Tseng, Wuzhen Li, Blerina Gkotse +1 more
The potential of Large Language Models (LLMs) to provide harmful information remains a significant concern due to the vast breadth of illegal queries...
Christopher J. Agostino, Quan Le Thien, Nayan D'Souza +1 more
Understanding the fundamental mechanisms governing the production of meaning in the processing of natural language is critical for designing safe,...
Fazhong Liu, Zhuoyan Chen, Tu Lan +6 more
Autonomous coding agents are increasingly integrated into software development workflows, offering capabilities that extend beyond code suggestion to...
Dong Yan, Jian Liang, Yanbo Wang +3 more
Test-Time Reinforcement Learning (TTRL) enables Large Language Models (LLMs) to enhance reasoning capabilities on unlabeled test streams by deriving...
Zou Qiang
Large language models (LLMs) demonstrate strong generative capabilities but remain vulnerable to hallucination and unreliable reasoning under...
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