AI Threat Alert indexes 3,023+ 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 201–220 of 266 papers
Clear filtersAbdul Aziz, Ingrid Huso, Savio Sciancalepore +1 more
Radio Frequency Fingerprinting (RFF) has evolved from an early idea for radar emitter identification into a broad research field for wireless device...
Blake Bullwinkel, Eugenia Kim, Amanda Minnich +1 more
AI red teaming must continually adapt to evolving attackers and defenders. Reinforcement learning offers a promising approach to discovering novel...
Qin Yang, Lu Malloy, Joshua Lee +4 more
Large language model (LLM)-powered content moderation systems have become a critical defense against harmful online content. However, these systems...
Hankun Lin, Ruqi Zhang
Ensuring the reliability of Large Language Models (LLMs) under distribution drift requires inference-time adaptation. While inference-time alignment...
Gilad Gressel, Rahul Pankajakshan, Julia Diament +3 more
As LLMs are deployed as agents, reliable monitoring requires knowing not only what they output, but which instructions are steering their behavior....
Shixiong Jiang, Taozheng Zhu, Fanxin Kong
Offline safe reinforcement learning (Safe RL) enables policy learning without online interactions, making it suitable for safety-critical systems...
Yinan Wang
AI Scientist agents are often evaluated as if capability were mainly a function of model quality, prompting, or reasoning scaffolds. We test a...
Yuhan Ma, Stefan Schmid
Tool-using large language model (LLM) agents face two distinct security failures: unauthorized external actions and exposure of sensitive plaintext...
Bastien Vuillod, Kevin Hector, Pierre-Alain Moellic +2 more
Federated Learning (FL) allows a set of clients to collectively train a global model without sharing local training data. Giving the responsibility...
Ethan Rathbun, Ahmed Agha, Saaduddin Mahmud +3 more
World models have recently seen a rapid growth in both their popularity and capability as more data efficient tools for generating robot training...
Charles Westphal, Timothy Douglas, Keivan Navaie +2 more
Large language models can be fine-tuned to encode prompt-borne secrets into fluent, seemingly benign outputs. This creates a steganographic...
Srravya Chandhiramowuli, Ding Wang, Alex Taylor
We present an ethnographic study of an alternative approach to data work, developed by a civic-tech initiative that builds datasets for training and...
Bartłomiej Marek, Lorenzo Rossi, Vincent Hanke +4 more
Recent work has applied differential privacy (DP) to adapt large language models (LLMs) for sensitive applications, offering theoretical guarantees....
Jianwei Tai
BCI-to-agent pipelines turn decoded neural activity into an authorization channel for tool-use agents, exposing a new attack surface we call...
Hyunseok Paeng
We present a reproducible failure mode of safety training in RAG-based LLM recommendation -- the Injection Paradox -- in which prompt injections...
Hyeji Choi, Yongtaek Lim, Minwoo Kim
Multilingual safety evaluation of large language models (LLMs) has predominantly relied on direct translation (DT) of English benchmarks into target...
Jiahao Chen, Xing He, Yong Yang +6 more
The prosperity of text-to-image (T2I) models has fostered a vibrant share-and-play ecosystem centered on Low-Rank Adaptation (LoRA) plugins, which...
Tiejin Chen, Pingzhi Li, Kaixiong Zhou +2 more
Privacy risks in text-only Large Language Models (LLMs) are well studied, particularly their tendency to memorize and leak sensitive information....
Arun Malik
Cloud network infrastructure at hyperscale presents unique operational challenges where traditional human-driven incident response cannot keep pace...
Xiaofeng Lin, Yukai Yang, Daniel Guo +3 more
Tool-using LLM agents interact with the world through actions that persist state in artifacts (e.g., workspace files or logs). Consequently,...
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 3,023+ 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