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 61–80 of 735 papers
Clear filtersAniruddh Pramod, James Oldfield, Adel Bibi
LLM agents increasingly act in multi-actor environments, exposing them to misuse from multiple sources: decomposition attacks, where a harmful...
Yao Lu, Zhaiyuan Ji, Yaxin Gao +6 more
With the rapid development of artificial intelligence, the emergence of various Large Language Models (LLMs) has created a rich model ecosystem....
Jianing Wen, Tianshi Li
As Large Language Models (LLMs) gain tool use capabilities such as web search, they can retrieve and cross-reference public information, creating...
Chaeeun Han, Soodeh Atefi, Yevgeniy Vorobeychik +1 more
As machine learning increasingly relies on public, untrusted data sources, data poisoning attacks, which inject malicious examples into training data...
Alessandro Pegoraro, Daryan Merx, Phillip Rieger +1 more
With the increasing capabilities of Large-Language-Models (LLMs) and LLM-based agents, users are increasingly using them to solve everyday problems,...
Amit Singh Bhatti, Vishal Vaddina
Safety routers send each request to one of several models and are judged against the best single model. A major routing benchmark picks that...
Jianhong Li, Jiahao Chen, Yuwen Pu +6 more
Beyond adapting Large Language Models (LLMs) to specialized applications, fine-tuning has recently been shown to recover private information that is...
Laziz U. Abdullaev, Minh-Hieu Pham, Bach Do +2 more
Activation steering provides a simple, training-free mechanism for controlling attributes of generative models such as sentiment, style, and...
Jianwei Li, Jung-Eun Kim
With the rapid adoption of large language models (LLMs) and parameter-efficient fine-tuning (PEFT) methods, the risk of backdoor attacks has become...
Jianwei Li, Min-Seon Kim, Jung-Eun Kim
Backdoored large language models (LLMs) can behave normally on benign inputs while producing attacker-specified outputs under hidden triggers....
Yi Song, Dongchen Xie, Xiaoyuan Xie +4 more
Modern software heavily relies on code reuse, so upstream vulnerability fixes do not automatically propagate to downstream codebases. Downstream...
Yu Wang, Shuhao Li, Tao Yin +4 more
Large language model (LLM) agents could help security operations centers (SOCs) investigate advanced persistent threats (APTs) by turning weak leads...
Fahao Chen, Linkang Du, Jinhao Zhou +2 more
Sparse attention is widely used to accelerate long-context inference in modern large language models (LLMs), but its input-dependent execution...
Yurong Hao, Wen Zhou, Guowei Guan +3 more
Advancing beyond traditional static scoring models, LLM-powered agentic recommender systems (LLM-ARS) instantiate users and items as autonomous...
Federico Torrielli, Gianluca Barmina, Andrea Blasi Núñez +4 more
Natural language autoencoders translate a language model's internal activations into readable explanations. Explaining every token position is...
Hongxu Su, Jianzhu Yao, Xuechao Wang +1 more
Federated learning enables multiple clients to collaboratively train models without sharing their private data. However, the lack of visibility into...
Issam Seddik, Mohamed El Amine Seddik
Securing modern AI systems against backdoor attacks remains an open challenge and requires fundamentally principled estimates of the adversary's...
Hao Chen, Wenhui Dong, Ye Chen +12 more
LLM agents operate in persistent collaborative environments involving multiple users, communities, memories, files, and tools. Community boundaries...
Hao Chen, Wenhui Dong, Ye Chen +12 more
LLM agents operate in persistent collaborative environments involving multiple users, communities, memories, files, and tools. Community boundaries...
Mashal Zainab, Salijona Dyrmishi, Hamid Bostani +2 more
Problem-space evasion attacks have exposed critical weaknesses in machine learning-based malware detectors; yet, their evaluation remains fragmented...
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