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 781–800 of 866 papers
Clear filtersDominik Schwarz
The security of Large Language Model (LLM) applications is fundamentally challenged by "form-first" attacks like prompt injection and jailbreaking,...
Sarah Ball, Andreas Haupt
Generative models are increasingly paired with safety classifiers that filter harmful or undesirable outputs. A common strategy is to fine-tune the...
Jiayu Ding, Lei Cui, Li Dong +2 more
Recent advances in Large Language Models (LLMs) show that extending the length of reasoning chains significantly improves performance on complex...
Jian Wang, Xiaofei Xie, Qiang Hu +4 more
Automated Program Repair (APR) plays a critical role in enhancing the quality and reliability of software systems. While substantial progress has...
Jidong Li, Lingyong Fang, Haodong Zhao +2 more
Multimodal large language models (MLLMs) have witnessed astonishing advancements in recent years. Despite these successes, MLLMs remain vulnerable to...
Norbert Tihanyi, Bilel Cherif, Richard A. Dubniczky +2 more
In this paper, we present the first large-scale study exploring whether JavaScript code generated by Large Language Models (LLMs) can reveal which...
Mohan Zhang, Yihua Zhang, Jinghan Jia +3 more
Modern large reasoning models (LRMs) exhibit impressive multi-step problem-solving via chain-of-thought (CoT) reasoning. However, this iterative...
Shaolun Liu, Sina Marefat, Omar Tsai +4 more
GraphQL's flexible query model and nested data dependencies expose APIs to complex, context-dependent vulnerabilities that are difficult to uncover...
Zonghao Ying, Yangguang Shao, Jianle Gan +9 more
Large vision-language model (LVLM)-based web agents are emerging as powerful tools for automating complex online tasks. However, when deployed in...
Ines Altemir Marinas, Anastasiia Kucherenko, Alexander Sternfeld +1 more
The performance of Large Language Models (LLMs) is determined by their training data. Despite the proliferation of open-weight LLMs, access to LLM...
Yongding Tao, Tian Wang, Yihong Dong +4 more
Data contamination poses a significant threat to the reliable evaluation of Large Language Models (LLMs). This issue arises when benchmark samples...
Xiaonan Si, Meilin Zhu, Simeng Qin +7 more
Retrieval-augmented generation (RAG) systems enhance large language models (LLMs) with external knowledge but are vulnerable to corpus poisoning and...
Debeshee Das, Luca Beurer-Kellner, Marc Fischer +1 more
The increasing adoption of LLM agents with access to numerous tools and sensitive data significantly widens the attack surface for indirect prompt...
Haoran Ou, Kangjie Chen, Xingshuo Han +4 more
Large Language Models (LLMs) have been augmented with web search to overcome the limitations of the static knowledge boundary by accessing up-to-date...
Eric Hanchen Jiang, Weixuan Ou, Run Liu +8 more
Safety alignment of large language models currently faces a central challenge: existing alignment techniques often prioritize mitigating responses to...
Rupam Patir, Keyan Guo, Haipeng Cai +1 more
The code generation capabilities of Large Language Models (LLMs) have transformed the field of software development. However, this advancement also...
Shen Dong, Mingxuan Zhang, Pengfei He +4 more
Large Language Model (LLM)-based Multi-Agent Systems (MAS) have emerged as a powerful paradigm for tackling complex, multi-step tasks across diverse...
Junjie Li, Fazle Rabbi, Bo Yang +2 more
Although Large Language Models (LLMs) show promising solutions to automated code generation, they often produce insecure code that threatens software...
Riku Mochizuki, Shusuke Komatsu, Souta Noguchi +1 more
We analyze answers generated by generative engines (GEs) from the perspectives of citation publishers and the content-injection barrier, defined as...
Zhiyuan Wei, Xiaoxuan Yang, Jing Sun +1 more
The increasing complexity of modern software systems exacerbates the prevalence of security vulnerabilities, posing risks of severe breaches and...
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