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 381–400 of 407 papers
Clear filtersXiangtao Meng, Tianshuo Cong, Li Wang +4 more
Large Language Models (LLMs) have shown remarkable performance across various applications, but their deployment in real-world settings faces several...
Thusitha Dayaratne, Ngoc Duy Pham, Viet Vo +5 more
The quality and experience of mobile communication have significantly improved with the introduction of 5G, and these improvements are expected to...
Abhejay Murali, Saleh Afroogh, Kevin Chen +3 more
Current safety alignment for Large Language Models (LLMs) implicitly optimizes for a "modal adult user," leaving models vulnerable to distributional...
Yining She, Daniel W. Peterson, Marianne Menglin Liu +4 more
With the increasing adoption of large language models (LLMs), ensuring the safety of LLM systems has become a pressing concern. External LLM-based...
Siwei Han, Kaiwen Xiong, Jiaqi Liu +9 more
As Large Language Model (LLM) agents increasingly gain self-evolutionary capabilities to adapt and refine their strategies through real-world...
Shuai Zhao, Xinyi Wu, Shiqian Zhao +4 more
During fine-tuning, large language models (LLMs) are increasingly vulnerable to data-poisoning backdoor attacks, which compromise their reliability...
Anindya Sundar Das, Kangjie Chen, Monowar Bhuyan
Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when...
Rui Wu, Yihao Quan, Zeru Shi +3 more
Safety-aligned Large Language Models (LLMs) still show two dominant failure modes: they are easily jailbroken, or they over-refuse harmless inputs...
Lesly Miculicich, Mihir Parmar, Hamid Palangi +4 more
The deployment of autonomous AI agents in sensitive domains, such as healthcare, introduces critical risks to safety, security, and privacy. These...
Yuhao Sun, Zhuoer Xu, Shiwen Cui +4 more
Large Language Models (LLMs) have achieved remarkable progress across a wide range of tasks, but remain vulnerable to safety risks such as harmful...
Muhammad Faheemur Rahman, Wayne Burleson
Memristive crossbar arrays enable in-memory computing by performing parallel analog computations directly within memory, making them well-suited for...
Guobin Shen, Dongcheng Zhao, Haibo Tong +3 more
Ensuring Large Language Model (LLM) safety remains challenging due to the absence of universal standards and reliable content validators, making it...
Shojiro Yamabe, Jun Sakuma
Diffusion language models (DLMs) generate tokens in parallel through iterative denoising, which can reduce latency and enable bidirectional...
Boyang Zhang, Istemi Ekin Akkus, Ruichuan Chen +4 more
Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in processing and reasoning over diverse modalities, but their...
Ayda Aghaei Nia
Completely Automated Public Turing tests to tell Computers and Humans Apart (CAPTCHAs) are a foundational component of web security, yet traditional...
Akio Hayakawa, Stefan Bott, Horacio Saggion
Despite their strong performance, large language models (LLMs) face challenges in real-world application of lexical simplification (LS), particularly...
Zherui Li, Zheng Nie, Zhenhong Zhou +7 more
The rapid advancement of Diffusion Large Language Models (dLLMs) introduces unprecedented vulnerabilities that are fundamentally distinct from...
Gauri Kholkar, Ratinder Ahuja
As autonomous AI agents are used in regulated and safety-critical settings, organizations need effective ways to turn policy into enforceable...
Yuqiao Meng, Luoxi Tang, Feiyang Yu +4 more
Large language models (LLMs) are increasingly used to help security analysts manage the surge of cyber threats, automating tasks from vulnerability...
Zeyu Shen, Basileal Imana, Tong Wu +3 more
Retrieval-Augmented Generation (RAG) enhances Large Language Models by grounding their outputs in external documents. These systems, however, remain...
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