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 84 papers
Clear filtersRyan Fetterman
LLMs fine-tuned for security classification are usually evaluated on held-out examples from the same distribution as their training data. We show...
Inderjeet Singh, Andrés Murillo, Motoyoshi Sekiya +2 more
Multimodal agentic retrieval-augmented generation (RAG) systems expand the attack surface beyond prompt injection to include text poisoning, image...
Praneeth Narisetty, Shiva Nagendra Babu Kore, Uday Kumar Reddy Kattamanchi +1 more
Recent work (2024 to 2026) has converged on a strategy for defending tool-using LLM agents against indirect prompt injection: rather than training...
Giulian Biolo, Michael Tezza, Yuanjun Gong +1 more
Software vulnerability remediation is a cognitively demanding task that requires specialized security expertise often lacking in general developers....
Hyejun Jeong, Dzung Pham, Amir Houmansadr +1 more
To better assist users with completing challenging tasks, AI agents mediate communications, access data, and interact with different APIs. Many...
Wenjie Zhu, Yabin Zhang, Liang Xu +3 more
While test-time adaptation (TTA) empowers vision-language models to adapt without costly retraining, it remains highly vulnerable to...
Yan-Lun Chen, Pin-Yu Chen, Chia-Mu Yu +3 more
Retrieval-Augmented Generation (RAG) systems are vulnerable to corpus poisoning attacks that manipulate model outputs through malicious retrieved...
Tianchen Guo, Chen Liu, Ling Chen +1 more
Multimodal Large Language Models (MLLMs) have shown remarkable progress in single-image perception, yet their ability to reason about complex...
Abrar Alotaibi, Raed Mughus, Moataz Ahmed
Large language models (LLMs) have demonstrated remarkable performance across natural language processing tasks, yet their deployment in high-stakes...
Kaicheng Shen, Lingyu Li, Wen Wu +3 more
AI companions powered by large language models increasingly interact with cognition-developing users, including children and adolescents, creating...
Andrew Stoltman, Johnathan Tang, Haipeng Cai
Large Language Models (LLMs) are increasingly used for automated vulnerability detection, but it remains unclear how program structure and semantics...
Yusheng Zheng, Tianyuan Wu, Quanzhi Fu +5 more
AI agents increasingly run in production through harnesses, the software around the LLM, including an engine that enforces safety and effectiveness...
Khanak Khandelwal
Scaling adversarial evaluation of large language models requires both a method for generating hard inputs and a reliable way to confirm that...
Ling Li, Bowen Liu, Zinuo Zhan +5 more
Pointing-based visual grounding requires models to precisely locate target objects by deciphering complex spatial relationships between the visual...
Shiding Zhu, Yudi Qi, Yajie Wang +6 more
Experience-driven self-evolution is critical for large language model (LLM) agents to improve through open-world interaction. However, existing...
Hojun Choi, Seulbin Hwang, Dae Jung Kim +3 more
Bird's-eye view (BEV) perception fuses multi-camera images into a unified top-down representation for autonomous driving. Despite recent progress,...
Onkar Shelar, Travis Desell
Large Language Models remain vulnerable to adversarial prompts that elicit harmful responses, and scaling red-teaming to cover a broad range of...
Yifei Zhao, Qian Lou, Mengxin Zheng
Vision-language models (VLMs) are increasingly used as perception-reasoning backbones for embodied intelligence in safety-critical physical systems,...
Bacem Etteib, Daniele Lunghi, Tégawendé F. Bissyandé
LLM agents increasingly load skills, file-based packages of natural-language instructions written by third parties and distributed through...
Vu Tuan Truong, Long Bao Le
Diffusion models (DMs), despite their impressive capabilities across a wide range of generative tasks, have been shown to be vulnerable to backdoor...
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