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 461–480 of 758 papers
Clear filtersMartin Odersky, Yaoyu Zhao, Yichen Xu +2 more
AI agents that interact with the real world through tool calls pose fundamental safety challenges: agents might leak private information, cause...
Oluseyi Olukola, Nick Rahimi
Machine learning based network intrusion detection systems are vulnerable to adversarial attacks that degrade classification performance under both...
Hsin Lin, Yan-Lun Chen, Ren-Hung Hwang +1 more
Backdoor attacks pose a critical threat to the security of deep neural networks, yet existing efforts on universal backdoors often rely on visually...
Yilian Liu, Xiaojun Jia, Guoshun Nan +6 more
Multimodal Large Language Models (MLLMs) have achieved remarkable performance but remain vulnerable to jailbreak attacks that can induce harmful...
Swapnil Parekh
Image captioning models are encoder-decoder architectures trained on large-scale image-text datasets, making them susceptible to adversarial attacks....
Jingyuan Xie, Wenjie Wang, Ji Wu +1 more
Supervised fine-tuning (SFT) is essential for the development of medical large language models (LLMs), yet prior poisoning studies have mainly...
Linxi Jiang, Zhijie Liu, Haotian Luo +1 more
Browser-use agents are widely used for everyday tasks. They enable automated interaction with web pages through structured DOM based interfaces or...
Qianxun Xu, Chenxi Song, Yujun Cai +1 more
Recent advances in text-to-video diffusion models have enabled high-fidelity and temporally coherent videos synthesis. However, current models are...
Qianxun Xu, Chenxi Song, Yujun Cai +1 more
Recent advances in text-to-video diffusion models have enabled high-fidelity and temporally coherent videos synthesis. However, current models are...
Kennedy Edemacu, Mohammad Mahdi Shokri
Retrieval-augmented generation (RAG) has emerged as a powerful paradigm for enhancing multimodal large language models by grounding their responses...
Xun Huang, Simeng Qin, Xiaoshuang Jia +6 more
As Large Language Models (LLMs) are increasingly used, their security risks have drawn increasing attention. Existing research reveals that LLMs are...
Tian Zhang, Yiwei Xu, Juan Wang +8 more
Large language model (LLM) agents increasingly rely on external tools and retrieval systems to autonomously complete complex tasks. However, this...
Marcus Graves
We introduce Reverse CAPTCHA, an evaluation framework that tests whether large language models follow invisible Unicode-encoded instructions embedded...
Zhonghao Zhan, Krinos Li, Yefan Zhang +1 more
Edge deployment of LLM agents on IoT hardware introduces attack surfaces absent from cloud-hosted orchestration. We present an empirical security...
Qianlong Lan, Anuj Kaul, Shaun Jones +1 more
Agentic large language model systems increasingly automate tasks by retrieving URLs and calling external tools. We show that this workflow gives rise...
Idan Habler, Vineeth Sai Narajala, Stav Koren +2 more
Retrieval-Augmented Generation (RAG) systems are essential to contemporary AI applications, allowing large language models to obtain external...
Bruce W. Lee, Chen Yueh-Han, Tomek Korbak
Frontier AI agents may pursue hidden goals while concealing their pursuit from oversight. Alignment training aims to prevent such behavior by...
Sarthak Munshi, Manish Bhatt, Vineeth Sai Narajala +4 more
While prior work has focused on projecting adversarial examples back onto the manifold of natural data to restore safety, we argue that a...
Zheng Gao, Xiaoyu Li, Zhicheng Bao +2 more
Generative images have proliferated on Web platforms in social media and online copyright distribution scenarios, and semantic watermarking has...
Inderjeet Singh, Vikas Pahuja, Aishvariya Priya Rathina Sabapathy +8 more
Current stateless defences for multimodal agentic RAG fail to detect adversarial strategies that distribute malicious semantics across retrieval,...
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