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 1–18 of 18 papers
Clear filtersYingbin Jin, Ji'an Wang, HaoYang Chai +7 more
Mobile GUI agents read the screen of a phone and operate apps on a user's behalf to complete multi-step tasks such as online shopping or messaging....
Nguyen Minh Thang
A hosted score in the Gemma 4 Developer Agent competition is one noisy number, so development needs a local evaluator that is fast, safe for...
Mo Zhou, Yiwei Zhang
Large language models increasingly evaluate, route, and moderate news, so a model's judgment of a headline has become a gatekeeping decision. We ask...
Zhitao He, Chi Him Zhang, Chengru Han +1 more
Personal AI agents face social engineering attacks supported by forged multimodal content, but existing evaluations mainly focus on text-based...
Rongting Zhang, Martin Bertran, Sandeep Avula +2 more
Indirect prompt-injection (IPI) benchmarks predominantly test planted instructions that redirect a tool-using agent toward an attacker-chosen task....
Fazong Wu, Xin Wang, Ming Yang +2 more
As large language models (LLMs) are increasingly deployed as general-purpose conversational assistants, they must handle diverse user requests while...
Norbert Sándor Szolnoki, Gábor Antal
Recent studies report promising results from supervised fine-tuning of pre-trained code language models for automated vulnerability detection on...
Tamer Abdelaziz, karim Ali
Researchers evaluate detectors of malicious smart-contract transactions on datasets that each paper assembles anew. Their positives come from...
Bohan Jiang, Dawei Li, Yasin Silva +1 more
Companies deploy large language model (LLM) assistants on their websites to advise customers. For commercial reasons, the operator can give an...
Paula Chikaodinaka Anyanwu, Valdini Douglace Lemofouet, Blessing Ngozi Uzor +7 more
As large language models (LLMs) become more widespread in Africa, their safety in low-resource languages remains largely untested since most...
Md. Robiul Islam Niloy, Abu Sayed Md. Mostafizur Rahaman
Large language models (LLMs) deployed in safety-critical settings must resist adversarial inputs designed to elicit harmful outputs. We present a...
Yukai Zhou, Wenjie Wang
A binary success indicator is a natural representation for discriminative tasks such as image classification under adversarial perturbations, where...
Justin Tan, Miao Li, Ding Zhao
Computer-use agents increasingly handle private information and act on users' behalf across desktop and web applications, including email. Phishing...
Zhiyue Xu, Xukai Wang, Zhiyuan Huang +3 more
Modern LLM agents persist state across sessions via two channels: long-lived memory files silently prepended to the system prompt, and scheduled...
Yixin Wu, Rachel Hong, Jamie Morgenstern +1 more
Machine learning benchmarks act as guideposts for model development and spur the creation of training datasets intended to improve benchmark scores....
Rui Melo, Andre Catarino, Claudia Mamede +2 more
Large language models can detect vulnerable code, yet the form of vulnerability encoding in their representations remains unclear. We analyze 8 code...
Hao Li, Tongyan Hu, Weidi Luo +8 more
Agent systems are shifting from task-scoped tool-use agents to persistent, personalized assistants such as OpenClaw. These claw-style agents maintain...
Leon Tu Nguyen, Rohan Menon, Rafael Tappe Maestro +2 more
Jailbreak methods are commonly compared using Attack Success Rate (ASR), but these comparisons depend on how responses are generated and judged. In...
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