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 21–40 of 404 papers
Clear filtersAmman Yusuf, Jiwoo Shin, Ruizhi Deng +3 more
The Safety-Aware Denoiser (SAD) is a recent, training-free, safety-guidance framework for text diffusion models. During inference, SAD steers text...
Jincheng Ying, Li Wenlin, Wencheng Yang +1 more
White-box neuron pruning has shown that refusal in large language models (LLMs) can depend on a small, removable set of feed-forward (FFN) channels....
Jingnan Zheng, Dongcheng Zhang, Yi Zhang +10 more
Recursive self-improvement, the participation of AI systems in improving their own capabilities, is beginning to move from theoretical prospect to...
Georgios Milis, Tom Sander, Tomáš Souček +2 more
Watermarking large language models is popular for tracing chatbot and agentic outputs, yet detectors remain unreleased since exposing them could let...
Ines Ortega-Fernandez, Mateusz Kowalczyk, Keri Warr
A compromised LLM inference server can leak model weights by encoding payload bits in otherwise plausible token choices. A replay of the same prompt...
William Hackett, Peter Garraghan
AI systems increasingly rely on Large Language Models (LLMs) as core reasoning engines, making them targets for prompt injection and jailbreaks....
Will Jedrzejczak, Cole Walther, Dilpreet Gill +1 more
Federated learning lets a UAV fleet train a shared GPS spoofing detector without raw receiver data leaving any aircraft, and several recent UAV-FL...
Teng-Ruei Chen
LLM routers pick a cheap or expensive model per request by its content, and many gateways and some cloud platforms can log that choice with content...
Jicheng Zhou, Kahim Wong, Jialong Wang +1 more
AI-generated text (AIGT) detection can be sensitive to the decoding choices of the source large language model (LLM). We observe that perturbing...
Georgios Koutidis, Nikolaos Kekatos, Tom Nianios +1 more
Security Operations Centers (SOCs) for information technology and operational technology share one incident-response problem: a flood of correlated...
Yi Wang, Xiuyuan Qi, Dongqi Han +2 more
Looped Language Models (LoopLMs) provide a parameter efficient approach to scaling model capabilities through repeated use of shared parameters...
Fernando Martinez, Abhishek Satyam, Tao Li +3 more
Policy-based reinforcement learning (RL) approaches have produced promising results for autonomous cyber defense; however, they are...
Weiwei Qi, Chongyu Wang, Tianhang Zheng +5 more
Supervised fine-tuning can substantially improve the downstream utility of large language models (LLMs) but may compromise their safety. Existing...
Wonjun Lee, Kyungsik Yang, Gaeun Ji +5 more
LLMs have advanced rapidly, raising growing concerns about their safety. Recent work has proposed approaches to detect and defend against attacks...
Swadesh Swain, Sanghamitra Dutta
Mechanistic interpretability has emerged as the primary means to understand safety behavior of LLMs. However, existing tools primarily focus on the...
Gefei Liu, Sonya Rashkovan, Sophia Lloyd George +2 more
Reinforcement learning from human feedback (RLHF) has played a central role in making large language models responsive to human instructions....
Kingshuk Gupta, Davide Buscaldi
As Large Language Models (LLMs) increasingly serve as foundational reasoning engines, their tendency to hallucinate remains a critical vulnerability....
Yahya Shahsavari, Sara Rouhani, Kaiwen Zhang
While the literature on blockchain-assisted intrusion detection and prevention systems (IDS/IPS) for Internet of Things (IoT) and Industrial Internet...
Paulo Severo, Silvio E. Quincozes, Amanda Dias
Machine-learning Network Intrusion Detection Systems (IDS) depend on substantial labeled datasets and task-specific training, whereas Large Language...
Harshith Doppalapudi, Nathaniel D. Bastian, Ankit Shah
An autonomous cyber defender trained with reinforcement learning (RL) is typically tied to the network on which it was trained, limiting its ability...
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