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 561–580 of 866 papers
Clear filtersKarolina Korgul, Yushi Yang, Arkadiusz Drohomirecki +7 more
Web-based agents powered by large language models are increasingly used for tasks such as email management or professional networking. Their reliance...
Kerem Zaman, Shashank Srivastava
Recent work, using the Biasing Features metric, labels a CoT as unfaithful if it omits a prompt-injected hint that affected the prediction. We argue...
Woorim Han, Yeongjun Kwak, Miseon Yu +4 more
Learning-based automated vulnerability repair (AVR) techniques that utilize fine-tuned language models have shown promise in generating vulnerability...
Vahideh Zolfaghari
Background Large language models (LLMs) are increasingly deployed in medical consultations, yet their safety under realistic user pressures remains...
Marc S. Montalvo, Hamed Yaghoobian
Recent advances in large language models (LLMs) are transforming data-intensive domains, with finance representing a high-stakes environment where...
Chinmay Pushkar, Sanchit Kabra, Dhruv Kumar +1 more
Large Language Models (LLMs) have demonstrated significant potential in automated software security, particularly in vulnerability detection....
Yifan Huang, Xiaojun Jia, Wenbo Guo +4 more
Large language models (LLMs) have revolutionized software development through AI-assisted coding tools, enabling developers with limited programming...
Jiashuo Liu, Jiayun Wu, Chunjie Wu +5 more
The rapid proliferation of Large Language Models (LLMs) and diverse specialized benchmarks necessitates a shift from fragmented, task-specific...
Miles Q. Li, Benjamin C. M. Fung, Martin Weiss +3 more
As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values has become a...
Adam Elaoumari
The purpose of this project is to assess how well defenders can detect DNS-over-HTTPS (DoH) file exfiltration, and which evasion strategies can be...
Zhenlei Ye, Xiaobing Sun, Sicong Cao +2 more
The advances of large language models (LLMs) have paved the way for automated software vulnerability repair approaches, which iteratively refine the...
Aaron Chan, Alex Ding, Frank Chen +3 more
The rapid integration of Large Language Models (LLMs) into decentralized physical infrastructure networks (DePIN) is currently bottlenecked by the...
Naseem Machlovi, Maryam Saleki, Ruhul Amin +5 more
As large language models (LLMs) become deeply embedded in daily life, the urgent need for safer moderation systems, distinguishing between naive from...
Naseem Machlovi, Maryam Saleki, Ruhul Amin +5 more
As large language models (LLMs) become deeply embedded in daily life, the urgent need for safer moderation systems that distinguish between naive and...
Liming Lu, Xiang Gu, Junyu Huang +5 more
Large Language Models (LLMs) are increasingly used in agentic systems, where their interactions with diverse tools and environments create complex,...
Zhang Wei, Peilu Hu, Zhenyuan Wei +16 more
The increasing deployment of large language models (LLMs) in safety-critical applications raises fundamental challenges in systematically evaluating...
Sumanth Bharadwaj Hachalli Karanam, Dhiwahar Adhithya Kennady
Manual software beta testing is costly and time-consuming, while single-agent large language model (LLM) approaches suffer from hallucinations and...
Scott Thornton
AI coding assistants produce vulnerable code in 45\% of security-relevant scenarios~\cite{veracode2025}, yet no public training dataset teaches both...
Wei Qian, Chenxu Zhao, Yangyi Li +1 more
The rapid advancements in artificial intelligence (AI) have primarily focused on the process of learning from data to acquire knowledgeable learning...
Wang Bin, Ao Yang, Kedan Li +5 more
In the domain of software security testing, Directed Grey-Box Fuzzing (DGF) has garnered widespread attention for its efficient target localization...
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