AI Threat Alert indexes 4,319+ 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 735 papers
Clear filtersYang Zhou, Krish Agarwal, Zhuoming Chen +16 more
Frontier AI agents increasingly succeed on realistic, long-horizon tasks and are beginning to improve the systems through which they operate. Yet...
Sujan Maharjan, Lu Liu
Large Language Models (LLMs) have emerged as primary interfaces for factual retrieval, yet current evaluation paradigms rely almost exclusively on...
Hesham Elbakoury, Deep Shah, Ankur Sharma
Frontier large language models (LLMs) deliver the strongest response quality but carry per-token prices often more than an order of magnitude above...
Howard Zhang, Chuck Arvin, Logan Brown +3 more
Deploying LLM-based analytics agents in enterprise settings requires evaluation frameworks that can reliably detect failures across complex,...
Weifeng Yuan, Zifan Chen, Yucheng Zhang +3 more
Artificial intelligence agents increasingly automate cybersecurity tasks, including offensive operations. Frequent attacks across the web make...
Haoyi Wu, Yunkai Dang, Wanyu Zhang +2 more
Large language models (LLMs) have shown strong capabilities across diverse applications, making both safety and utility essential for reliable...
Xinyi Wu, Jiagui Chen, JiaYi Dong +5 more
Web agents extend LLMs from text generation to real-world web interaction by relying on execution harnesses that interpret user goals, perceive...
Marco Arazzi, Mert Cihangiroglu, Antonino Nocera
Swarm Learning improves resilience and removes the need for a single trusted coordinator by distributing model aggregation and validation across...
E. Kelly Buchanan, Crystal Zhou, Scott W. Linderman +1 more
Coding agents are among the most economically consequential deployments of LLMs to date, making reliable evaluation increasingly important. Yet even...
Jianhong Ma, Wenhao Li, Xixing Li +2 more
Early assessment of Common Vulnerability Scoring System (CVSS) vectors from Open Source Intelligence (OSINT) can reduce the delay between initial...
Chao Pan
Fast adversarial training (FAT) makes robust training affordable by replacing the multi-step attack with a single-step one, but it suffers from...
Annabella Chow, Jinhao Zhu, Sylvie Venuto +5 more
Web agents commonly follow the ReAct paradigm, selecting each action from runtime observations that inherently mix trusted and untrusted content....
Yutao Wu, Xiao Liu, Ming Wen +3 more
Web agents increasingly browse, shop, and manage accounts on behalf of their users. Prior work has shown that they can be misled by adversarial...
Yutao Wu, Xiao Liu, Ming Wen +3 more
Web agents increasingly browse, shop, and manage accounts on behalf of their users. Prior work has shown that they can be misled by adversarial...
Shuaidong Li, Chenhao Lin, Xinshan Yang +3 more
System prompt is a critical intellectual property of large language model (LLM) services. To analyze its leakage, prompt extraction attacks have been...
Wei-Lin Chen, Zhepei Wei, Xinyu Zhu +3 more
Large language model (LLM) coding agents increasingly operate with shell access, allowing them to write scripts, move files, alter permissions, and...
Hasan Kaplan, Indika Kumara, Willem-Jan van den Heuvel +1 more
Large language models (LLMs) using retrieval-augmented generation (RAG) can synthesize Amazon Web Services (AWS) Identity and Access Management (IAM)...
Yiwei Zha, Qingyu Meng, Herbert Bos +1 more
LLM agents compact long histories to fit their context windows, but the compacted context must still carry the operating rules that govern later...
Shengyan Huo, Peihai Jiang, Xixiang Lyu +1 more
Third-party LoRA adapters introduce serious backdoor risks: malicious adapters can maintain normal task performance while embedding hidden,...
Javad Mohammad Alizadeh, Huanmei Wu
LLM agents are increasingly built into data-analysis software, yet little evidence shows how reliably they preprocess clinical data or whether the...
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 4,319+ 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