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 1–20 of 140 papers
Clear filtersPenghui Li
Office documents are now routinely uploaded to large language models (LLMs) for processing. However, an LLM does not always see what a human sees,...
Hui Xuan Tan, Stefanos Chaliasos, Alastair F. Donaldson
A zero-knowledge virtual machine (zkVM) lets an untrusted prover convince a verifier that a program, typically Rust compiled to RISC-V, ran...
Long Dang, Ali Alfatemi, Kaiqi Xiong +4 more
Distributed machine learning (DML), including conventional distributed training and federated learning (FL), enables collaborative model development...
Sai Suresh Macharla Vasu, Sumedh Santosh Joshi, Philipp Christmann +6 more
The number of paper submissions to major AI conferences has increased dramatically in recent years, substantially increasing the peer-review workload...
Sheila Zingg, Florian Tramèr, Martin Vechev +1 more
There are different levels of transparency for LLMs: open weights, open data, and/or open pipeline. Recently, more interest has emerged in fully...
Jiaming Zhang, Zherui Li, Siqi Guo +3 more
As vision-language models (VLMs) transition from frozen-encoder pipelines to native multimodal architectures, the visual channel increasingly serves...
Jiahong Qian
Audits of large language model (LLM) extraction from full-length documents report severe unreliability, leaving two questions open: what the failures...
Jerrold Huang, Junwei Quan, Saiyue Lyu +2 more
Agent skills turn natural-language instructions into actions, creating a security challenge: legitimate automation and malicious behaviour can look...
Xiuyuan Qi, Yi Wang, Wenjie Wang
Preference alignment enables language models to better reflect human values, but the preference data contains sensitive information, especially when...
Varun Kohli, Lee Bing Cheng, Nur Hazim Ghazali +3 more
Effective source recovery is critical to security applications such as malware analysis, vulnerability assessment, and legacy maintenance. Large...
Zhengyang Zhu, Liming Huang, Runmin Ji +8 more
Coding agent harnesses mediate tool use and authorize actions, yet their security mechanisms and runtime effects remain incompletely characterized....
Keegan Wang, Anantika Mannby
A language model may behave safely in a single-agent evaluation yet produce vulnerable code when its context suggests that it is part of a...
Md. Robiul Islam Niloy
Open source software (OSS) ecosystems face growing threats from sophisticated supply chain attacks including typosquatting, dependency confusion,...
Serhii Zabolotnii
Benchmarks, audits, and agent protocols describe performance, permissions, and repair, but not how observed evidence should change an agent's...
Jihun Han, Yejin Jang, Byung Il Kwak +1 more
LLM-based agents extend their capabilities through third-party skills that provide task-specific instructions, scripts, and tool-use procedures....
Zhuo Chen, Hao Zeng, Jiawei Liu +6 more
The rapid growth of submissions and reviewing workload has accelerated the use of large language models (LLMs) in peer review. Prior studies suggest...
Bravish Ghosh
Autonomous coding agents read untrusted files, run shell commands and spawn sub-agents with little supervision, yet their record is usually an...
Mauro Conti, Lorenzo Perinello, Umberto Salviati
The mobility sector is undergoing a paradigm shift driven by advances in Generative Artificial Intelligence. With a global market valued at...
Heewon Baek, Alsharif Abuadbba, Kristen Moore +2 more
Agentic AI extends LLM security beyond generated content to persistent state, autonomous actions, tool use, and interactions with humans and other...
Mengxiao Wang, Nitesh Saxena
Autonomous large language model (LLM) agents are moving rapidly into high-stakes domains, yet existing agentic-AI security studies remain largely...
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