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 2881–2900 of 3,023 papers
Milad Nasr, Yanick Fratantonio, Luca Invernizzi +7 more
As deep learning models become widely deployed as components within larger production systems, their individual shortcomings can create system-level...
Niloofar Mireshghallah, Tianshi Li
The discourse on privacy risks in Large Language Models (LLMs) has disproportionately focused on verbatim memorization of training data, while a...
John Hawkins, Aditya Pramar, Rodney Beard +1 more
Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation...
Youwei Bao, Shuhan Yang, Hyunsoo Yang
Deterministic pseudo random number generators (PRNGs) used in generative artificial intelligence (GAI) models produce predictable patterns vulnerable...
Zhenyu Pan, Yiting Zhang, Zhuo Liu +13 more
LLM-based multi-agent systems excel at planning, tool use, and role coordination, but their openness and interaction complexity also expose them to...
Luoxi Tang, Yuqiao Meng, Ankita Patra +3 more
Large Language Models (LLMs) are intensively used to assist security analysts in counteracting the rapid exploitation of cyber threats, wherein LLMs...
Jaiden Fairoze, Sanjam Garg, Keewoo Lee +1 more
As large language models (LLMs) advance, ensuring AI safety and alignment is paramount. One popular approach is prompt guards, lightweight mechanisms...
Isha Gupta, Rylan Schaeffer, Joshua Kazdan +2 more
The field of adversarial robustness has long established that adversarial examples can successfully transfer between image classifiers and that text...
Luca Cotti, Idilio Drago, Anisa Rula +2 more
System logs represent a valuable source of Cyber Threat Intelligence (CTI), capturing attacker behaviors, exploited vulnerabilities, and traces of...
Shoumik Saha, Jifan Chen, Sam Mayers +3 more
Code-capable large language model (LLM) agents are increasingly embedded into software engineering workflows where they can read, write, and execute...
Yinuo Liu, Ruohan Xu, Xilong Wang +2 more
Multiple prompt injection attacks have been proposed against web agents. At the same time, various methods have been developed to detect general...
Muhammad Faheemur Rahman, Wayne Burleson
Memristive crossbar arrays enable in-memory computing by performing parallel analog computations directly within memory, making them well-suited for...
Xiangfang Li, Yu Wang, Bo Li
With the rapid advancement of large language models (LLMs), ensuring their safe use becomes increasingly critical. Fine-tuning is a widely used...
Zhengliang Shi, Ruotian Ma, Jen-tse Huang +14 more
Large language models (LLMs) are increasingly entrusted with high-stakes decisions that affect human welfare. However, the principles and values that...
Alexandrine Fortier, Thomas Thebaud, Jesús Villalba +2 more
Large Language Models (LLMs) and their multimodal extensions are becoming increasingly popular. One common approach to enable multimodality is to...
Guobin Shen, Dongcheng Zhao, Haibo Tong +3 more
Ensuring Large Language Model (LLM) safety remains challenging due to the absence of universal standards and reliable content validators, making it...
Yicheng Lang, Yihua Zhang, Chongyu Fan +3 more
Large language model (LLM) unlearning aims to surgically remove the influence of undesired data or knowledge from an existing model while preserving...
Chen-An Li, Tzu-Han Lin, Hung-yi Lee
Large audio-language models (LALMs) unify speech and text processing, but their robustness in noisy real-world settings remains underexplored. We...
Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang +1 more
Existing data poisoning attacks on retrieval-augmented generation (RAG) systems scale poorly because they require costly optimization of poisoned...
Shojiro Yamabe, Jun Sakuma
Diffusion language models (DLMs) generate tokens in parallel through iterative denoising, which can reduce latency and enable bidirectional...
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