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 361–380 of 1,175 papers
Clear filtersHaozhen Wang, Haoyue Liu, Jionghao Zhu +3 more
Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of applications. However, their practical deployment is...
Ahmed Lekssays
Large Language Models (LLMs) face critical challenges when analyzing security vulnerabilities in real world codebases: token limits prevent loading...
Alexander Panfilov, Peter Romov, Igor Shilov +3 more
LLM agents like Claude Code can not only write code but also be used for autonomous AI research and engineering \citep{rank2026posttrainbench,...
Joseph G. Zalameda, Megan A. Witherow, Alexander M. Glandon +2 more
Machine learning models trained on small data sets for security applications are especially vulnerable to adversarial attacks. Person identification...
Yulin Shen, Xudong Pan, Geng Hong +1 more
Recent advances in the Model Context Protocol (MCP) have enabled large language models (LLMs) to invoke external tools with unprecedented ease. This...
Qianlong Lan, Anuj Kaul
Deploying large language models (LLMs) as autonomous browser agents exposes a significant attack surface in the form of Indirect Prompt Injection...
Xingyu Zhu, Beier Zhu, Shuo Wang +4 more
As vision-language models (VLMs) are increasingly deployed in open-world scenarios, they can be easily induced by visual jailbreak attacks to...
Huamin Chen, Xunzhuo Liu, Bowei He +5 more
Over the past year, the vLLM Semantic Router project has released a series of work spanning: (1) core routing mechanisms -- signal-driven routing,...
Kwanyoung Kim, Byeongsu Sim
Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models with human preferences, inspiring the...
Zihui Chen, Yuling Wang, Pengfei Jiao +4 more
Text-attributed graphs (TAGs) enhance graph learning by integrating rich textual semantics and topological context for each node. While boosting...
Yasamin Medghalchi, Milad Yazdani, Amirhossein Dabiriaghdam +7 more
Ultrasound is widely used in clinical practice due to its portability, cost-effectiveness, safety, and real-time imaging capabilities. However, image...
Abed K. Musaffar, Ambuj Singh, Francesco Bullo
Large language models (LLMs) are increasingly deployed in human-AI teams as support agents for complex tasks such as information retrieval,...
Matta Varun, Ajay Kumar Dhakar, Yuan Hong +1 more
Graph neural network (GNN) is a powerful tool for analyzing graph-structured data. However, their vulnerability to adversarial attacks raises serious...
Yusheng Zheng, Yiwei Yang, Wei Zhang +1 more
LLM agent frameworks increasingly offer checkpoint-restore for error recovery and exploration, advising developers to make external tool calls safe...
Wenjing Hong, Zhonghua Rong, Li Wang +5 more
Large Language Models (LLMs) have been widely deployed, especially through free Web-based applications that expose them to diverse user-generated...
Vicenç Torra, Maria Bras-Amorós
Memory poisoning attacks for Agentic AI and multi-agent systems (MAS) have recently caught attention. It is partially due to the fact that Large...
Qi Luo, Minghui Xu, Dongxiao Yu +1 more
Many learning systems now use graph data in which each node also contains text, such as papers with abstracts or users with posts. Because these...
Dong-Xiao Zhang, Hu Lou, Jun-Jie Zhang +2 more
Adversarial vulnerability in vision and hallucination in large language models are conventionally viewed as separate problems, each addressed with...
Toan Tran, Olivera Kotevska, Li Xiong
Membership inference attacks (MIAs), which enable adversaries to determine whether specific data points were part of a model's training dataset, have...
Aravind Krishnan, Karolina Stańczak, Dietrich Klakow
As Spoken Language Models (SLMs) integrate speech and text modalities, they inherit the safety vulnerabilities of their LLM backbone and an expanded...
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