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 1121–1140 of 1,175 papers
Clear filtersXiangfang Li, Yu Wang, Bo Li
With the rapid advancement of large language models (LLMs), ensuring their safe use becomes increasingly critical. Fine-tuning is a widely used...
Alexandrine Fortier, Thomas Thebaud, Jesús Villalba +2 more
Large Language Models (LLMs) and their multimodal extensions are becoming increasingly popular. One common approach to enable multimodality is to...
Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang +1 more
Existing data poisoning attacks on retrieval-augmented generation (RAG) systems scale poorly because they require costly optimization of poisoned...
Raik Dankworth, Gesina Schwalbe
Deep neural networks (NNs) for computer vision are vulnerable to adversarial attacks, i.e., miniscule malicious changes to inputs may induce...
Tsubasa Takahashi, Shojiro Yamabe, Futa Waseda +1 more
Differential Attention (DA) has been proposed as a refinement to standard attention, suppressing redundant or noisy context through a subtractive...
Yu Yan, Siqi Lu, Yang Gao +4 more
Recently, Bit-Flip Attack (BFA) has garnered widespread attention for its ability to compromise software system integrity remotely through hardware...
Chenxiang Luo, David K. Y. Yau, Qun Song
Federated learning (FL) enables collaborative model training without sharing raw data but is vulnerable to gradient inversion attacks (GIAs), where...
Dalal Alharthi, Ivan Roberto Kawaminami Garcia
Large language models have gained widespread prominence, yet their vulnerability to prompt injection and other adversarial attacks remains a critical...
Samar Fares, Nurbek Tastan, Noor Hussein +1 more
Generative models can generate photorealistic images at scale. This raises urgent concerns about the ability to detect synthetically generated images...
Luis Burbano, Diego Ortiz, Qi Sun +5 more
Embodied Artificial Intelligence (AI) promises to handle edge cases in robotic vehicle systems where data is scarce by using common-sense reasoning...
Anshul Nasery, Edoardo Contente, Alkin Kaz +2 more
Model fingerprinting has emerged as a promising paradigm for claiming model ownership. However, robustness evaluations of these schemes have mostly...
Firas Ben Hmida, Abderrahmen Amich, Ata Kaboudi +1 more
Deep neural networks (DNNs) are increasingly being deployed in high-stakes applications, from self-driving cars to biometric authentication. However,...
Shuai Shao, Qihan Ren, Chen Qian +8 more
Advances in Large Language Models (LLMs) have enabled a new class of self-evolving agents that autonomously improve through interaction with the...
Qinjian Zhao, Jiaqi Wang, Zhiqiang Gao +3 more
Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also...
Xiaobao Wang, Ruoxiao Sun, Yujun Zhang +4 more
Graph Neural Networks (GNNs) have demonstrated strong performance across tasks such as node classification, link prediction, and graph...
Marco Zimmerli, Andreas Plesner, Till Aczel +1 more
Deep neural networks remain vulnerable to adversarial examples despite advances in architectures and training paradigms. We investigate how training...
Dennis Jacob, Emad Alghamdi, Zhanhao Hu +2 more
Large language models (LLMs) have become increasingly popular due to their ability to interact with unstructured content. As such, LLMs are now a key...
Yein Park, Jungwoo Park, Jaewoo Kang
Large language models (LLMs), despite being safety-aligned, exhibit brittle refusal behaviors that can be circumvented by simple linguistic changes....
Yuepeng Hu, Zhengyuan Jiang, Mengyuan Li +4 more
Large language models (LLMs) are often modified after release through post-processing such as post-training or quantization, which makes it...
Yanchen Jiang, Zhe Feng, Aranyak Mehta
Large language models (LLMs) are increasingly used in modern search and answer systems to synthesize multiple, sometimes conflicting, texts into a...
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