AI Threat Alert indexes 3,771+ 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 3481–3500 of 3,771 papers
Dominik 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...
Caelin Kaplan, Alexander Warnecke, Neil Archibald
AI models are being increasingly integrated into real-world systems, raising significant concerns about their safety and security. Consequently, AI...
Zicheng Liu, Lige Huang, Jie Zhang +3 more
The increasing autonomy of Large Language Models (LLMs) necessitates a rigorous evaluation of their potential to aid in cyber offense. Existing...
Ting Li, Yang Yang, Yipeng Yu +3 more
Adversarial attacks on knowledge graph embeddings (KGE) aim to disrupt the model's ability of link prediction by removing or inserting triples. A...
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...
Sean Oesch, Jack Hutchins, Luke Koch +1 more
In living off the land attacks, malicious actors use legitimate tools and processes already present on a system to avoid detection. In this paper, we...
Rui Xu, Jiawei Chen, Zhaoxia Yin +2 more
The widespread use of large language models (LLMs) and open-source code has raised ethical and security concerns regarding the distribution and...
Pengyu Zhu, Lijun Li, Yaxing Lyu +3 more
LLM-based multi-agent systems (MAS) demonstrate increasing integration into next-generation applications, but their safety in backdoor attacks...
Michael Schlichtkrull
When AI agents retrieve and reason over external documents, adversaries can manipulate the data they receive to subvert their behaviour. Previous...
Jiahao Liu, Bonan Ruan, Xianglin Yang +5 more
LLM-based agents have demonstrated promising adaptability in real-world applications. However, these agents remain vulnerable to a wide range of...
Vasilije Stambolic, Aritra Dhar, Lukas Cavigelli
Retrieval-Augmented Generation (RAG) increases the reliability and trustworthiness of the LLM response and reduces hallucination by eliminating the...
Alexander Sternfeld, Andrei Kucharavy, Ljiljana Dolamic
Large language Models (LLMs) have shown remarkable proficiency in code generation tasks across various programming languages. However, their outputs...
Zhuochen Yang, Kar Wai Fok, Vrizlynn L. L. Thing
Large language models have gained widespread attention recently, but their potential security vulnerabilities, especially privacy leakage, are also...
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...
Hyeseon An, Shinwoo Park, Suyeon Woo +1 more
The promise of LLM watermarking rests on a core assumption that a specific watermark proves authorship by a specific model. We demonstrate that this...
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...
Qizhou Peng, Yang Zheng, Yu Wen +2 more
Reinforcement learning (RL) has been an important machine learning paradigm for solving long-horizon sequential decision-making problems under...
Zonghuan Xu, Jiayu Li, Yunhan Zhao +3 more
Vision-Language-Action (VLA) models map multimodal perception and language instructions to executable robot actions, making them particularly...
Zaixi Zhang, Souradip Chakraborty, Amrit Singh Bedi +16 more
The rapid adoption of generative artificial intelligence (GenAI) in the biosciences is transforming biotechnology, medicine, and synthetic biology....
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 3,771+ 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