AI Threat Alert indexes 3,381+ 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 401–420 of 569 papers
Clear filtersYanting Wang, Wei Zou, Runpeng Geng +1 more
Large language models (LLMs) and their applications, such as agents, are highly vulnerable to prompt injection attacks. State-of-the-art prompt...
Anubhab Sahu, Diptisha Samanta, Reza Soosahabi
System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive...
Jingning Xu, Haochen Luo, Chen Liu
Vision-language models (VLMs) are vulnerable to adversarial image perturbations. Existing works based on adversarial training against task-specific...
Jiaqing Li, Zhibo Zhang, Shide Zhou +3 more
Model merging has emerged as a powerful technique for combining specialized capabilities from multiple fine-tuned LLMs without additional training...
Aengus Lynch
Autonomous AI agents are being deployed with filesystem access, email control, and multi-step planning. This thesis contributes to four open problems...
Chong Xiang, Drew Zagieboylo, Shaona Ghosh +5 more
AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions...
Meiwen Ding, Song Xia, Chenqi Kong +1 more
Although multimodal large language models (MLLMs) are increasingly deployed in real-world applications, their instruction-following behavior leaves...
Kavindu Herath, Joshua Zhao, Saurabh Bagchi
Backdoor attacks on federated learning (FL) are most often evaluated with synthetic corner patches or out-of-distribution (OOD) patterns that are...
Miles Farmer, Ekincan Ufuktepe, Anne Watson +4 more
Large Language Models (LLMs) have emerged as a popular choice in vulnerability detection studies given their foundational capabilities, open source...
Yunrui Yu, Xuxiang Feng, Pengda Qin +5 more
Adversarial robustness evaluation faces a critical challenge as new defense paradigms emerge that can exploit limitations in existing assessment...
KrishnaSaiReddy Patil
LLM-based chatbots in government services face critical security gaps. Multi-turn adversarial attacks achieve over 90% success against current...
Bilgehan Sel, Xuanli He, Alwin Peng +2 more
Fine-tuning APIs offered by major AI providers create new attack surfaces where adversaries can bypass safety measures through targeted fine-tuning....
Chihan Huang, Huaijin Wang, Shuai Wang
The pervasive deployment of deep learning models across critical domains has concurrently intensified privacy concerns due to their inherent...
Chengyin Hu, Jiaju Han, Xuemeng Sun +6 more
Vision-language models (VLMs) rely on a shared visual-textual representation space to perform tasks such as zero-shot classification, image...
Aymen Lassoued, Nacef Mbarek, Bechir Dardouri +3 more
Vulnerability detection in C programs is a critical challenge in software security. Although large language models (LLMs) achieve strong detection...
Tran Duong Minh Dai, Triet Huynh Minh Le, M. Ali Babar +2 more
Although Graph Neural Networks (GNNs) have shown promise for smart contract vulnerability detection, they still face significant limitations....
Haochuan Kevin Wang
We present a stage-decomposed analysis of prompt injection attacks against five frontier LLM agents. Prior work measures task-level attack success...
Bhavuk Jain, Sercan Ö. Arık, Hardeo K. Thakur
Multimodal large language models (MLLMs) integrate information from multiple modalities such as text, images, audio, and video, enabling complex...
Eyal Hadad, Mordechai Guri
On-device Vision-Language Models (VLMs) promise data privacy via local execution. However, we show that the architectural shift toward Dynamic...
Younes Salmi, Hanna Bogucka
Deep learning (DL) has been widely studied for assisting applications of modern wireless communications. One of the applications is automatic...
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 3,381+ 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