AI Threat Alert indexes 3,371+ 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 471 papers
Clear filtersTong Zhang, Zexin Li, Simin Chen +1 more
Jailbreak defenses are essential for protecting large language models (LLMs), but they can also introduce secondary costs that weaken model utility....
Mohammed Aldeen, Muhammad Sami Irfan, Sagar Dasgupta +3 more
Autonomous vehicles (AVs) depend on Global Navigation Satellite Systems (GNSS) for localization and navigation, making them vulnerable to spoofing...
Zhetong Zhang, Honghao Fu, Miao Xu +2 more
As Video Large Language Models are increasingly deployed in real-world applications, ensuring their safety alignment has become critical....
Yuxi Li, Zhibo Zhang, Kailong Wang +3 more
Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall...
Chenyu Zhou, Yabin Peng, Wei Huang +3 more
Federated Graph Neural Networks (FedGNNs) are highly vulnerable to backdoor poisoning, yet existing defenses typically rely on rule-based approaches...
Lena Libon, Ben Rank, Jehyeok Yeon +5 more
As AI agents begin to automate AI R&D, we need ways to assess whether their outputs are safe to deploy, even when the agents themselves may be...
Harry Rogers, Sally Shiels, Ashley Tomlinson +5 more
Objective Structured Clinical Examinations (OSCEs) are the gold standard for assessing clinical competence, yet scoring remains vulnerable to...
Behzad Ousat, Nikita Turkmen, Lalchandra Rampersaud +2 more
LLM-based browser agents are rapidly changing the threat landscape for web security. Unlike traditional automation frameworks that execute predefined...
Shasha Yu, Fiona Carroll, Barry L. Bentley
Large language models (LLMs) serving as planners in tool-using autonomous agents introduce dynamic reliability risks in multi-turn execution. While...
Xingfu Zhou, Pengfei Wang, Yuan Zhou +2 more
Agentic retrieval-augmented generation (RAG) systems increasingly retrieve external evidence and orchestrate tools for knowledge-intensive...
Darius Lim, Nathan Leow, Xin Wei Chia
Transcoders have recently emerged as a promising approach for mechanistic interpretability (MI), enabling circuit-level analysis of model behaviour....
Preeti Ravindra, Rahul Tiwari, Vincent Wolowski
AI software development agents are increasingly capable of modifying infrastructure and security critical systems, creating risks where an agent...
Yiheng Huang, Zhijia Zhao, Bihuan Chen +6 more
Open source software is vulnerable to supply-chain attacks through transitive dependencies, especially malicious code injected into NPM packages....
Leo Richter, Matt J. Kusner
Whistleblowers are a key safeguard against organizational wrongdoing, but the threat of retaliation deters reporting. Existing...
Zhenpeng Li
Large language model (LLM)-based intrusion detection systems (IDS) are increasingly studied for security monitoring, yet their robustness against...
Eunna Lee, Jungpyo Nam, Sunjun Hwang
When cast as the protector of a vulnerable user yet given no explicit capability boundary, a large language model (LLM) may respond not by...
Mingyang Sun, Guozhu Meng
Large language models (LLMs) are increasingly applied to vulnerability detection due to their strong code comprehension capabilities, but most...
Yuxin Huang, Ziming Hong, Mingming Gong +3 more
Recent diffusion-based video generation models have enabled high-quality personalized video customization through both tuning-based pipelines, which...
Qiyuan Fan, Zhi Li, Junjie Li +3 more
Filesystem isolation in container ecosystems is often weakened by cross-boundary path misresolution, causing path traversal (PaTra) vulnerabilities....
Quanyan Zhu
The paper introduces the Internet of Agentic Things (IoAT), an architectural framework that integrates agentic AI, IoT, cyber-physical systems,...
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 3,371+ 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