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 941–960 of 1,146 papers
Clear filtersHongwei Yao, Yun Xia, Shuo Shao +3 more
Large language models (LLMs) increasingly employ guardrails to enforce ethical, legal, and application-specific constraints on their outputs. While...
Hao Zhu, Jia Li, Cuiyun Gao +7 more
Large language models (LLMs) have achieved remarkable progress in code understanding tasks. However, they demonstrate limited performance in...
Geoff McDonald, Jonathan Bar Or
Large Language Models (LLMs) are increasingly deployed in sensitive domains including healthcare, legal services, and confidential communications,...
Yize Liu, Yunyun Hou, Aina Sui
Large Language Models (LLMs) have been widely deployed across various applications, yet their potential security and ethical risks have raised...
Amy Chang, Nicholas Conley, Harish Santhanalakshmi Ganesan +1 more
Open-weight models provide researchers and developers with accessible foundations for diverse downstream applications. We tested the safety and...
Rishi Rajesh Shah, Chen Henry Wu, Shashwat Saxena +3 more
Recent advances in long-context language models (LMs) have enabled million-token inputs, expanding their capabilities across complex tasks like...
Chloe Loughridge, Paul Colognese, Avery Griffin +3 more
As AI deployments become more complex and high-stakes, it becomes increasingly important to be able to estimate their risk. AI control is one...
Aashray Reddy, Andrew Zagula, Nicholas Saban
Large Language Models (LLMs) remain vulnerable to jailbreaking attacks where adversarial prompts elicit harmful outputs. Yet most evaluations focus...
Xu Liu, Yan Chen, Kan Ling +4 more
The widespread deployment of Large Language Models (LLMs) as public-facing web services and APIs has made their security a core concern for the web...
Chen-Wei Chang, Shailik Sarkar, Hossein Salemi +7 more
Scam detection remains a critical challenge in cybersecurity as adversaries craft messages that evade automated filters. We propose a Hierarchical...
Daniyal Ganiuly, Assel Smaiyl
Large Language Models (LLMs) are increasingly used in intelligent systems that perform reasoning, summarization, and code generation. Their ability...
Hamin Koo, Minseon Kim, Jaehyung Kim
Identifying the vulnerabilities of large language models (LLMs) is crucial for improving their safety by addressing inherent weaknesses. Jailbreaks,...
Qin Zhou, Zhexin Zhang, Zhi Li +1 more
With the rapid advancement of AI models, their deployment across diverse tasks has become increasingly widespread. A notable emerging application is...
Minseok Kim, Hankook Lee, Hyungjoon Koo
Large language models (LLMs) are reshaping numerous facets of our daily lives, leading widespread adoption as web-based services. Despite their...
Xin Liu, Aoyang Zhou, Aoyang Zhou
Visual-Language Pre-training (VLP) models have achieved significant performance across various downstream tasks. However, they remain vulnerable to...
Berk Atil, Rebecca J. Passonneau, Fred Morstatter
Large language models (LLMs) undergo safety alignment after training and tuning, yet recent work shows that safety can be bypassed through jailbreak...
Peng Ding, Jun Kuang, Wen Sun +5 more
Large language models (LLMs) remain vulnerable to jailbreaking attacks despite their impressive capabilities. Investigating these weaknesses is...
Phil Blandfort, Robert Graham
Activation probes are attractive monitors for AI systems due to low cost and latency, but their real-world robustness remains underexplored. We ask:...
Ruofan Liu, Yun Lin, Zhiyong Huang +1 more
Large language models (LLMs) are increasingly integrated into IT infrastructures, where they process user data according to predefined instructions....
Xin Yao, Haiyang Zhao, Yimin Chen +3 more
The Contrastive Language-Image Pretraining (CLIP) model has significantly advanced vision-language modeling by aligning image-text pairs from...
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