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 261–280 of 4,319 papers
Mohsen Amoei, Kathleen Fraser, Dan Poenaru
Health systems are deploying large language models (LLMs) into clinical workflows, often on the assumption that a second automated check can only...
Xiaoyu Wu, Zhaoxin Yu, Xinglin Xiao +1 more
Advancing physics reasoning in large language models requires scalable training data that connect physical laws, concrete problem scenarios, and...
Dixi Yao, Tahseen Rabbani, Tian Li
Retrieval-Augmented Generation (RAG) enhances the capabilities of large language models (LLMs) by querying external structured knowledge. However, it...
Hasan Demirkiran, Jens Ernstberger
AI agents take actions through tools. Some actions are sensitive, so guards that supervise them must themselves be evaluated reliably. Yet the data...
Kshitij Mishra, Abhijith Sharma, Nils Lukas +1 more
Modern agentic systems extend language models with external tools, enabling them to complete complex tasks through multi-turn interactions. As these...
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...
Zhiyuan Wang, Yuezhi Zhou, Ziqi Zhang +3 more
On-device deployment of large language models (LLMs) is increasingly adopted due to latency and privacy requirements, but exposes proprietary models...
Vasileios Perifanis, Nikolaos Pavlidis
Federated learning (FL) is increasingly used to adapt a pretrained, centrally fine-tuned model to data that remain on user devices, beyond training a...
Shuoran Jiang, Wentao Zhu, Yang Xiang +8 more
Biological intelligence continually adapts to new information while retaining prior skills through localized plasticity. In contrast, continual...
Yufei Chen, Yao Wang, Haibin Zhang
Retrieval-augmented generation (RAG) mitigates hallucinations and knowledge staleness in large language models using external knowledge. However,...
Jieyu Li, Jingya Li, Sheng Li +2 more
Agent harnesses, the prompt and tool code around a base model, leak. Claude Code's 512,000 lines were mirrored within hours of a packaging error. A...
Huaien Zhang, Zhengjie Zhao, Yu Pei +4 more
Rust has become a popular systems programming language in recent years because of its strong guarantees on memory and concurrency safety. Many types...
Huaien Zhang, Yu Pei, Hao Chen +1 more
Static application security testing (SAST) tools help detect potential software vulnerabilities, but they themselves contain faults undermining...
Ferry Afit Kurniawan, Kazushi Okamoto, Koki Karube +2 more
Cyber threat intelligence (CTI) relies on the timely identification of emerging threats, enabling organizations and security analysts to support...
Junhoo Lee, Baekseung Kim, Seungyeon Kim +1 more
Traditional backdoor attacks inject artificial trigger patterns into training data, causing models to misclassify triggered inputs while maintaining...
Harsh Aaryan, Ce Zhou
Autonomous vehicles (AVs) couple safety-critical perception to thermally constrained compute. Interfaces built for night perception and package...
Ravan Nazaraliyev, Yicheng Zhang, Nael Abu-Ghazaleh
NVIDIA's Grace Hopper (GH200) superchip represents a new generation of heterogeneous computing, tightly integrating a 72-core Arm-based CPU with a...
Gosha Kozhevnikov, Tyler Tracy
We present Screwtape, a pipeline that converts real agent transcripts into attacks that evade action-only monitors. An LLM attacker edits a...
Qianlong Lan, Anuj Kaul, Vinothini Pandurangan +1 more
Prompt-injection defenses are commonly evaluated as binary detectors, although deployed LLM applications must make operational decisions about...
Joas Antonio dos Santos Barbosa
LLM coding agents such as Claude Code and OpenAI Codex can drive penetration-testing tools, but they reason about an engagement as a flat list of...
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