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 61–80 of 4,319 papers
Fazong Wu, Xin Wang, Ming Yang +2 more
As large language models (LLMs) are increasingly deployed as general-purpose conversational assistants, they must handle diverse user requests while...
Xiaobo Chen, Genliang Zhu, Ziyuan Wang +1 more
Enterprise AI agents increasingly split a user's request across subagents and merge their results, and each handoff can summarize away, alter or...
Jaime Ruiz-Serra, Tomáš Gavenčiak, Jobst Heitzig
Power matters for AI safety. Optimal agents tend to acquire power across a wide range of objectives (instrumental convergence). As we embed AI agents...
Woosang Lim, Yeseul Chang, Jaewoo Lee
Tool-using agents act on email, files, and payments, so an instruction hidden in a web page or a shared document can make an agent send data or money...
Hong kyu Lee, Kai Shu, Li Xiong
Large vision-language models (LVLMs) are vulnerable to compositional harm: an image and a prompt that are benign in isolation become harmful through...
Andrew W. Lo, Chaoyi Zhao
Evolution has shaped intelligence for billions of years. Artificial intelligence (AI) now raises a striking possibility: intelligence may begin to...
Guoqin Xiong, Shengtao Wen, Xiang Chen +5 more
Tool-using large language model (LLM) agents translate model outputs into consequential actions, turning indirect prompt injection into an...
Chaomeng Lu, Pooya Rostami Mazrae, Bert Lagaisse
Automated vulnerability detection is critical for securing modern software systems, yet existing learning-based approaches often treat functions as...
Hamid Dashtbani, Alexandra Dmitrienko
Large language models (LLMs) undergo safety alignment to prevent harmful generations, yet they remain vulnerable to jailbreak attacks. Recent work...
Jianhong Ma, Wenhao Li, Xixing Li +2 more
Early assessment of Common Vulnerability Scoring System (CVSS) vectors from Open Source Intelligence (OSINT) can reduce the delay between initial...
Quentin Le Roux, Marti Jimenez, Yannick Teglia +1 more
The protection of mature, multi-stage Face Recognition Systems is crucial to system providers. This technical report targets the threat model most...
Norbert Sándor Szolnoki, Gábor Antal
Recent studies report promising results from supervised fine-tuning of pre-trained code language models for automated vulnerability detection on...
Jorge García-Carrasco, Javier Sanchis, Álvaro Navarro +2 more
Open-weight language models that fit on a single consumer GPU are becoming capable on a growing range of tasks, and they matter because they can run...
Erfan Baghaei Potraghloo, Saeid Shokoufa, Seyedarmin Azizi +4 more
Mixture-of-Experts (MoE) language models send each token through a few of many expert subnetworks. Serving methods make these models faster by...
Martin Pinzger, Katharina Stengg, Christian Macho +2 more
Many recent approaches for vulnerability detection use large language models (LLMs) to classify functions as vulnerable or benign, leaving developers...
Chao Pan
Fast adversarial training (FAT) makes robust training affordable by replacing the multi-step attack with a single-step one, but it suffers from...
Annabella Chow, Jinhao Zhu, Sylvie Venuto +5 more
Web agents commonly follow the ReAct paradigm, selecting each action from runtime observations that inherently mix trusted and untrusted content....
Shumpei Shiina, Haruka Takahashi, Kento Sasaki +2 more
Advances in CPU and GPU confidential computing enable confidential AI, allowing LLMs to process user prompts without exposing them to service...
Penghui Li
Office documents are now routinely uploaded to large language models (LLMs) for processing. However, an LLM does not always see what a human sees,...
Yutao Wu, Xiao Liu, Ming Wen +3 more
Web agents increasingly browse, shop, and manage accounts on behalf of their users. Prior work has shown that they can be misled by adversarial...
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