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 321–340 of 1,229 papers
Clear filtersSanket Badhe, Priyanka Tiwari
Reusable skills are becoming a fundamental building block of Large Language Model (LLM) agents, enabling capabilities to be packaged, shared, and...
Dima Galat, Marian-Andrei Rizoiu
We investigate which language model evasion attacks survive state-of-the-art adversarial fine-tuning, developing strategies that sweep the top 5...
Na Li, Boyu Kuang, Hongsheng Hu +4 more
To overcome data scarcity and privacy constraints in data collection, it has become standard practice across academia and industry to augment real...
Michael O. Eniolade
Clinical AI models can expose patients to harm when adversarial vulnerabilities go undetected, yet formal security auditing requires statistical...
Roman Prosvirnin, Victor Minchenkov, Alexey Soldatov +1 more
Jailbreak-robustness research typically evaluates safety through generated responses using an LLM-as-judge approach. Such evaluations, however, are...
Yuhang Yan, Linchao Mou, Bokang Yang +1 more
Beyond perception, reasoning is essential in remote sensing for advanced interpretation, inference, and decision-making. Recent advances in large...
Anna Gerchanovsky, Lujo Bauer, Michael K. Reiter
We report on the design and evaluation of MindReader, a tool that helps a user replace her password when she is required to do so. Left to their own...
Zedong Peng, Chenggang Wang, Shangyue Zhu
Large language models (LLMs) frequently generate code with security vulnerabilities, yet these weaknesses are rarely isolated: they often span...
Preet Jhanglani, Zeel Kaushal Desai, Vidhi Kansara +1 more
The integration of AI-powered coding agents into Continuous Integration/Continuous Delivery (CI/CD) pipelines has fundamentally altered how software...
Arastoo Zibaeirad, Marco Vieira, Thomas Zimmermann
Given a vulnerability-fixing commit, trigger localization asks which specific statement turns the vulnerable program state into a concrete unsafe...
Yibo Hu, Ren Wang
As multi-agent, tool-using LLM systems are deployed, a common safety net is a runtime monitor that checks each message, tool call, or step on its...
Xutao Mao, Xiang Zheng, Cong Wang
Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands, and workspace state, making safety failures...
Ahmed M. Elmisery
Adversary emulation plans describe multi-step attacker procedures using MITRE ATT&CK techniques, privilege requirements, and observable telemetry....
Anqi Li, Jie Zhang, Zhongqi Wang +4 more
While Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities, they remain highly susceptible to embedded social biases. Existing...
Yi Ting Shen, Kentaroh Toyoda, Alex Leung
Safety evaluation of large language models (LLMs) relies largely on single-turn attack datasets and single-judge scoring, underestimating risk from...
Anjun Gao, Yueyang Quan, Zhuqing Liu +1 more
Large language models have enabled powerful code completion systems that assist developers by predicting subsequent lines of code. However, these...
Felix Wang, Anudeep Das, Mei Nagappan +1 more
Large language models (LLMs) are increasingly used for code generation, but they struggle to generate functional code free of security...
Victor Giannakouris, Immanuel Trummer
Analytical workloads operating on data stored in external database systems face a fundamental bottleneck: data access is guarded entirely by the...
Marwan Lazrag, Badis Hammi, Lorena Gonzalez-Manzano +1 more
Poisoning attacks against public datasets lead to major concerns, such as (i) misclassification of perceived objects when the poisoned data is used...
Zhangheng LI, Jianing Zhu, Junyuan Hong +4 more
Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on cross-modal tasks by jointly training on large-scale textual 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 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