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 721–740 of 866 papers
Clear filtersYingjia Wang, Ting Qiao, Xing Liu +3 more
The rapid advancement of deep neural networks (DNNs) heavily relies on large-scale, high-quality datasets. However, unauthorized commercial use of...
Zheng Zhang, Haonan Li, Xingyu Li +2 more
Bug bisection has been an important security task that aims to understand the range of software versions impacted by a bug, i.e., identifying the...
Kaiwen Zhou, Ahmed Elgohary, A S M Iftekhar +1 more
The ability of LLM agents to plan and invoke tools exposes them to new safety risks, making a comprehensive red-teaming system crucial for...
André V. Duarte, Xuying li, Bin Zeng +3 more
If we cannot inspect the training data of a large language model (LLM), how can we ever know what it has seen? We believe the most compelling...
Emily Herron, Junqi Yin, Feiyi Wang
Large language models (LLMs) have demonstrated transformative potential in scientific research, yet their deployment in high-stakes contexts raises...
Simon Yu, Peilin Yu, Hongbo Zheng +3 more
We present VISAT, a novel open dataset and benchmarking suite for evaluating model robustness in the task of traffic sign recognition with the...
He Hu, Chiyuan Ma, Qianning Wang +5 more
The shortage of mental health professionals has driven the web to become a primary avenue for accessible psychological support. While Large Language...
Zheng Zhang, Guanlong Wu, Sen Deng +2 more
In the rapidly expanding landscape of Large Language Model (LLM) applications, real-time output streaming has become the dominant interaction...
Juan Ren, Mark Dras, Usman Naseem
Agentic methods have emerged as a powerful and autonomous paradigm that enhances reasoning, collaboration, and adaptive control, enabling systems to...
Yifan Wu, Xuewei Feng, Yuxiang Yang +1 more
As the core of the Internet infrastructure, the TCP/IP protocol stack undertakes the task of network data transmission. However, due to the...
María Sanz-Gómez, Víctor Mayoral-Vilches, Francesco Balassone +3 more
Cybersecurity spans multiple interconnected domains, complicating the development of meaningful, labor-relevant benchmarks. Existing benchmarks...
Vladyslav Larin, Ihor Naumenko, Aleksei Ivashov +2 more
As centralized AI hits compute ceilings and diminishing returns from ever-larger training runs, meeting demand requires an inference layer that...
Hiromu Takahashi, Shotaro Ishihara
We propose Fast-MIA (https://github.com/Nikkei/fast-mia), a Python library for efficiently evaluating membership inference attacks (MIA) against...
Armin Gerami, Kazem Faghih, Ramani Duraiswami
Retrieval Augmented Generation (RAG) enhances Large Language Models (LLMs) by connecting them to external knowledge, improving accuracy and reducing...
Julia Bazinska, Max Mathys, Francesco Casucci +4 more
AI agents powered by large language models (LLMs) are being deployed at scale, yet we lack a systematic understanding of how the choice of backbone...
Hao Zheng, Zirui Pang, Ling li +5 more
Advances in Multimodal Large Language Models (MLLMs) intensify concerns about data privacy, making Machine Unlearning (MU), the selective removal of...
Wenxuan Bao, Ruxi Deng, Jingrui He
Pretrained vision-language models such as CLIP achieve strong zero-shot generalization but remain vulnerable to distribution shifts caused by input...
Mojtaba Eshghie, Gabriele Morello, Matteo Lauretano +2 more
Smart contract vulnerabilities cost billions of dollars annually, yet existing automated analysis tools fail to generate deployable defenses. We...
Christoph Bühler, Matteo Biagiola, Luca Di Grazia +1 more
Large Language Models (LLMs) have evolved into AI agents that interact with external tools and environments to perform complex tasks. The Model...
Divyanshu Kumar, Nitin Aravind Birur, Tanay Baswa +2 more
Frontier Large Language Models (LLMs) pose unprecedented dual-use risks through the potential proliferation of chemical, biological, radiological,...
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