AI Threat Alert indexes 4,319+ 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 21–40 of 609 papers
Clear filtersChengquan Guo, Xiaodong Liu, Weiwei Yang +7 more
LLM agents are increasingly adopted in long-horizon tasks and interact with diverse external environments. Despite their growing capabilities, these...
Pengfei Zeng, Changhua Luo, Penghui Li
Large language models (LLMs) have enabled more effective vulnerability scanning of web applications. However, these capabilities also make it...
Vincess Dongmo, Astride Melvin Fokam Ninyim
Multi-relational graph detectors learn from clean data how much to trust each relation, but an adversary pays a different price to manipulate each...
Haiyong Tang, Hanzhou Wu, Xinpeng Zhang +1 more
Large language models (LLMs) are valuable digital assets, yet their weights can be easily modified after unauthorized acquisition, making model...
Puyuan Yang, Shaoxuan Dong, Liujie Wu +2 more
The stance expressed in responses from retrieval-augmented generation systems is significantly influenced by the stance distribution of the retrieved...
Chieh-Yuan Chang, Guan-Wei Chen, Chia-Yi Hsu +3 more
AI coding agents routinely clone repositories, install packages, and read source code obtained from the Web, so publicly hosted code becomes part of...
Chao Gu, Quanyan Zhu
This paper studies the problem of safe tool execution for large language model (LLM) agents under prompt injection. Using Petri nets, we formalize...
Ke Zhu, Yanli Chen, Ling Xiong +2 more
With the rapid adoption of large language models (LLMs) in text generation applications, it has become increasingly difficult to trace generated...
Yahao Ren, Jian Lou, Huadi Zheng +1 more
Instruction-data selectors choose which instruction-following records are used for fine-tuning, improving alignment quality, raising training...
Luca Zanolini
Before an AI agent takes a consequential action, such as paying, messaging or changing code, several monitors check it. Their verdicts are combined...
Tanqiu Jiang, Min Bai, Sadat Shahriar +2 more
Persistent memory is a largely undefended surface for injection and poisoning, and the same risk limits memory sharing among agents. We present...
Vita Santa Barletta, Danilo Caivano, Gabriel Cellammare +3 more
The increasing complexity of Industrial Control Systems (ICS) and their integration with IT infrastructures has significantly expanded the cyber...
Vasisht Duddu, Adam Caulfield, Xi He
Regulations require companies to run AI models in a regulatory sandbox, an isolated environment that enables monitoring model behavior by regulators,...
Nataša Krčo, Euodia Dodd, Peter Romov +1 more
Speech models are increasingly used as an interface to AI systems, from transcription tools to voice agents. Existing audio backdoors require an...
Walid El Maouaki, Mohammad Izen, Nouhaila Innan +2 more
Quantum machine-learning (QML) models are increasingly considered for security applications, yet their adversarial robustness in malware analysis...
Anastasiia Kucherenko, Francois Brouchoud, Dimitri Percia David +1 more
Confidentiality requirements increasingly push legal professionals toward small, on-device LLMs that keep case data in-house, used for everyday tasks...
Manohar Kaul, Sadbhavana Babar, Aditya Ramesh +4 more
Adversarial vulnerability persists across modern vision architectures from CNNs to vision language models (VLMs), yet existing detection methods rely...
Yuchen Chen, Wei Cheng, Yuan Xiao +7 more
Retrieval-Augmented Generation (RAG) enables large language models to access external knowledge during inference, but its reliance on external...
Chang Zhou, Jiarun Zhou, Xingtong Yu +3 more
Generator--critic trading systems pair an LLM-based trader that makes trading decisions with a red team agent that evaluates these decisions and...
Vasileios Perifanis, Nikolaos Pavlidis
Federated learning (FL) is increasingly used to adapt a pretrained, centrally fine-tuned model to data that remain on user devices, beyond training 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 4,319+ 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