AI Threat Alert indexes 3,371+ 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 3,371 papers
Leo Sambrook, Sampo Sovio
AI agents performing cryptographic operations (signing Git commits, authenticating API calls, issuing certificates) currently store private keys in...
Abdulkadir Külçe, Alihan Esen, Cağla Fikir +4 more
This paper presents ECHO (Enhanced Care \& Health Observer), a locally-deployable conversational health assistant for long-term chronic care...
Jiale Han, Xiang Li, Jing Qian +7 more
Economic World Models (EWMs) are generative economic models that simulate how economies evolve from within by modeling heterogeneous agents, their...
Dong Wang, Qiaoyu Han, Lin Yang +3 more
Test assertions are critical elements of unit tests, serving as checkpoints to validate expected behavior and ensure software correctness. Numerous...
S. M . Bhagya P. Samarakoon, M. A. Viraj J. Muthugala, W. K. R. Sachinthana +1 more
Vision-Language Models (VLMs) are increasingly deployed as planners in robotic systems, where they translate natural-language commands into...
Changshuo Liu, Yanzheng Jin, Shangfeng Cai +3 more
With increasingly diverse and heterogeneous information sources, effectively leveraging multimodal data is becoming pivotal for high-quality...
Yuchen Chen, Wei Cheng, Yuan Xiao +5 more
LLM customization platforms allow users to build task-specific models for code intelligence tasks by embedding instructions into system prompts,...
Jialuo Chen, Lingqi Jiang, Xinhao Deng +7 more
Self-evolving skill (SES) systems distill agent trajectories into persistent skills, allowing untrusted experience to become trusted instruction. We...
He Zhang, Feilong Li, Dingning Long +5 more
Smart-home assistants increasingly use multimodal large language models (MLLMs) that perceive video and audio directly. This raises a safety question...
Buzhao Liu, Xinhang Ma, Yevgeniy Vorobeychik
The remarkable instruction-following ability of modern LLMs has enabled their practical use as the minds of agents that can autonomously complete...
Alina Klerings, Jannik Brinkmann, Heiner Stuckenschmidt +1 more
Large language models typically undergo post-training to align them with safety policies but there exist many sophisticated jailbreaks that sidestep...
Yanting Wang, Chenlong Yin, Runpeng Geng +1 more
Prompt injection poses significant security risks to LLM agents. Efficient and effective red-teaming is therefore critical, both for evaluating these...
Johann Knechtel, Ozgur Sinanoglu, Paul V. Gratz +1 more
The semiconductor industry is undergoing a dual revolution: the shift toward heterogeneous 2.5D chiplet systems and the integration of Large Language...
Yuxuan Huang, Xingyu Zeng, Tianhang Zheng +1 more
Released aligned large language models remain vulnerable to malicious downstream finetuning. Existing defenses are largely designed for the...
Ethen Santana, Gabriel Gyaase, Hao Zheng
Hardware designs, like software, are susceptible to bugs that can introduce security vulnerabilities and create opportunities for malicious...
Ali Khoramfar, Mohammad Javad Dousti, Alireza Mohamadian +1 more
Standard accuracy metrics for VLMs often mask significant reliability failures in sensitive domains. In this work, we utilize a...
Longtao Guo, Zelin Zhang, Kaifeng Huang +1 more
LLM-based web agents automate user tasks by observing webpages and executing browser actions on behalf of users. As these agents operate on real web...
Rui Yang, Michael Fu, Kla Tantithamthavorn +2 more
Autonomous coding agents are increasingly embedded in enterprise software workflows with delegated authority over connected systems. Central to this...
Liehuang Zhu, Yuhang Li, Tianxing Wang +7 more
AI agents are evolving from isolated task executors into networked autonomous entities that can communicate, delegate tasks, invoke tools, access...
Azizi Ariffin, Afif Haris, Faiz Zaki +2 more
Network intrusion detection systems (IDS) trained on fixed traffic snapshots decay silently after deployment as threat distributions shift....
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 3,371+ 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