2,529+ academic papers on AI security, attacks, and defenses
Showing 1–13 of 13 papers
Clear filtersPedro Conde, Henrique Branquinho, Valerio Mazzone +3 more
AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will...
Saba Pourhanifeh, AbdulAziz AbdulGhaffar, Ashraf Matrawy
Large Language Models(LLMs) are increasingly explored for cybersecurity applications such as vulnerability detection. In the domain of threat...
Qinghua Mao, Xi Lin, Jinze Gu +3 more
Large language models (LLMs) increasingly rely on knowledge editing to support knowledge-intensive reasoning, but this flexibility also introduces...
Xia Hu, Zhenrui Yue, Brian Potetz +4 more
As current Multimodal Large Language Models rapidly saturate canonical visual reasoning benchmarks, a key question emerges: do these strong scores...
Huy Hoang Ha, Benoit Favre, Francois Portet
Large language models (LLMs) have saturated standard medical benchmarks that test factual recall, yet their ability to perform higher-order...
Jingshen Zhang, Bo Wang, Yanlin Fu +4 more
In this paper, we study an emergent self-debiasing mechanisms against stereotypical content in Large Language Models (LLMs). Unlike traditional...
Yilin Zhang, Yingkai Hua, Chunyu Wei +2 more
Vision-language model (VLM) based web agents demonstrate impressive autonomous GUI interaction but remain vulnerable to deceptive interface elements....
Di Lu, Bo Zhang, Xiyuan Li +5 more
Self-hosted computer-use agents (SHCUAs), such as OpenClaw, combine natural-language interaction with direct access to host-side resources, including...
Qinfeng Li, Yuntai Bao, Jianghui Hu +5 more
LLM agents rely on prompts to implement task-specific capabilities based on foundation LLMs, making agent prompts valuable intellectual property....
Christopher G. Pedraza Pohlenz, Hassan Jalil Hadi, Ali Hassan +1 more
LLMs are increasingly explored for malware analysis; however, current LLM-based malware attribution remains limited by unsupported indicators and...
Xiaomin Li, Andrzej Banburski-Fahey, Jaron Lanier
Auditing language-model outputs often requires more than judging correctness: an auditor may need to identify which source document most likely...
Dasol Choi, Eugenia Kim, Jaewon Noh +14 more
Current LLM safety benchmarks are predominantly English-centric and often rely on translation, failing to capture country-specific harms. Moreover,...
Chenglin Yang
Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A...
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