AI Threat Alert indexes 3,397+ 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 341–360 of 1,753 papers
Clear filtersZhihao Dou, Qinjian Zhao, Zhiqiang Gao +1 more
Vision--Language Models (VLMs) are increasingly deployed in safety-critical applications, yet remain vulnerable to backdoor attacks. Existing methods...
Siddhant Panpatil, Arth Singh, Mijin Koo +3 more
Vision-language models (VLMs) are now proposed as runtime safety guards for embodied agents in homes and factories. A deployable guard must catch...
Yalin E. Sagduyu, Tugba Erpek, Aylin Yener +1 more
Semantic communication (SemCom) has emerged as a promising paradigm in which the transmission of task-relevant information is prioritized over raw...
Yukun Zhang, Kemu Xu
AI agents increasingly operate inside digital accounts by exercising privileges that users already hold, raising a new control question: whether an...
Moreno D'Incà, Massimiliano Mancini, Nicu Sebe
To improve safety in Large Language Models (LLMs) we can either perform post-training alignment or exploit refusal directions in the activation...
Seyed Bagher Hashemi Natanzi, Bo Tang
Large language models are no longer only text generators. They are increasingly embedded in retrieval pipelines, enterprise assistants, coding...
Robert Schambach, Quoc Do Le, Sergei Arnautov +1 more
Large Language Models (LLMs) have rapidly proliferated, driving widespread adoption of AI applications. Most deployments rely on centralized...
Zhengxing Li, David J. Miller, Guangmingmei Yang +1 more
While post-training backdoor detection and trigger inversion schemes have been developed for AIs used e.g. for images, there is a paucity of such...
Hongliang Liu, Yuhao Wu, Tung-Ling Li
AI agents increasingly acquire and execute skills at runtime: bundles of prompt instructions, executable code, and tool declarations fetched from...
Yong Yang, Xing Zheng, Huiyu Wu +7 more
The fast growth of open-source AI infrastructure, from model serving engines and agent platforms to the Model Context Protocol (MCP) ecosystem and...
Mohammed Latif Siddiq, Md. Nafiu Rahman, Joanna C. S. Santos
Large Language Models (LLMs) are rapidly transforming software development, yet their use in security-critical contexts raises a key question: do...
Xudong Shen, Li Yuan, Ye Chen +3 more
Large Language Models (LLMs) exhibit strong semantic capabilities, yet their resilience to manipulative linguistic patterns such as logical fallacies...
Chenyu Zhou, Qiliang Jiang, Shuning Wu +1 more
Hard-constrained sequential decision systems have no certified way to spend the test-time compute of modern AI: executing the multi-step drafts of a...
Yuanai Xie, Jiaxin Chen, Zhaozhi Liu
Large language model (LLM)-enabled edge networks (LLMENs) offer mobile users high-quality and low-latency AI-generated content services in the 6G...
Afia Mubashir, Boden Moraski, Stephanie Choi +1 more
Artificial intelligence (AI) systems are increasingly integrated into daily life, with millions now using AI chatbots built on Large Language Models...
Arash Raftari, Mehrdad Mahdavi, Nathan Blackthorn +1 more
Backdoor attacks pose a serious threat to large language models (LLMs) by causing otherwise benign systems to produce attacker-specified malicious...
Brent A. Griffin, Jason J. Corso
Foundation model pseudo-labeling - labeling data strictly via zero-shot inference - enables massive scale, but performance is undermined by...
Luciano Pianese, Vittorio Orbinato, Pietro Liguori +1 more
Generative AI has emerged as a significant cybersecurity threat, with several recent attack campaigns leveraging LLMs to generate code for malicious...
Mitchell Hermon, Rahul Gupta, Weitong Ruan +2 more
We identify a security-fidelity tradeoff in defending LLMs against indirect prompt injection: defenses resist injected instructions largely by...
Peizhi Niu, Wenjie Qu, Shangding Gu +14 more
Claw-like AI agents (e.g., OpenClaw) are always-on processes with persistent access to credentials, files, tools, and external services. They take on...
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 3,397+ 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