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 1061–1080 of 1,175 papers
Clear filtersWentian Zhu, Zhen Xiang, Wei Niu +1 more
Unlike regular tokens derived from existing text corpora, special tokens are artificially created to annotate structured conversations during the...
Yutao Wu, Xiao Liu, Yinghui Li +5 more
Knowledge poisoning poses a critical threat to Retrieval-Augmented Generation (RAG) systems by injecting adversarial content into knowledge bases,...
Mengyao Zhao, Kaixuan Li, Lyuye Zhang +4 more
Recent advances in Large Language Models (LLMs) have brought remarkable progress in code understanding and reasoning, creating new opportunities and...
Yue Deng, Francisco Santos, Pang-Ning Tan +1 more
Deep learning based weather forecasting (DLWF) models leverage past weather observations to generate future forecasts, supporting a wide range of...
Ruizhe Zhu
The widespread application of large vision language models has significantly raised safety concerns. In this project, we investigate text prompt...
Mikhail Terekhov, Alexander Panfilov, Daniil Dzenhaliou +4 more
AI control protocols serve as a defense mechanism to stop untrusted LLM agents from causing harm in autonomous settings. Prior work treats this as a...
Yifan Zhu, Lijia Yu, Xiao-Shan Gao
In recent years, data poisoning attacks have been increasingly designed to appear harmless and even beneficial, often with the intention of verifying...
Milad Nasr, Nicholas Carlini, Chawin Sitawarin +11 more
How should we evaluate the robustness of language model defenses? Current defenses against jailbreaks and prompt injections (which aim to prevent an...
Brandon Lit, Edward Crowder, Daniel Vogel +1 more
AI chatbots are an emerging security attack vector, vulnerable to threats such as prompt injection, and rogue chatbot creation. When deployed in...
Ragib Amin Nihal, Rui Wen, Kazuhiro Nakadai +1 more
Large language models (LLMs) remain vulnerable to multi-turn jailbreaking attacks that exploit conversational context to bypass safety constraints...
Abhishek K. Mishra, Antoine Boutet, Lucas Magnana
Large Language Models (LLMs) are increasingly deployed across multilingual applications that handle sensitive data, yet their scale and linguistic...
Aofan Liu, Lulu Tang
Vision-Language Models (VLMs) have garnered significant attention for their remarkable ability to interpret and generate multimodal content. However,...
Muxi Diao, Yutao Mou, Keqing He +6 more
The safety of Large Language Models (LLMs) is crucial for the development of trustworthy AI applications. Existing red teaming methods often rely on...
Jiyang Qiu, Xinbei Ma, Yunqing Xu +2 more
The rapid deployment of large language model (LLM)-based agents in real-world applications has raised serious concerns about their trustworthiness....
Stanisław Pawlak, Jan Dubiński, Daniel Marczak +1 more
Model merging (MM) recently emerged as an effective method for combining large deep learning models. However, it poses significant security risks....
Kazuki Egashira, Robin Staab, Thibaud Gloaguen +2 more
Model pruning, i.e., removing a subset of model weights, has become a prominent approach to reducing the memory footprint of large language models...
Weisen Jiang, Sinno Jialin Pan
This paper introduces MetaDefense, a novel framework for defending against finetuning-based jailbreak attacks in large language models (LLMs). We...
Renhua Ding, Xiao Yang, Zhengwei Fang +3 more
Large vision-language models (LVLMs) enable autonomous mobile agents to operate smartphone user interfaces, yet vulnerabilities in their perception...
Christos Ziakas, Nicholas Loo, Nishita Jain +1 more
Automated red-teaming has emerged as a scalable approach for auditing Large Language Models (LLMs) prior to deployment, yet existing approaches lack...
Artur Horal, Daniel Pina, Henrique Paz +7 more
This paper presents the vision, scientific contributions, and technical details of RedTWIZ: an adaptive and diverse multi-turn red teaming framework,...
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