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 1–20 of 319 papers
Clear filtersLiwei Liu, Tianzhu Han, Zijian Liu +2 more
With the rapid evolution of LLM-driven agents, Model Context Protocol (MCP), an open protocol bridging LLMs with external tools, has quickly become...
Manar Alsaid, Chimdumebi Nebolisa, Faris Abbas
Security misconfigurations in Terraform Infrastructure-as-Code are a growing risk in cloud deployments, and large language models are increasingly...
A. S. Ushakov, Yu. N. Berdinsk
We propose a complete architectural blueprint for safe artificial general intelligence based on a closed reentry loop (D <-> I cycle). In contrast to...
Seth Dobrin, Łukasz Chmiel
AI agents are granted access to tools, APIs, and other infrastructure, making them active principals in those systems. The dominant approach places...
Balamurugan Palanisamy, G S S Chalapathi, Vikas Hassija +1 more
Retrieval-Augmented Generation (RAG) has emerged as a dominant paradigm for enhancing large language models with external knowledge. By coupling...
Yarin Yerushalmi Levi, Roy Betser, Amit Giloni +5 more
Agentic AI systems powered by large language models (LLMs) are rapidly evolving into autonomous decision-making systems, exposing attack vectors...
Yinpeng Wu, Yitong Chen, Lixiang Wang +3 more
Device-side Large Language Models (LLMs) have grown explosively, offering stronger privacy and higher availability than their cloud-side...
Ruixiao Lin, Xinhao Deng, Qingming Li +12 more
Self-evolving LLM agent systems, which autonomously update their model parameters, memory, tools, and architectures, introduce a qualitatively new...
Reza Soosahabi, Vivek Namsani
Agentic AI systems increasingly rely on language-model components to interpret instructions, process external data, invoke tools, and coordinate with...
Gulshan Saleem, Nisar Ahmed, Muhammad Imran Zaman +1 more
Prompt injection is ranked as the most critical vulnerability in large language model (LLM) deployments by the OWASP Top 10 for LLM Applications, yet...
Nils Loose, Jonas Sander, Felix Mächtle +1 more
Large language models (LLMs) are increasingly deployed in sensitive settings such as software engineering, where their outputs directly shape...
Xinjian Luo, Hongyan Chang, Jianxin Wei +5 more
Distributed large language model (LLM) inference frameworks connect isolated consumer-grade devices for large-scale model inference, substantially...
Yuchuan Tian, Mengyu Zheng, Haocheng Mei +5 more
Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent...
Xinru Liu, Xianglong Zhang, Di Cai +3 more
Injecting malicious knowledge into retrieval-augmented generation (RAG) systems can manipulate retrieved evidence and mislead downstream generation,...
David Huang, Jaewon Chang, Avidan Shah +2 more
The Rapid Response (RR) framework, deployed in production systems, including Anthropic's ASL-3 safeguards, continuously improves jailbreak-detection...
Jiaqi Luo, Jiarun Dai, Zhile Chen +8 more
Nowadays, the autonomous execution of cyberattacks capable of causing substantial real-world harm is widely regarded as one of the critical red lines...
Md Jafrin Hossain, Mohammad Arif Hossain, Weiqi Liu +1 more
Agentic large language model systems that autonomously invoke tools, maintain persistent memory, and execute multi-step plans are increasingly...
Tarun Sharma
Retrieval-augmented generation (RAG) agents increasingly run with persistent memory that accumulates across user sessions. This creates a new attack...
Lin Sun, Heming Zhang, Xiangzheng Zhang
Production LLM systems accumulate reusable operational experience, but the practical deployment issue is not merely whether such experience can help....
Ge Shi, Jun Yin, Donglin Xie +3 more
Jailbreak attacks expose persistent safety weaknesses in large language models (LLMs), but existing stateless single-turn methods face a trade-off:...
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