AI Threat Alert indexes 3,771+ 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 1861–1880 of 1,883 papers
Clear filtersXiaotian Zou
Multimodal Large Language Models (MLLMs) have transformed text-to-image workflows, allowing designers to create novel visual concepts with...
Jeongyeon Hwang, Sangdon Park, Jungseul Ok
Watermarking offers a promising solution for detecting LLM-generated content, yet its robustness under realistic query-free (black-box) evasion...
Xingyu Li, Juefei Pu, Yifan Wu +13 more
Open-source software projects are foundational to modern software ecosystems, with the Linux kernel standing out as a critical exemplar due to its...
Antreas Ioannou, Andreas Shiamishis, Nora Hollenstein +1 more
In an era dominated by Large Language Models (LLMs), understanding their capabilities and limitations, especially in high-stakes fields like law, is...
Nakyeong Yang, Dong-Kyum Kim, Jea Kwon +3 more
Large language models trained on web-scale data can memorize private or sensitive knowledge, raising significant privacy risks. Although some...
Haochen Gong, Chenxiao Li, Rui Chang +1 more
Large language model (LLM)-based computer-use agents represent a convergence of AI and OS capabilities, enabling natural language to control system-...
Jiayu Ding, Xinpeng Liu, Zhiyi Pan +2 more
Lifting 2D open-vocabulary understanding into 3D Gaussian Splatting (3DGS) scenes is a critical challenge. However, mainstream methods suffer from...
Lukas Twist, Jie M. Zhang, Mark Harman +1 more
Large language models (LLMs) are increasingly used to generate code, yet they continue to hallucinate, often inventing non-existent libraries. Such...
David Benfield, Stefano Coniglio, Phan Tu Vuong +1 more
Adversarial machine learning concerns situations in which learners face attacks from active adversaries. Such scenarios arise in applications such as...
Anton Korznikov, Andrey Galichin, Alexey Dontsov +3 more
Activation steering is a promising technique for controlling LLM behavior by adding semantically meaningful vectors directly into a model's hidden...
Bochuan Cao, Changjiang Li, Yuanpu Cao +3 more
Large language models (LLMs) have been widely adopted across various applications, leveraging customized system prompts for diverse tasks. Facing...
Jaehan Kim, Minkyoo Song, Seungwon Shin +1 more
Recent large language models (LLMs) have increasingly adopted the Mixture-of-Experts (MoE) architecture for efficiency. MoE-based LLMs heavily depend...
Daiki Chiba, Hiroki Nakano, Takashi Koide
Phishing attacks are a significant societal threat, disproportionately harming vulnerable populations and eroding trust in essential digital...
Miao Yu, Zhenhong Zhou, Moayad Aloqaily +5 more
Fine-tuned Large Language Models (LLMs) are vulnerable to backdoor attacks through data poisoning, yet the internal mechanisms governing these...
Prakhar Sharma, Haohuang Wen, Vinod Yegneswaran +3 more
The evolution toward 6G networks is being accelerated by the Open Radio Access Network (O-RAN) paradigm -- an open, interoperable architecture that...
Wei Huang, De-Tian Chu, Lin-Yuan Bai +6 more
Modern email spam and phishing attacks have evolved far beyond keyword blacklists or simple heuristics. Adversaries now craft multi-modal campaigns...
Jiahao Huo, Shuliang Liu, Bin Wang +5 more
Semantic-level watermarking (SWM) for large language models (LLMs) enhances watermarking robustness against text modifications and paraphrasing...
Anh Tu Ngo, Anupam Chattopadhyay, Subhamoy Maitra
In this paper we show that cryptographic backdoors in a neural network (NN) can be highly effective in two directions, namely mounting the attacks as...
Xiaofan Li, Xing Gao
In recent years, various software supply chain (SSC) attacks have posed significant risks to the global community. Severe consequences may arise if...
Wenhan Wu, Zheyuan Liu, Chongyang Gao +2 more
Current LLM unlearning methods face a critical security vulnerability that undermines their fundamental purpose: while they appear to successfully...
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 3,771+ 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