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 321–340 of 685 papers
Clear filtersXiaodong Wu, Zhimin Zhao, Qi Li +4 more
A coding agent edits files and executes shell commands with its developer's privileges, allowing malicious requests to translate directly into...
Xiaodong Wu, Yu Shi, Qi Li +5 more
Self-evolving LLM coding agents write their own tools by imitating retrieved skills from shared skill libraries. We identify a vulnerability in this...
Roberto Riaño, Gorka Abad, Stjepan Picek +1 more
Spiking Neural Networks (SNNs) are increasingly distributed as pretrained checkpoints and reused as backbones for new tasks. However, current SNN...
Lovisa Eriksson, Dave Zachariah, André M. H. Teixeira
Predictive models are widely used in many fields, but are vulnerable to false data injection attacks. To address this, detection schemes and...
Andrey Labunets
Refusal training protects AI models from jailbreaks by training models to decline unsafe queries, reducing the risk of misuse. Recent work finds that...
Dev Mehta, Lily Dukette, William Folan +4 more
The move of LLM inference to edge AI accelerators introduces new physical vulnerabilities. During execution, model parameters and intermediate...
Huakang Lin, Tiancheng Zheng, Mingxuan Sun +4 more
Mixture-of-Experts (MoE) architectures enable scalable and efficient large language models (LLMs) by selectively activating expert sub-networks...
Zuobin Xiong, Deval Mukherjee, Homook Cho +1 more
The development of federated learning (FL) techniques has helped improve the privacy preservation of users' data and extended the applications of...
Zhonghao Zhan, Hamed Haddadi
Self-evolving Skill harnesses (AutoSkills, Hermes Agent) generate more advisory orchestration automatically; their reported gains are efficiency, not...
Philipp E. Glass, Allan Tucker, Yongmin Li +1 more
Activation steering can be embedded directly into a language model's weights, shaping behaviour without inference-time intervention and offering a...
Yichao Gao, Yumo Zhang, Yunhao Yao +4 more
LLM agents integrated with external resources gain complex task capabilities, yet the unified natural-language context channel makes them vulnerable...
Joshua Penman
Everything a language model sees is tokens. The serving stack knows what each span is -- user input, tool output, instructions -- but the model must...
Nikita Kezins
Gumbel-based inference verification bounds LLM weight exfiltration by only forgiving token choices that plausibly arise from honest GPU...
Aldo Gangemi, Emanuele Bottazzi
Large Language Models (LLMs) recognise patterns but do not natively track the path of exclusions that a coherent discourse demands. When an input...
Pankaj Kumar, Judith T. Karpen, David Lario +4 more
Understanding how energetic particles are accelerated and released from the low corona into the interplanetary medium during solar eruptions is...
Zeyu Feng, Qingyu Wu, Yuzhe Luo +1 more
Large language models (LLMs) are increasingly deployed in education, healthcare, policy advising, and other interactive settings, where users engage...
Yue Li, Sudip Bhujel, Cameron Lira +2 more
Decentralized federated learning (DFL) is a promising paradigm for autonomous nodes to collaboratively train AI models without relying on a central...
Wenyun Li, Guiping Cao, Xiangyuan Lan +1 more
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language interaction, yet their safety alignment remains...
Vincenzo Sammartino, Nathanael Denis, Roberto Di Pietro
X-band SAR satellites (8-12 GHz) play a critical role in disaster response, environmental monitoring, and military intelligence. Yet, they lack...
Roshan Sood, Onat Gungor, Tajana Rosing
LLMs remain vulnerable to prompt injection attacks, where adversarial instructions embedded in user inputs or external content manipulate model...
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