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 21–40 of 1,450 papers
Clear filtersSeungdeok Roh, Seokjun Ryu, Sohee Park +1 more
LLM agents can exploit web vulnerabilities fast enough that patching may come too late. Deception against such agents has mostly lured them away from...
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...
Woosang Lim, Yeseul Chang, Jaewoo Lee
Tool-using agents act on email, files, and payments, so an instruction hidden in a web page or a shared document can make an agent send data or money...
Chaomeng Lu, Pooya Rostami Mazrae, Bert Lagaisse
Automated vulnerability detection is critical for securing modern software systems, yet existing learning-based approaches often treat functions as...
Quentin Le Roux, Marti Jimenez, Yannick Teglia +1 more
The protection of mature, multi-stage Face Recognition Systems is crucial to system providers. This technical report targets the threat model most...
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...
Jorge García-Carrasco, Javier Sanchis, Álvaro Navarro +2 more
Open-weight language models that fit on a single consumer GPU are becoming capable on a growing range of tasks, and they matter because they can run...
Martin Pinzger, Katharina Stengg, Christian Macho +2 more
Many recent approaches for vulnerability detection use large language models (LLMs) to classify functions as vulnerable or benign, leaving developers...
Jiamin Chang, Kristina Nikolić, Rishi Sharma +7 more
Prompt injection is usually discussed and evaluated as a single, homogeneous type of attack. However, vulnerabilities reported in real-world systems...
Naohiro Fujie, Shigeya Suzuki
We evaluate, at implementation level and under an explicit threat model, the verification pipelines of three Verifiable Credential (VC) formats:...
Tamer Abdelaziz, karim Ali
Researchers evaluate detectors of malicious smart-contract transactions on datasets that each paper assembles anew. Their positives come from...
Li Zheng, Simin Chen
Finite element method (FEM) solvers are foundational to scientific and engineering simulation, yet their susceptibility to \emph{efficiency attacks}...
Gia Phong Tran, Thai Duong Huynh, Randolph Loh +6 more
Artificial Intelligence (AI) has seen significant developments and increased usage in recent years. AI benefits various tasks, automates...
Zhuyi Zhao, Shengjie Yuan, Shengyu Wang +4 more
Single-pass scoring models such as Jev give each code function a vulnerability probability, so that security teams can rank many functions for review...
Zhuyi Zhao, Shengjie Yuan, Shengyu Wang +4 more
Single-pass scoring models such as Jev give each code function a vulnerability probability, so that security teams can rank many functions for review...
Geyuan Wang, Shunyu Liu, Siyuan Liang +2 more
Large Language Models (LLMs) have shown promise for empowering search agents to tackle complex information-seeking tasks. However, since acquiring...
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...
Kainan Zhou, Gangzhen Qian, Janet Sung +3 more
An indirect prompt injection can affect a search-augmented large language model only after its carrier page reaches model context. SearchInject...
Junwei Yao, Jianan Liu, Yongxi Zhou +1 more
Programs that use a language model as a classifier act on its most probable label. Text injected into the input can move that label to one the...
Zewei Shi, Ruoxi Sun, Minhui Xue +4 more
Accurate electricity-demand forecasting is essential for the modern energy infrastructure. Recently, Times-Series Large Language Models (TS-LLMs)...
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