AI Threat Alert indexes 2,841+ 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 1241–1260 of 1,352 papers
Clear filtersAofan Liu, Lulu Tang
Vision-Language Models (VLMs) have garnered significant attention for their remarkable ability to interpret and generate multimodal content. However,...
Jiyang Qiu, Xinbei Ma, Yunqing Xu +2 more
The rapid deployment of large language model (LLM)-based agents in real-world applications has raised serious concerns about their trustworthiness....
Xiangtao Meng, Tianshuo Cong, Li Wang +4 more
Large Language Models (LLMs) have shown remarkable performance across various applications, but their deployment in real-world settings faces several...
Eric Hanchen Jiang, Weixuan Ou, Run Liu +8 more
Safety alignment of large language models currently faces a central challenge: existing alignment techniques often prioritize mitigating responses to...
Man Hu, Xinyi Wu, Zuofeng Suo +5 more
With the rise of advanced reasoning capabilities, large language models (LLMs) are receiving increasing attention. However, although reasoning...
Chongyu Fan, Changsheng Wang, Yancheng Huang +2 more
Machine unlearning for large language models (LLMs) aims to remove undesired data, knowledge, and behaviors (e.g., for safety, privacy, or copyright)...
Shen Dong, Mingxuan Zhang, Pengfei He +4 more
Large Language Model (LLM)-based Multi-Agent Systems (MAS) have emerged as a powerful paradigm for tackling complex, multi-step tasks across diverse...
Muris Sladić, Veronica Valeros, Carlos Catania +1 more
There are very few SotA deception systems based on Large Language Models. The existing ones are limited only to simulating one type of service,...
Riku Mochizuki, Shusuke Komatsu, Souta Noguchi +1 more
We analyze answers generated by generative engines (GEs) from the perspectives of citation publishers and the content-injection barrier, defined as...
Tavish McDonald, Bo Lei, Stanislav Fort +2 more
Models are susceptible to adversarially out-of-distribution (OOD) data despite large training-compute investments into their robustification. Zaremba...
Tiancheng Xing, Jerry Li, Yixuan Du +1 more
Large language models (LLMs) are increasingly used as rerankers in information retrieval, yet their ranking behavior can be steered by small,...
Zhiyuan Wei, Xiaoxuan Yang, Jing Sun +1 more
The increasing complexity of modern software systems exacerbates the prevalence of security vulnerabilities, posing risks of severe breaches and...
Weidi Luo, Qiming Zhang, Tianyu Lu +9 more
Computer-use agent (CUA) frameworks, powered by large language models (LLMs) or multimodal LLMs (MLLMs), are rapidly maturing as assistants that can...
Thusitha Dayaratne, Ngoc Duy Pham, Viet Vo +5 more
The quality and experience of mobile communication have significantly improved with the introduction of 5G, and these improvements are expected to...
Ali Naseh, Anshuman Suri, Yuefeng Peng +3 more
Generative AI leaderboards are central to evaluating model capabilities, but remain vulnerable to manipulation. Among key adversarial objectives is...
Shadi Rahimian, Mario Fritz
Single nucleotide polymorphism (SNP) datasets are fundamental to genetic studies but pose significant privacy risks when shared. The correlation of...
Mary Llewellyn, Annie Gray, Josh Collyer +1 more
Before adopting a new large language model (LLM) architecture, it is critical to understand vulnerabilities accurately. Existing evaluations can be...
Yasod Ginige, Akila Niroshan, Sajal Jain +1 more
Penetration testing and vulnerability assessment are essential industry practices for safeguarding computer systems. As cyber threats grow in scale...
Cade Houston Kennedy, Amr Hilal, Morteza Momeni
With the growth of digital financial systems, robust security and privacy have become a concern for financial institutions. Even though traditional...
Zizhao Wang, Dingcheng Li, Vaishakh Keshava +4 more
Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of...
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 2,841+ 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