AI Threat Alert indexes 3,397+ 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 241–260 of 495 papers
Clear filtersSam Herring, Jake Naviasky, Karan Malhotra
Language models are instruction-tuned to refuse harmful requests, but the mechanisms underlying this behavior remain poorly understood. Popular...
Sae Furukawa, Alina Oprea
Supervised Finetuning (SFT) has become one of the primary methods for adapting a large language model (LLM) with extensive pre-trained knowledge to...
Shuo Ni, Tong Wang, Jing Zhang +4 more
Vision-Language Models (VLMs) increasingly operate on ultra-high-resolution (UHR) Earth observation imagery, yet they remain vulnerable to a severe...
Fanpu Cao, Xin Zou, Xuming Hu +1 more
Multimodal large language models (MLLMs) have become a key interface for visual reasoning and grounded question answering, yet they remain vulnerable...
Stefan-Claudiu Susan, Andrei Arusoaie, Dorel Lucanu
The irreversible nature of blockchain transactions makes the identification of smart contract vulnerabilities an essential requirement for secure...
Pedro Conde, Henrique Branquinho, Valerio Mazzone +3 more
AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will...
Saba Pourhanifeh, AbdulAziz AbdulGhaffar, Ashraf Matrawy
Large Language Models(LLMs) are increasingly explored for cybersecurity applications such as vulnerability detection. In the domain of threat...
Chiyu Zhang, Huiqin Yang, Bendong Jiang +8 more
The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content...
Dahlia Shehata, Ming Li
Multi-agent systems (MAS) assume that collaborating inherently improves Large Language Model (LLM) reasoning. We challenge this by demonstrating that...
Hongwei Yao, Yiming Liu, Yiling He +1 more
Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts,...
Hui Lu, Xueyuan Chen, Huimeng Wang +4 more
Full-duplex spoken dialogue requires a model to keep listening while generating its own spoken response. This is challenging for large language...
Qinghua Mao, Xi Lin, Jinze Gu +3 more
Large language models (LLMs) increasingly rely on knowledge editing to support knowledge-intensive reasoning, but this flexibility also introduces...
Xia Hu, Zhenrui Yue, Brian Potetz +4 more
As current Multimodal Large Language Models rapidly saturate canonical visual reasoning benchmarks, a key question emerges: do these strong scores...
Huy Hoang Ha, Benoit Favre, Francois Portet
Large language models (LLMs) have saturated standard medical benchmarks that test factual recall, yet their ability to perform higher-order...
Jingshen Zhang, Bo Wang, Yanlin Fu +4 more
In this paper, we study an emergent self-debiasing mechanisms against stereotypical content in Large Language Models (LLMs). Unlike traditional...
Yilin Zhang, Yingkai Hua, Chunyu Wei +2 more
Vision-language model (VLM) based web agents demonstrate impressive autonomous GUI interaction but remain vulnerable to deceptive interface elements....
Shai Feldman, Yaniv Romano
Evaluating and predicting the performance of large language models (LLMs) in multi-turn conversational settings is critical yet computationally...
Mohammad Mamun, Mohamed Gaber, Scott Buffett +1 more
Language Model Agents (LMAs) are emerging as a powerful primitive for augmenting red-team operations. They can support attack planning, adversary...
Di Lu, Bo Zhang, Xiyuan Li +5 more
Self-hosted computer-use agents (SHCUAs), such as OpenClaw, combine natural-language interaction with direct access to host-side resources, including...
Qinfeng Li, Yuntai Bao, Jianghui Hu +5 more
LLM agents rely on prompts to implement task-specific capabilities based on foundation LLMs, making agent prompts valuable intellectual property....
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 3,397+ 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