AI Threat Alert indexes 3,771+ 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 101 papers
Clear filtersYusuf Khalid Shire, Sang-Chul Kim
Prompt-injection detectors are typically evaluated using aggregate F1 on in-distribution test data, which offers limited insight into behavior under...
Bingzheng Wang, Xiaoyan Gu, Wentao Wang +3 more
Large language model (LLM) agents interact with external environments through tool invocation, but tool outputs can also expose them to indirect...
Xue Tan, Changhui Wang, Sanrui Yang +6 more
Modern large language model (LLM) agents often construct prompts by aggregating retrieved passages, user reviews, and documents from multiple...
Xue Tan, Xuandi Zeng, Yu Shao +5 more
Modern Vision-Language Retrieval-Augmented Generation (VLRAG) systems augment Large Vision-Language Models (LVLMs) with retrieved visual and textual...
Juanen Li, Peng Qian, Guanyan Li +6 more
Smart contracts, serving as the cornerstone of decentralized applications, autonomously manage trillion-dollar digital assets, making them attractive...
Haozhe Lu, Jiaqi Li, Xinyuan Zhu +1 more
Retrieval-Augmented Generation (RAG) can ground large language model (LLM) outputs in external evidence, but it also exposes the system to knowledge...
Rui Cao, Shaojing Fan, Liming Fang +3 more
Decentralized Finance (DeFi) has emerged as a rapidly growing blockchain-based financial service, where market transaction dynamics and underlying...
Asif Pinjari, Mithun Paul Saint-Germain
When an indirect prompt injection succeeds against an LLM agent, the compromise is visible in the agent's own behavior: a benign prefix of tool...
Zehua Zhang, Jie Hu, Pratham Hegde +13 more
Conventional vulnerability analysis relies on either system access or dynamic interaction, all of which may be unavailable to third-party analysts...
Bokang Zeng, Zheng Gao, Xiaoyu Li +2 more
Watermarking the final patch produced by a coding agent provides provenance evidence for the submitted artifact, but does not authenticate the...
Zhantong Xue, Pingchuan Ma, Zhaoyu Wang +3 more
Zero-knowledge (ZK) proof systems for neural-network inference compile the model into a system of arithmetic constraints. Many of these constraints...
Ryan Lum, Yongfeng Zhang
AI systems become more useful when they can adapt to the people using them, but in multi-agent systems, useful context learned by one agent often...
Jing Guan, Yachao Yang, Zhaoliang Liu +3 more
Large language models remain fragile against malicious fine-tuning, motivating training-time defenses against harmful persona drift. Preventative...
Arnab Chattopadhayay, Debdipta Halder
Large language model agents produce fluent action sequences across a wide range of tasks, yet they fail in characteristic ways once the environment...
Rafael M. Mamede, Pedro C. Neto, Ana F. Sequeira
Deepfake detectors remain vulnerable to transfer-based black-box attacks, in which adversarial examples are generated on a source surrogate model and...
Ammar Kamoona, Sajad Koushkbaghi, Mahdi Jalili +2 more
The digitalisation of electrical distribution networks has increased the exposure of power-grid infrastructure to cyber attacks. Existing intrusion...
Thomas Rivasseau
Large language model safety and security research is preoccupied with, among other things, detecting and preventing jailbreak attacks: alignment...
Julien Michel, Abdul Qadir Khan, Majed Jaber +1 more
In network traffic, legitimate behaviours and attack techniques evolve jointly - the phenomenon known as 'concept drift' [1]. Every detector is...
Iliano Fasolino
Retrieval-augmented generation (RAG) grounds a language model in retrieved documents, which reduces hallucination but creates a new attack surface:...
Hyun Gu Kang, Daniil Gurgurov, Tanja Baeumel +2 more
This study examines the compositionality of steering vectors for language and behavioral control in large language models. Focusing on language,...
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 3,771+ 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