2,077+ academic papers on AI security, attacks, and defenses
Showing 61–80 of 115 papers
Clear filtersArmstrong Foundjem, Lionel Nganyewou Tidjon, Leuson Da Silva +1 more
Machine learning (ML) underpins foundation models in finance, healthcare, and critical infrastructure, making them targets for data poisoning, model...
Shaghayegh Shajarian, Kennedy Marsh, James Benson +2 more
Modern networks generate vast, heterogeneous traffic that must be continuously analyzed for security and performance. Traditional network traffic...
Junjun Pan, Yixin Liu, Rui Miao +5 more
Large language model (LLM)-based multi-agent systems (MAS) have shown strong capabilities in solving complex tasks. As MAS become increasingly...
Bin Wang, Wenjie Yu, Yilu Zhong +6 more
Large language models (LLMs) for code generation are becoming integral to modern software development, but their real-world prevalence and security...
Abhivansh Gupta
As LLM-based agents grow more autonomous and multi-modal, ensuring they remain controllable, auditable, and faithful to deployer intent becomes...
Richard Helder Moulton, Austin O'Brien, John D. Hastings
Although large language models (LLMs) are increasingly used in security-critical workflows, practitioners lack quantitative guidance on which...
Viet K. Nguyen, Mohammad I. Husain
Agentic AI introduces security vulnerabilities that traditional LLM safeguards fail to address. Although recent work by Unit 42 at Palo Alto Networks...
Arth Bhardwaj, Sia Godika, Yuvam Loonker
Traditional, centralized security tools often miss adaptive, multi-vector attacks. We present the Multi-Agent LLM Cyber Defense Framework (MALCDF), a...
Dongchao Zhou, Lingyun Ying, Huajun Chai +1 more
JavaScript's widespread adoption has made it an attractive target for malicious attackers who employ sophisticated obfuscation techniques to conceal...
Amy Chang, Tiffany Saade, Sanket Mendapara +2 more
Artificial intelligence (AI) systems are being readily and rapidly adopted, increasingly permeating critical domains: from consumer platforms and...
Shashie Dilhara Batan Arachchige, Benjamin Zi Hao Zhao, Hassan Jameel Asghar +2 more
Large Language Models (LLMs) are often fine-tuned to adapt their general-purpose knowledge to specific tasks and domains such as cyber threat...
Padmeswari Nandiya, Ahmad Mohsin, Ahmed Ibrahim +2 more
Industry 5.0's increasing integration of IT and OT systems is transforming industrial operations but also expanding the cyber-physical attack...
Fenghua Weng, Chaochao Lu, Xia Hu +2 more
As multimodal reasoning improves the overall capabilities of Large Vision Language Models (LVLMs), recent studies have begun to explore...
Zhibo Liang, Tianze Hu, Zaiye Chen +1 more
Autonomous Large Language Model (LLM) agents exhibit significant vulnerability to Indirect Prompt Injection (IPI) attacks. These attacks hijack agent...
Arush Sachdeva, Rajendraprasad Saravanan, Gargi Sarkar +2 more
Cybercrime increasingly exploits human cognitive biases in addition to technical vulnerabilities, yet most existing analytical frameworks focus...
Xianzong Wu, Xiaohong Li, Lili Quan +1 more
Large language models(LLMs) are increasingly expanding their real-world applications across domains, e.g., question answering, autonomous driving,...
Eranga Bandara, Amin Hass, Ross Gore +8 more
AI agent-based systems are becoming increasingly integral to modern software architectures, enabling autonomous decision-making, dynamic task...
Mihai Christodorescu, Earlence Fernandes, Ashish Hooda +11 more
In recent years, agentic artificial intelligence (AI) systems are becoming increasingly widespread. These systems allow agents to use various tools,...
Kaixiang Wang, Zhaojiacheng Zhou, Bunyod Suvonov +2 more
Large Language Model (LLM)-based Multi-Agent Systems (MAS) are susceptible to linguistic attacks that can trigger cascading failures across the...
Shaona Ghosh, Barnaby Simkin, Kyriacos Shiarlis +9 more
This paper introduces a dynamic and actionable framework for securing agentic AI systems in enterprise deployment. We contend that safety and...
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