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 1–20 of 197 papers
Clear filtersJoas Antonio dos Santos Barbosa
Autonomous penetration-testing harnesses use large language models (LLMs) for reconnaissance, exploitation, and reporting, but often rely on those...
Xuwei Tan, Yao Ma, Xueru Zhang
Real-time payment fraud detection is a non-stationary streaming prediction problem: adversaries adapt before supervised labels mature, and localized...
Yue Xing, Pengfei He, Zitao Li
With recent advancements in large language models (LLMs) and LLM-based agents, these agents are becoming increasingly autonomous and gaining broader...
Youssef Hamdi Zafan Ibrahim, Muhammad Ikram, Mohammed Khalaf Salama
Running large language models (LLMs) locally is often considered more private than cloud-hosted inference because user prompts remain on the device....
Rushabh Vipulkumar Patel, Dipo Dunsin, Mohammed Almaiah +1 more
AI-driven penetration testing has been demonstrated with premium frontier models such as GPT-4, but the per-engagement token cost makes continuous,...
Sebastian Neef
Content Management Systems (CMS), such as WordPress, power a large share of the web (~58%), and their extensibility through third-party plugins is a...
Rakesh Kumar Surapani, Pradeep Kumar Dolabehera Kakitapelli, Arun Morampudi +1 more
Tool-using artificial intelligence (AI) agents, systems that autonomously invoke application programming interfaces (APIs), databases, browsers, and...
Anna Gazani, Spyridon Kounoupidis, Panagiotis Katsaros +3 more
The integration of Large Language Models (LLMs) into Security Operations Centers (SOCs) streamlines threat intelligence but introduces critical...
Ayan Roy, Kaustuvi Basu
Agentic AI systems with persistent memory introduce a distinct attack surface known as memory poisoning, in which adversarially crafted content is...
Andrea Ponte, Luca Demetrio, Luca Oneto +2 more
Industrial Windows malware detectors are commonly described as Compound AI Systems composed of multiple heterogeneous components, including...
Srikumar Nayak
Federated learning allows banks, hospitals, and other regulated organizations to train a shared model without moving raw records off their own...
Zhiyang Ding, Yang Luo, Guangpu Chen +2 more
Remote Model Context Protocol (MCP) services enable large language model agents to invoke external tools, but OAuth authorization alone does not...
Laurent Bindschaedler, Quentin Botha, Christoph Siebenbrunner
Long-horizon agents execute thousands of actions, resulting in sequential failures rather than isolated errors. When a coding agent deletes a...
Padmeswari Nandiya, Ahmad Mohsin, Ahmed Ibrahim +2 more
The growing complexity of cyber-physical attack surfaces in advanced manufacturing has made cyber threat intelligence analysis increasingly...
Pingyu Wu, Weiming Zhang, Nenghai Yu
Safeguards in deployed LLM services are evaluated by refusal, attack success, and policy violation rates. Those rates characterize how a control...
Panduranga Sai Varma Dantuluri, Jyotirmoy Sundi
Autonomous LLM agents increasingly act on a user's behalf: they hold credentials, call tools and services, and spawn sub-agents that act further on...
Lifei Liu, Haoran Yu
Multi-agent applications delegate work across independently operated deployers. After an incident, a verifier must answer two questions: which...
Chuanchao Zang, Jianing Wang, Wenyu Chen +6 more
LLM agents commonly use knowledge-based tools and access their underlying files, databases, and search indexes through tool invocation. This...
Jiayi Zhang, Zexin Wang, Degang Sun +4 more
Large language model (LLM)-based agents have shown strong potential in solving complex tasks through multi-step reasoning, yet they remain vulnerable...
XiuYu Zhang, Bonan Ruan, Junfeng Fang +3 more
Large language models (LLMs) are increasingly deployed with layered defenses, yet malicious prompts can still bypass them. Interpretability methods...
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