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 361–380 of 3,771 papers
Yu Li, Liqi Zhuang, Dong Wei +5 more
Skills for large language model (LLM) agents have been widely deployed across diverse application domains. However, we observe that these skills...
Nokimul Hasan Arif, Qian Lou, Mengxin Zheng
Large Language and Vision-Language Models are increasingly deployed through inference pipelines that include prompt wrappers (e.g., templates and...
Xabier Muruaga
LLM-based agents can act on behalf of a user to access cloud services, call tools, or invoke agents. At session start, the agent's permissions are...
Riku Mochizuki, Shusuke Komatsu, Souta Noguchi +1 more
We characterize the attack surface of generative search engines (GSEs) against poisoning attacks in the political domain, from the perspectives of...
Md Rezwanul Islam
Machine-learning detectors for power-system cyberattacks are themselves attack surfaces, and quantum machine learning has been proposed for them. We...
Julian Minder, Viktor Moskvoretskii, Raghav Singhal +12 more
As language-model-based AI is increasingly deployed in autonomous settings, aligning its goals and values with those of humans becomes critical....
Daniel Perkins, John Squires, Janou Milligan +2 more
Modern image classification models excel when trained on single task-specific datasets but often struggle to generalize across domains and difficulty...
Md Wasiul Haque, Sagar Dasgupta, Mizanur Rahman +1 more
Autonomous vehicles depend on large safety-critical software stacks, where weaknesses reachable from adversarial inputs may affect steering, braking,...
Peng Li, Qianqian Xu, Shilong Bao +2 more
Traffic video understanding has become an important problem in intelligent transportation, as road videos provide direct evidence for accidents,...
Ziqi Zhao, Jialin Lu, Junjie Shan +3 more
Vertical Federated Learning (VFL) enables organizations holding complementary features of shared entities to collaborate and train models. In this...
Beining Xu, Hairui Wang, Jiaxin Wang +2 more
While the privacy risks of multimodal large language models (MLLMs) have drawn significant attention, the unique vulnerabilities of domain-specific...
Fangzhou Chen, Shiji Zhao, Mengyang Wang +4 more
Large language models (LLMs) remain vulnerable to harmful requests and jailbreak attacks. Parameter-efficient safety alignment methods based on...
Xiaoyan Feng, Yanjun Zhang, He Zhang +2 more
Watermarking LLM-generated text is an important task for tracing its provenance. Existing LLM watermarks preserve provenance under editing, but this...
Junliang Liu, Ruoyu Li, Wenxin Tang +4 more
LLM agents increasingly rely on third-party skills, using natural-language descriptions for selection and instruction bodies for planning. This...
Zhenpeng Li
An unconditional risk bound on automated decisions can be satisfied without automating anything, since a selector that never acts drives the bound to...
Van Tran, Taveesh Sharma, Tajveer Singh Dhesi +1 more
AI agents are rapidly becoming more capable and widely deployed, promising substantial gains in productivity and enabling new classes of...
Nikolette Pedersen, Regitze Sydendal, Veronika Cheplygina +1 more
Vision-language models, such as contrastive language-image pre-training (CLIP)-based approaches, have reached state-of-the-art (SOTA) results in...
Yutao Mou, Pengfei Yang, Zhe Yin +6 more
Large language model (LLM) agents integrated with external tools are vulnerable to indirect prompt injections embedded in environmental states....
Xucheng Yu, Emily Knox, Haohan Wang
As large language models enter everyday information pipelines, understanding how they handle sensitive topics matters as much as understanding...
Nimet Beyza Bozdag, Emre Can Acikgoz, Gokhan Tur +1 more
Persuasion is a core dynamic of natural language communication, shaping how large language models (LLMs) update beliefs, resolve disagreements, and...
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