2,529+ academic papers on AI security, attacks, and defenses
Showing 1–20 of 69 papers
Clear filtersTim Van hamme, Thomas Vissers, Javier Carnerero-Cano +4 more
LLMs are increasingly deployed as autonomous agents with access to tools, databases, and external services, yet practitioners (across different...
Zhaorun Chen, Xun Liu, Haibo Tong +14 more
AI agents are increasingly deployed across diverse domains to automate complex workflows through long-horizon and high-stakes action executions. Due...
Haoyu Zhang, Mohammad Zandsalimy, Shanu Sushmita
Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We...
Weiyi Kong, Ahmad Mohammad Saber, Amr Youssef +1 more
In modern energy systems, industrial control systems (ICS) and power-system SCADA require intrusion detection that is not only accurate but also...
Yuchuan Zhao, Tong Chen, Junliang Yu +3 more
Large language model-powered sequential recommender systems (LLM-SRSs) have recently demonstrated remarkable performance, enabling recommendations...
Run Hao, Zhuoran Tan
Model Context Protocol (MCP) is increasingly adopted for tool-integrated LLM agents, but its multi-layer design and third-party server ecosystem...
Jiamin Chang, Minhui Xue, Ruoxi Sun +3 more
Recent advances in embodied Vision-Language Agentic Systems (VLAS), powered by large vision-language models (LVLMs), enable AI systems to perceive...
Jiacheng Liang, Yao Ma, Tharindu Kumarage +5 more
Reinforcement Learning from Human Feedback (RLHF) is central to aligning Large Language Models (LLMs), yet it introduces a critical vulnerability: an...
Wei Zhao, Zhe Li, Peixin Zhang +1 more
Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet...
Yihao Zhang, Kai Wang, Jiangrong Wu +7 more
Large Language Models (LLMs) face prominent security risks from jailbreaking, a practice that manipulates models to bypass built-in security...
Vu Tuan Truong, Long Bao Le
Large Language Models (LLMs), despite their impressive capabilities across domains, have been shown to be vulnerable to backdoor attacks. Prior...
Zhuowen Yuan, Zhaorun Chen, Zhen Xiang +5 more
Existing research on LLM agent security mainly focuses on prompt injection and unsafe input/output behaviors. However, as agents increasingly rely on...
Anubhab Sahu, Diptisha Samanta, Reza Soosahabi
System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive...
Jingning Xu, Haochen Luo, Chen Liu
Vision-language models (VLMs) are vulnerable to adversarial image perturbations. Existing works based on adversarial training against task-specific...
Aengus Lynch
Autonomous AI agents are being deployed with filesystem access, email control, and multi-step planning. This thesis contributes to four open problems...
Chong Xiang, Drew Zagieboylo, Shaona Ghosh +5 more
AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions...
KrishnaSaiReddy Patil
LLM-based chatbots in government services face critical security gaps. Multi-turn adversarial attacks achieve over 90% success against current...
Tran Duong Minh Dai, Triet Huynh Minh Le, M. Ali Babar +2 more
Although Graph Neural Networks (GNNs) have shown promise for smart contract vulnerability detection, they still face significant limitations....
Ron Litvak
System prompt configuration can make the difference between near-total phishing blindness and near-perfect detection in LLM email agents. We present...
Charoes Huang, Xin Huang, Amin Milani Fard
Prompt injection is listed as the number-one vulnerability class in the OWASP Top 10 for LLM Applications that can subvert LLM guardrails, disclose...
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