AI Threat Alert indexes 3,771+ 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 883 papers
Clear filtersLukáš Brůna, Robert Bridges, Adam Ek
Large Language Models (LLMs) consume and produce a single sequence of text; hence, if text can be added to the beginning of the LLM's response, i.e.,...
Karina Elzer, Niklas Netterstrøm Johansen, Emmanouil Vasilomanolakis
Publicly exposed large language model (LLM) infrastructure creates a growing attack surface, yet real-world targeting remains poorly understood. We...
Yu-Ling Liao, Tzu-Chin Chiu, Zong-You Chen +2 more
Large audio-language models (LALMs) expand language models to process and interpret audio, but also expose them to heterogeneous audio jailbreaks. We...
Siyuan Pang, Yepeng Yao, Zhengwei Jiang +2 more
The Node.js ecosystem heavily relies on NPM packages, and software supply chain attacks targeting malicious NPM packages are rampant. Malicious code...
Tiantong Wu, Wei Yang Bryan Lim
Most studies of prompt injection focus on generative agents, leaving their effects on models with schema-defined outputs unclear. We examine these...
Arthur Cordeiro, Alberto Maria Mongardini, Emmanouil Vasilomanolakis
Honeypots are designed to deceive attackers, and recent work shows they can also derail autonomous LLM-based pentesters. These evaluations, however,...
Ariel Flint, Luca Maria Aiello, Sara M. Constantino +2 more
As generative AI agents are deployed at scale, safety will depend not only on technical safeguards and individual model design, but also on...
Fernando Outeda, Gustavo Betarte, Juan Diego Campo +1 more
Large language models (LLMs) are increasingly deployed in production systems, raising concerns about their exposure to adversarial manipulation...
Florian Krone, Elena Hoemann, Sven Hallerbach
Neural networks, both convolution or transformer based, are essential for modern computer vision systems. However, they are vulnerable to small...
Ben Shapira, Roi Cohen, Shang-Tse Chen +1 more
With face-recognition models now embedded in everyday authentication and surveillance, recent works have pinpointed a critical weakness: these models...
Hyeongjun Choi, Wonyoung Jung, Haehoon Seo +1 more
Large language models are being integrated into malware triage workflows as reasoning components that summarize static evidence and produce...
Makram Chehayeb, Walid Fahs, Amina Rizk +2 more
The availability and consistency of online services remain vulnerable due to Distributed Denial of Service (DDoS) attacks. These attacks are evolving...
Jiachang Zhang, Min Chen, Xiao Ren +4 more
Retrieval-augmented generation (RAG) systems enhance large language models (LLMs) with external knowledge but have been demonstrated to be vulnerable...
Roberto Riaño, Gorka Abad, Stjepan Picek +1 more
Pretrained world models, learned simulators that encode an observation into a latent state and predict how it evolves under actions, are beginning to...
Oliver Stevanovic, Jasmin Wachter
Logic attack graphs grounded in scanner output provide explicit and auditable attack path reasoning LLM-based agents lack. Integrating symbolic...
Zhaofeng Yu, Haokai Ma, Dongyang Zhan +3 more
A centralized LLM-based multi-agent system (MAS) extends its functionality by registering new worker agents, whose descriptions are read by the...
Aashiq Muhamed, Mona T. Diab, Virginia Smith +2 more
Backdoor poisoning attacks add poisoned examples to otherwise-clean finetuning data, pairing a trigger with a target behavior that the model learns...
Yusuf Khalid Shire, Sang-Chul Kim
Prompt-injection detectors are typically evaluated using aggregate F1 on in-distribution test data, which offers limited insight into behavior under...
Bingzheng Wang, Xiaoyan Gu, Wentao Wang +3 more
Large language model (LLM) agents interact with external environments through tool invocation, but tool outputs can also expose them to indirect...
Haozhe Lu, Jiaqi Li, Xinyuan Zhu +1 more
Retrieval-Augmented Generation (RAG) can ground large language model (LLM) outputs in external evidence, but it also exposes the system to knowledge...
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 3,771+ 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