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 221–240 of 1,229 papers
Clear filtersJinpu Jiang, Xuan Wu, Wenhao Song +6 more
Retrieval-Augmented Generation (RAG) has emerged as a powerful architecture for Question Answering (QA) by integrating external information into...
Pei-Sze Tan, Tasuku Igarashi, Isao Echizen
Agentic AI assistants are increasingly used in everyday life. However, they may also be misused to support harmful manipulation in interpersonal...
Ze Sheng, Aleksandar Kezic, Zhicheng Chen +1 more
Evaluating the ability of large language models (LLMs) to discover software bugs is increasingly important. Existing benchmarks typically evaluate...
Lin-Fa Lee, YI-YU Chang, Kuo-Hui Yeh
The emerging W3C WebMCP proposal enables LLM agents to invoke tools exposed by web pages. In multi-party web environments, however, integrating agent...
Yueyang Quan, Anjun Gao, Yufei Xia +2 more
Retrieval-augmented generation (RAG) improves the factuality of large language models by grounding responses in external documents, but it also...
Trung-Anh Dang, Duy-Cuong Bui, Ngoc-Son Vu +2 more
Continual learning faces the persistent challenge of catastrophic forgetting, where sequential task updates degrade previously acquired knowledge....
Mehrdad Rostamzadeh, Sidhant Narula, Mohammad Ghasemigol +1 more
The Model Context Protocol (MCP) has emerged as the standard layer connecting Large Language Model agents to external tool backends. This openness...
Seokjin Hwang, Yuting, Li +1 more
Instance encoding is a popular empirical technique for privacy enhancement when sharing data to an untrusted server. It transforms sensitive data...
Seokjin Hwang, Yuting Li, Kiwan Maeng
Instance encoding is a popular empirical technique for privacy enhancement when sharing data to an untrusted server. It transforms sensitive data...
Or Biton, Tomer Krichli, Itai Allouche +1 more
Although Large Language Models (LLMs) are aligned to optimize for both helpfulness and harmlessness, these dual objectives may conflict, inevitably...
Lorenzo Bossi, Federico Saccani, Francesco Panebianco +4 more
Cyber threat intelligence from underground forums has traditionally relied on passive monitoring. However, as users have become more aware of...
Xiangxin Zhang, Zhanwei Zhang, Zhihang Fu +2 more
Web search agents powered by Large Language Models (LLMs) show strong promise, but deep research tasks expose a recurring failure mode: once an agent...
Saber Zerhoudi, Jelena Mitrovic, Michael Granitzer
A safety rule and an episodic log compete for the same tokens in an AI agent's context. When the budget overflows, both are summarized at the same...
YuanHang Xiao
Agent benchmarks often evaluate only final answers even when agents run on stateful runtimes. We argue this under-specifies what is being evaluated:...
Cheng Xu, Nan Yan, Liming Chen +1 more
Whether a language model has improved itself is increasingly judged not by mean accuracy but by which individual problems it gains and loses....
Yiting Qu, Ziqing Yang, Chi Cui +3 more
Hidden chain-of-thought (CoT) traces, especially those from frontier proprietary large reasoning models (LRMs), are valuable model assets. Yet...
Yue Wang, Yi Liu, Gelei Deng +4 more
Agent Skills extend LLM agents with reusable instruction packages that may also include scripts, resources, and service configuration. This creates a...
Ye Tao, Hong Shen, Hui Tian +2 more
Gradient inversion attacks recover private training text from gradients shared in federated learning, posing a serious threat to collaborative model...
Avijit Gayen, Sayan Mondal, Angshuman Jana
In today's era of rapid advancements in artificial intelligence, computer security and online safeguarding measures have undergone significant...
Muris Sladić, Veronica Valeros, Eman Alibalić +1 more
LLM-based SSH honeypots often use closed cloud LLMs because they give strong shell realism, but cloud models create deployment problems. These...
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