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 562 papers
Clear filtersYi Liu, Zhihao Chen, Yanjun Zhang +5 more
Third-party agent skills extend LLM-based agents with instruction files and executable code that run on users' machines. Skills execute with user...
Junhyeok Lee, Han Jang, Kyu Sung Choi
Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems are increasingly integrated into clinical workflows; however, prompt...
Navita Goyal, Hal Daumé
Model steering, which involves intervening on hidden representations at inference time, has emerged as a lightweight alternative to finetuning for...
José Ramón Pareja Monturiol, Juliette Sinnott, Roger G. Melko +1 more
Machine learning in clinical settings must balance predictive accuracy, interpretability, and privacy. Models such as logistic regression (LR) offer...
Rui Jia, Ruiyi Lan, Fengrui Liu +7 more
Large language models (LLMs) have advanced the development of personalized learning in education. However, their inherent generation mechanisms often...
Nelu D. Radpour
Contemporary benchmarks for agentic artificial intelligence (AI) frequently evaluate safety through isolated task-level accuracy thresholds,...
Ruixin Yang, Ethan Mendes, Arthur Wang +4 more
Vision-language models (VLMs) have demonstrated strong performance in image geolocation, a capability further sharpened by frontier multimodal large...
Casey Ford, Madison Van Doren, Emily Dix
Multimodal large language models (MLLMs) are increasingly deployed in real-world systems, yet their safety under adversarial prompting remains...
Mengru Wang, Zhenqian Xu, Junfeng Fang +4 more
Large Language Models (LLMs) can acquire unintended biases from seemingly benign training data even without explicit cues or malicious content....
Debargha Ganguly, Sreehari Sankar, Biyao Zhang +8 more
Current approaches to LLM safety fundamentally rely on a brittle cat-and-mouse game of identifying and blocking known threats via guardrails. We...
Bibhabasu Mandal, Sagnik Nandy
In sensitive applications involving relational datasets, protecting information about individual links from adversarial queries is of paramount...
Omar Abdelnasser, Fatemah Alharbi, Khaled Khasawneh +2 more
Safety alignment in Language Models (LMs) is fundamental for trustworthy AI. However, while different stakeholders are trying to leverage Arabic...
Hao Li, Ruoyao Wen, Shanghao Shi +2 more
AI agents that autonomously interact with external tools and environments show great promise across real-world applications. However, the external...
Tomer Kordonsky, Maayan Yamin, Noam Benzimra +2 more
LLMs are increasingly used for code generation, but their outputs often follow recurring templates that can induce predictable vulnerabilities. We...
Najmul Hasan, Prashanth BusiReddyGari
The Uniform Resource Locator (URL), introduced in a connectivity-first era to define access and locate resources, remains historically limited,...
Rodrigo Tertulino, Ricardo Almeida, Laercio Alencar
The digitization of healthcare has generated massive volumes of Electronic Health Records (EHRs), offering unprecedented opportunities for training...
Hoang M. Ngo, Tre' R. Jeter, Incheol Shin +3 more
Quantum Machine Learning (QML) is becoming increasingly prevalent due to its potential to enhance classical machine learning (ML) tasks, such as...
Wenjin Hou, Wei Liu, Han Hu +3 more
Multimodal Large Language Models (MLLMs) have shown remarkable proficiency on general-purpose vision-language benchmarks, reaching or even exceeding...
Yen-Shan Chen, Zhi Rui Tam, Cheng-Kuang Wu +1 more
Current evaluations of LLM safety predominantly rely on severity-based taxonomies to assess the harmfulness of malicious queries. We argue that this...
Yangfan Deng, Anirudh Nakra, Min Wu
3D content acquisition and creation are expanding rapidly in the new era of machine learning and AI. 3D Gaussian Splatting (3DGS) has become a...
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