2,529+ academic papers on AI security, attacks, and defenses
Showing 101–120 of 142 papers
Clear filtersShiva Gaire, Srijan Gyawali, Saroj Mishra +3 more
The Model Context Protocol (MCP) has emerged as the de facto standard for connecting Large Language Models (LLMs) to external data and tools,...
Guanquan Shi, Haohua Du, Zhiqiang Wang +4 more
Large Language Models (LLMs) are evolving into autonomous agents capable of executing complex workflows via standardized protocols (e.g., MCP)....
Mehrab Hosain, Sabbir Alom Shuvo, Matthew Ogbe +4 more
The modern web stack, which is dominated by browser-based applications and API-first backends, now operates under an adversarial equilibrium where...
Wei Zhao, Zhe Li, Jun Sun
Large Language Models (LLMs) exhibit remarkable capabilities but remain vulnerable to adversarial manipulations such as jailbreaking, where crafted...
Juan A. Wibowo, George C. Polyzos
Background: Autonomous agents powered by Large Language Models (LLMs) are driving a paradigm shift toward an "Internet of Agents" (IoA). While...
Boyuan Chen, Sitong Fang, Jiaming Ji +57 more
As intelligence increases, so does its shadow. AI deception, in which systems induce false beliefs to secure self-beneficial outcomes, has evolved...
Jaehwan Park, Kyungchan Lim, Seonhye Park +1 more
The advent of Artificial Intelligence (AI), particularly large language models (LLMs), has revolutionized software development by enabling developers...
Jiangrui Zheng, Yingming Zhou, Ali Abdullah Ahmad +2 more
Bug bounty platforms (e.g., HackerOne, BugCrowd) leverage crowd-sourced vulnerability discovery to improve continuous coverage, reduce the cost of...
Strahinja Janjusevic, Anna Baron Garcia, Sohrob Kazerounian
Generative AI is reshaping offensive cybersecurity by enabling autonomous red team agents that can plan, execute, and adapt during penetration tests....
Zimo Ji, Xunguang Wang, Zongjie Li +6 more
Large Language Model (LLM)-based agents with function-calling capabilities are increasingly deployed, but remain vulnerable to Indirect Prompt...
Gioliano de Oliveira Braga, Pedro Henrique dos Santos Rocha, Rafael Pimenta de Mattos Paixão +3 more
Wi-Fi Channel State Information (CSI) has been repeatedly proposed as a biometric modality, often with reports of high accuracy and operational...
Shaowei Guan, Hin Chi Kwok, Ngai Fong Law +3 more
Retrieval-augmented generation (RAG) has rapidly emerged as a transformative approach for integrating large language models into clinical and...
James Jin Kang, Dang Bui, Thanh Pham +1 more
The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can...
Gabrielle M Gauthier, Eesha Ali, Amna Asim +2 more
Human content moderators (CMs) routinely review distressing digital content at scale. Beyond exposure, the work context (e.g., workload, team...
Gian Maria Campedelli
While the possibility of reaching human-like Artificial Intelligence (AI) remains controversial, the likelihood that the future will be characterized...
Yuntao Wang, Siamak P. Najad-Davarani, Elizabeth Bossart +3 more
Background: Modern large language models (LLMs) offer powerful reasoning that converts narratives into structured, taxonomy-aligned data, revealing...
Qin Zhou, Zhexin Zhang, Zhi Li +1 more
With the rapid advancement of AI models, their deployment across diverse tasks has become increasingly widespread. A notable emerging application is...
Kathrin Grosse, Nico Ebert
Recent improvement gains in large language models (LLMs) have lead to everyday usage of AI-based Conversational Agents (CAs). At the same time, LLMs...
Dominik Schwarz
As Large Language Models (LLMs) are increasingly integrated into automated, multi-stage pipelines, risk patterns that arise from unvalidated trust...
Robert A. Bridges, Thomas R. Mitchell, Mauricio Muñoz +1 more
The advent of Large Language Models (LLMs) promised to resolve the long-standing paradox in honeypot design, achieving high-fidelity deception with...
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