AI Threat Alert indexes 3,023+ peer-reviewed and preprint papers on AI/ML security — covering adversarial attacks, model defenses, red-teaming benchmarks, surveys, and security tooling. Papers are sourced from arXiv, classified by type and by relevance to real-world threats, and cross-referenced with the CVEs and incidents they relate to.
Showing 21–40 of 319 papers
Clear filtersQijun Wang, Chunqi Qian, Huacheng Zeng
In today's digitally connected world, keyboards remain the primary interface for inputting sensitive information, making them a persistent target for...
Xiaofeng Lin, Yukai Yang, Daniel Guo +3 more
Tool-using LLM agents interact with the world through actions that persist state in artifacts (e.g., workspace files or logs). Consequently,...
Kuncan Wang, Ziting Wang, Peizhuo Lv +4 more
Data agents integrate LLM-driven reasoning with relational data access, executable analytical tools, and multi-step workflow orchestration, making...
Lin-Fa Lee, Yi-Yu Chang, Chia-Mu Yu +1 more
WebMCP is a newly emerging protocol that enables websites to expose tools directly to AI agents, bypassing traditional user interfaces and...
Anlan Zheng, Tiantian Zhu
LLM-driven automated penetration testing agents are typically evaluated against static targets that neither detect nor respond to attacks, so their...
Eric Liang
Distributed event-based systems have become a common substrate for Internet-scale publish/subscribe services, IoT telemetry, cloud-native...
Zhiqing Ma, Zhonghao Xu, Dong Yu +3 more
Multi-turn jailbreak attacks pose a growing threat to LLMs by exploiting conversational dynamics such as gradual escalation and cross-turn...
Yuchen Zhang, Ning Xi, Pengbin Feng +5 more
Industrial Internet systems face increasing threats from sophisticated industrial control system (ICS) attacks, resulting in critical safety...
Dongrui Liu, Yu Li, Zhonghao Yang +47 more
Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources....
Qihan Deng, Minghua Zhang, Yang Yang +1 more
Pilot readback of Air Traffic Control (ATC) voice instructions is a primary safeguard against miscommunication in air transportation. However,...
Mohammadreza Hallajiyan, Xueren Ge, Athish Pranav Dharmalingam +4 more
The growing integration of artificial intelligence (AI) and machine learning (ML) in medical systems requires effective measures to address emerging...
Aman Priyanshu, Supriti Vijay, Esha Pahwa
LLM safety evaluations predominantly test models in isolation, yet deployed AI agents increasingly operate within persistent social environments...
Md Hafizur Rahman, Zafaryab Haider, Tanzim Mahfuz +1 more
Multi-agent LLM systems decompose workflows across agents, tools, shared context, memory, and decision gates. This modularity improves...
Faruk Alpay, Taylan Alpay
LLM agents process trusted instructions, retrieved records, and tool observations through a common generative channel. This conflates data flow with...
Miel Verkerken, Laurens D'hooge, Bruno Volckaert +2 more
Network Intrusion Detection Systems (NIDS) are now increasingly leveraging Machine Learning (ML) techniques to detect malicious network activities....
Bingyu Yan, Xiaoming Zhang, Jinyu Hou +4 more
While Large Language Model-based Multi-Agent Systems (LLM-MAS) demonstrate remarkable capabilities in solving complex tasks by orchestrating...
Mahavir Dabas, Jihyun Jeong, Ming Jin +1 more
Modern LLM agents combine long-term memory for personalization with tool-calling interfaces for taking actions in the world -- a combination...
Ting Liu
Skills are increasingly used to package agent instructions, workflows, scripts, and reference materials. In enterprise settings, however, skills...
Ze Sheng, Zhicheng Chen, Qingxiao Xu +2 more
Software vulnerabilities pose critical security threats, with nearly 50,000 CVEs reported in 2025. While Large Language Models (LLMs) show promise...
Mihai Christodorescu, Earlence Fernandes, Ashish Hooda +11 more
We take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted...
AI security research studies how AI and machine-learning systems can be attacked and defended — covering adversarial examples, prompt injection, model poisoning, training-data extraction, and the mitigations against them. AI Threat Alert curates this research from academic sources so security teams can track the threats behind emerging AI risks.
AI Threat Alert indexes 3,023+ papers on AI/ML security, classified across attack, defense, benchmark, survey, and tool categories and updated continuously.
Papers are sourced from arXiv, then classified by type and by relevance to real-world AI/ML threats, and cross-referenced with the CVEs and incidents they relate to.
Coverage spans adversarial attacks, model and system defenses, red-teaming benchmarks, literature surveys, and security tooling for LLMs, ML libraries, AI agents, and inference pipelines.
Every paper is filtered for AI security relevance and linked to the vulnerabilities, vendors, and incidents it relates to, so the research connects directly to operational threat intelligence.
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