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 41–60 of 450 papers
Clear filtersHabibur Rahaman, Qipan Xu, Zafaryab Haider +3 more
Modern machine learning (ML) pipelines depend heavily on third party libraries for graph compilation and hardware acceleration. While current...
Haoyan Luo, Mateo Espinosa Zarlenga, Mateja Jamnik
Sparse autoencoders (SAEs) decompose language model activations into sparse features, but standard SAEs encode each token independently and do not...
Taksch Dube
Advertisers delegate bidding to autobidders; users delegate tasks to language-model agents. A person describes what they want to an automated proxy...
Jarosław A. Miszczak
The potential capabilities of quantum computers motivated the development of cryptographic protocols suitable for securing communication against...
Weifeng Yuan, Wenbo Guo, Feng Dong +2 more
LLM agents acquire new capabilities by downloading skills from open registries. Instead of browsing these catalogs manually, developers typically ask...
Elette Boyle, MohammadTaghi Hajiaghayi, Keivan Rezaei +2 more
Model stealing attacks have recently been introduced, enabling the extraction of precise information from black-box commercial language models. In...
Eugene Ng Yi Sheng, Bingquan Shen
Self-interested agents, left unconstrained, tend toward defection in repeated social dilemmas, causing cooperative gains from trade to collapse. This...
Puji Wang, Yingchen Zhang, Ruqing Zhang +2 more
Persistent AI agents extend large language models (LLMs) beyond single-turn interaction into long-lived software systems. Unlike traditional chat...
Zifan Zhang, Minghong Fang, Dianwei Chen +5 more
Federated reinforcement learning (FRL) is crucial for enabling collaborative learning across multiple agents without sharing raw data, thereby...
Phat T. Tran-Truong, Xuan-Bach Le, Minh Nhat Nguyen
Federated foundation-model adaptation increasingly relies on heterogeneous private artifacts (retrieval corpora, prompts and demonstrations, LoRA...
Issam Seddik, Sami Souihi, Mohamed Tamaazousti +1 more
Backdoor attacks severely threaten large-scale AI models. When model owners delegate training to external compute providers within a decentralized...
Sai Varun Kodathala
AI agents issue tool calls on the basis of text they cannot verify, so any party who controls part of the context can forge the appearance of...
Kristina Nikolić, Egor Zverev, Javier Rando +3 more
Defenses that provide security guarantees against prompt injection attacks rely on strict isolation between trusted instructions and untrusted data....
Xavier Martínez-Luaña, Alba Gude-Santos, Manuel Fernández-Veiga +1 more
Distributed machine learning enables collaborative model training without centralizing data, but it also exposes learning processes to privacy...
Christopher Ellis, Shreyas Chaudhari, Mei-Yu Wang +3 more
In practice, most commercial LLM providers do not publicly release details of underlying LLM architectures. However, prior work has shown that given...
Yalin E. Sagduyu, Tugba Erpek, Aylin Yener +1 more
Semantic communication (SemCom) has emerged as a promising paradigm in which the transmission of task-relevant information is prioritized over raw...
Arash Raftari, Mehrdad Mahdavi, Nathan Blackthorn +1 more
Backdoor attacks pose a serious threat to large language models (LLMs) by causing otherwise benign systems to produce attacker-specified malicious...
Kunyang Li, Kyle Domico, Jonathan Gregory +1 more
Multi-agent systems (MAS) are increasingly used to automate complex, distributed workflows. However, their inter-agent communication channels...
Jun Wen Leong
We discover a behavioral invariant in LLM agents under persistent memory poisoning: in architectures where routing information is retrieved through...
Chen Frydman, Aviram Zilberman, Rubin Krief +6 more
Mitigating an observed adversary in an enterprise network typically takes weeks of expert work: an analyst derives a mitigation tailored to that...
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