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 1–20 of 36 papers
Clear filtersAbrar Alotaibi, Moataz Ahmed
Adversarial evaluation of AI systems has matured along four largely disconnected tracks: diffusion-based attacks on text and large language models...
Nicola Franco
We evaluate the adversarial robustness of two frontier large language models (LLMs) developed by Anthropic, Fable 5 and Opus 4.8, against four...
Yimeng Chen, Zhe Ren, Firas Laakom +3 more
Large language model (LLM)-based search agents synthesize open-web content into actionable recommendations on behalf of users, creating a risk that...
Xinyu Zhao, Rana Muhammad Shahroz Khan, Zhen Xu +2 more
The integration of Large Language Models (LLMs) and Multimodal LLMs (MLLMs) into scientific peer-review workflows introduces novel and significant...
Bo-Han Feng, Yu-Hsuan Li Liang, Chien-Feng Liu +2 more
Large Audio Language Models (LALMs) expand jailbreak risks from token-level prompting to the full speech perception-to-reasoning pipeline, where...
Zisis Tsiatsikas, Alexandros Fakis, Georgios Karopoulos +2 more
The need for secure and private Artificial Intelligence (AI) and Machine Learning (ML) on edge and mobile devices has increased the necessity of...
Lingyao Li, Junjie Xiong, Changjia Zhu +5 more
Large language models (LLMs) are increasingly used in academic peer review, yet their reliability, alignment with human judgment, and robustness to...
Karthik Raghu Iyer, Yazdan Jamshidi, Nicholas Bray +1 more
We introduce a reusable framework for auditing whether LLM attack benchmarks collectively cover the threat surface: a 4$\times$6 Target $\times$...
Lei Jiang, Fan Chen
Variational quantum algorithms (VQAs) are a central paradigm for noisy intermediate-scale (NISQ) quantum computing, yet their reliance on predesigned...
Monika Jotautaitė, Maria Angelica Martinez, Ollie Matthews +1 more
We introduce a red-teaming methodology that exposes harder-to-catch attacks for coding-agent monitors, suggesting that current practices may...
Feiyue Xu, Hongsheng Hu, Chaoxiang He +9 more
Large Language Models (LLMs) have achieved remarkable success but remain highly susceptible to jailbreak attacks, in which adversarial prompts coerce...
Luyao Xu, Xiang Chen
Autonomous agent frameworks built upon large language models (LLMs) are evolving into complex, tool-integrated, and continuously operating systems,...
Yuming Xu, Mingtao Zhang, Zhuohan Ge +5 more
Retrieval-augmented generation (RAG) significantly enhances large language models (LLMs) but introduces novel security risks through external...
Charafeddine Mouzouni
LLM agents with tool access can discover and exploit security vulnerabilities. This is known. What is not known is which features of a system prompt...
Bhavuk Jain, Sercan Ö. Arık, Hardeo K. Thakur
Multimodal large language models (MLLMs) integrate information from multiple modalities such as text, images, audio, and video, enabling complex...
Shouqiao Wang, Marcello Politi, Samuele Marro +1 more
As agentic systems move into real-world deployments, their decisions increasingly depend on external inputs such as retrieved content, tool outputs,...
Dimitris Mitropoulos, Nikolaos Alexopoulos, Georgios Alexopoulos +1 more
Security code reviews increasingly rely on systems integrating Large Language Models (LLMs), ranging from interactive assistants to autonomous agents...
Fabrizio Dimino, Bhaskarjit Sarmah, Stefano Pasquali
The rapid adoption of large language models (LLMs) in financial services introduces new operational, regulatory, and security risks. Yet most...
Shruti Srivastava, Kiranmayee Janardhan, Shaurya Jauhari
Cybersecurity threats are becoming increasingly sophisticated, making traditional defense mechanisms and manual red teaming approaches insufficient...
Kunal Mukherjee
Trusted Execution Environments (TEEs) (e.g., Intel SGX and ArmTrustZone) aim to protect sensitive computation from a compromised operating system,...
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