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 421–440 of 946 papers
Clear filtersNirajan Acharya, Gaurav Kumar Gupta
The Model Context Protocol (MCP), introduced by Anthropic in November 2024 and now governed by the Linux Foundation's Agentic AI Foundation, has...
Xaver Fink, Borja Fernandez Adiego, Daniele Mirarchi +4 more
In this paper, we analyze and improve the adversarial robustness of a convolutional neural network (CNN) that assists crystal-collimator alignment at...
Igor Maljkovic, Maria Rosaria Briglia, Iacopo Masi +2 more
Vision-Language Models (VLMs) have become essential for tasks such as image synthesis, captioning, and retrieval by aligning textual and visual...
Jiaren Peng, Zeqin Li, Chang You +17 more
The rapid advancement of Large Language Models (LLMs) has created new opportunities for Automated Penetration Testing (AutoPT), spawning numerous...
Shaofei Huang, Christopher M. Poskitt, Lwin Khin Shar
Cyber-physical systems often contend with incomplete architectural documentation or outdated information resulting from legacy technologies,...
Md Shamimul Islam, Luis G. Jaimes, Ayesha S. Dina
Network Intrusion Detection Systems (NIDS) face important limitations. Signature-based methods are effective for known attack patterns, but they...
Anes Abdennebi, Nadjia Kara, Laaziz Lahlou +1 more
Modern Security Operations Centers struggle with alert fatigue, fragmented tooling, and limited cross-source event correlation. Challenges that...
Wuyang Zhang, Shichao Pei
Tool-use large language model (LLM) agents are increasingly deployed to support sensitive workflows, relying on tool calls for retrieval, external...
Purva Chiniya, Kevin Scaria, Sagar Chaturvedi
Large language models (LLMs) remain susceptible to jailbreak and direct prompt-injection attacks, yet the strongest defensive filters frequently...
Geert Trooskens, Aaron Karlsberg, Anmol Sharma +6 more
We study compiled AI, a paradigm in which large language models generate executable code artifacts during a compilation phase, after which workflows...
Jiling Zhou, Aisvarya Adeseye, Seppo Virtanen +2 more
Chain-of-Thought (CoT) prompting has been used to enhance the reasoning capability of LLMs. However, its reliability in security-sensitive analytical...
Zijun Wang, Haoqin Tu, Letian Zhang +11 more
OpenClaw, the most widely deployed personal AI agent in early 2026, operates with full local system access and integrates with sensitive services...
Vinod Vaikuntanathan, Or Zamir
AI agents are increasingly deployed to interact with other agents on behalf of users and organizations. We ask whether two such agents, operated by...
Zhuohao Yu, Zhiwei Steven Wu, Adam Block
Inference-time compute scaling has emerged as a powerful paradigm for improving language model performance on a wide range of tasks, but the question...
Jia Chengyu, AprilPyone MaungMaung, Huy H. Nguyen +2 more
Recent advances in vision-language models (VLMs) trained on web-scale image-text pairs have enabled impressive zero-shot transfer across a diverse...
Shuyao Gao, Minghao Huang
The deployment of Large Language Models (LLMs) has ignited concerns about technological unemployment. Existing task-based evaluations predominantly...
Fariha Tanjim Shifat, Hariswar Baburaj, Ce Zhou +2 more
Large language models (LLMs) are increasingly embedded in open-source software (OSS) ecosystems, creating complex interactions among natural language...
Qiqing Huang, Xingyu Wang, Wanda Guo +2 more
Modern 5G user equipment (UE) processes Radio Resource Control (RRC) configuration messages during early control-plane exchanges, before...
Aobo Chen, Chenxu Zhao, Chenglin Miao +1 more
Large language models (LLMs) possess strong semantic understanding, driving significant progress in data mining applications. This is further...
Matteo Migliarini, Joaquin Pereira Pizzini, Luca Moresca +3 more
Instrumental convergence predicts that sufficiently advanced AI agents will resist shutdown, yet current safety training (RLHF) may obscure this risk...
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