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 21–37 of 37 papers
Clear filtersJunyu Lin, Mengjie Wu, Yonghao Dong +11 more
As streaming generation becomes the dominant serving paradigm for both text-only and multimodal large language models, ensuring safety throughout the...
Haowen Dai, Alejandro Guerra-Manzanares
Indirect prompt injection creates a distinctive risk for blue-team Large Language Model (LLM) agents in Security Operations Centers (SOCs). Malicious...
Yiran Lin, Ye Deng, Ziqi Pan +2 more
Artificial intelligence (AI) agents are increasingly explored as collaborative learning partners in mathematics education, yet it remains unclear...
Gerardo Iuliano, Gabriele De Vito, Dario Di Nucci
Smart contracts are immutable programs deployed on blockchain platforms, where vulnerabilities can translate directly into financial loss. Among the...
Jonathan F. Jao, Andrew Kyle Lampinen
Automated red-team auditing of language models is an important way to evaluate safety-relevant behaviors. These audits implicitly search a tree of...
Yuelin Han
Prior work framed the envelope layer as the channel through which malicious content enters an agent, and established it as a defense surface...
Hongyan Chang, Hady Elsahar, Tom Sander +10 more
Proprietary language models and their reasoning traces are vulnerable to API-based distillation, where an adversary trains a student model on the...
Yuchen Zhang, Yaxiong Wang, Yujiao Wu +6 more
Multimodal forgery detection is commonly studied under a static assumption: training attacks are expected to approximate those encountered after...
Amine Lbath, Massih-Reza Amini
A vulnerability costs more to fix the later it is discovered. As coding agents generate code faster than developers can review it, software needs a...
Gadi Evron
An adversary brain is an LLM-based model of a threat actor's behavior, held as an evolving logical signature: a hypothesis with enough structure that...
Yu Yan, Jiahao Chen, Siqi Lu +4 more
As large language models (LLMs) are increasingly integrated into Web search, online recommendation, and intelligent decision-making, the third-party...
Mintong Kang, Zhaorun Chen, Bo Li
Despite the remarkable capabilities of large language models (LLMs) across diverse applications, they remain vulnerable to generating content that...
Xiarun Chen, Jiaxing Xu, Bozhi Wu +6 more
Missing project context can prevent build-dependent analyzers from constructing program relations required for vulnerability detection, while neural...
Jinhao Hu, Bardia Mohammadi, Mofasshara Binte Rafique +4 more
AI agents keep long-term memory, much of which comes from web pages and tool results. Agent harnesses, the software that runs the model, do not...
Siyuan Li, Jiayi Zhou, Zhiyuan Xia +6 more
Code reuse in modern software ecosystems facilitates the spread of 1-day vulnerabilities, posing significant security risks. Determining if patches...
Yinxiang Wang, Zehua Ma, Kejiang Chen +2 more
LLM-based guardrails are effective against indirect prompt injection (IPI), but their performance depends heavily on model capability: as the...
Haoran Xue, Nikta Akbarpour, Gias Uddin +1 more
Large language model (LLM) coding agents, such as Claude Code, are increasingly used for security auditing, with task-specific skills providing...
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