AI Threat Alert indexes 4,319+ 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 461–480 of 926 papers
Clear filtersIlan Zini, Boussad Addad, Katarzyna Kapusta
Vision Language Models (VLMs) have recently emerged as a critical component of multimodal AI systems, enabling joint reasoning over visual and...
Kai Li, Jong-Ik Park, Carlee Joe-Wong +2 more
Federated training enables language models to learn from distributed private text, but the server cannot directly verify the local supervision or...
Muris Sladić, Veronica Valeros, Eman Alibalić +1 more
LLM-based SSH honeypots often use closed cloud LLMs because they give strong shell realism, but cloud models create deployment problems. These...
Yajing Bai, Jinhao Duan, Jie Peng +4 more
Large language models are increasingly deployed through agent harnesses that manage tools, extensions, persistent state, permissions, and external...
Istiaque Ahmed, Afia Anjum Borsha, Ranat Das Prangon +2 more
Large Language Models (LLMs) in real-world applications often face the risks of specially crafted prompts designed to bypass the safety controls....
Enrique Barba Roque, Luís Cruz, Annibale Panichella
Background: Large Language Models (LLMs) are increasingly being applied to Software Engineering (SE) tasks, achieving high accuracy across problems...
Md Abdullahil Oaphy, Anhao Xiang, Zongxing Xie +3 more
Multimodal large language models (MLLMs) are increasingly used to interact with screenshots, scanned documents, diagrams, and other visually grounded...
Rabimba Karanjai, Yang Lu, Richard Williamson +5 more
Autonomous AI agents are emerging as interfaces for decentralized finance (DeFi) actions such as swaps, lending operations, and yield management....
Mehrdad Ghassabi
Retrieval-Augmented Generation (RAG) has significantly enhanced the performance of large language models (LLMs), yet these systems remain vulnerable...
Sibo Liu
A personal language agent learns a fact from one audience and may later place it in the prompt it assembles for another. This memory-to-context step...
Abyad Enan, Sagar Dasgupta, Mizanur Rahman +1 more
Autonomous vehicles (AVs) depend on reliable Global Navigation Satellite System (GNSS) positioning. However, spoofed GNSS signals can induce...
Tong Zhang, Motasem Alfarra, Carlos Hinojosa +2 more
As text-to-image generative models advance, they raise critical safety concerns, particularly the generation of Not-Safe-For-Work (NSFW) content such...
Chang Liu, Yuni Lai, Mingyue Cui +5 more
Multimodal Retrieval Augmented Generation (M-RAG) is increasingly vulnerable to adversarial attacks where malicious data are crafted to produce...
Abdullah Alghamdi, Siamak Layeghy, Marius Portmann
We propose a two-stage large language model (LLM) framework for zero-shot detection of insider threats and advanced persistent threats (APTs) from...
Stylianos Kampakis, Fabio Rovai, Marcos Charalambides +2 more
Cyber threats continue to escalate in both frequency and sophistication, necessitating more adaptive and scalable defense strategies. This paper...
Jun He, Deying Yu
Operational telemetry is predominantly engineered for human reading: systems repeatedly serialize verbose prose, static keys, and redundant context...
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...
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....
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 4,319+ 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