AI Threat Alert indexes 3,023+ 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 481–500 of 758 papers
Clear filtersPiyush Jaiswal, Aaditya Pratap, Shreyansh Saraswati +2 more
Large Language Models (LLMs) are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient...
Che Wang, Fuyao Zhang, Jiaming Zhang +6 more
Large Language Model (LLM) agents are susceptible to Indirect Prompt Injection (IPI) attacks, where malicious instructions in retrieved content...
Yige Liu, Yiwei Lou, Che Wang +2 more
As a distributed collaborative machine learning paradigm, vertical federated learning (VFL) allows multiple passive parties with distinct features...
David Schmotz, Luca Beurer-Kellner, Sahar Abdelnabi +1 more
LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM...
Zac Garby, Andrew D. Gordon, David Sands
A conversation with a large language model (LLM) is a sequence of prompts and responses, with each response generated from the preceding...
Natalie Shapira, Chris Wendler, Avery Yen +35 more
We report an exploratory red-teaming study of autonomous language-model-powered agents deployed in a live laboratory environment with persistent...
Xunzhuo Liu, Huamin Chen, Samzong Lu +27 more
As large language models (LLMs) diversify across modalities, capabilities, and cost profiles, the problem of intelligent request routing -- selecting...
Kaiwen Wang, Xiaolin Chang, Yuehan Dong +1 more
Secure comparison is a fundamental primitive in multi-party computation, supporting privacy-preserving applications such as machine learning and data...
Nadav Kadvil, Malak Fares, Ayellet Tal
Large Vision-Language Models (LVLMs) can be vulnerable to adversarial images that subtly bias their outputs toward plausible yet incorrect responses....
Xiaochong Jiang, Shiqi Yang, Wenting Yang +2 more
Agentic systems built on large language models (LLMs) extend beyond text generation to autonomously retrieve information and invoke tools. This...
Amirhossein Farzam, Majid Behabahani, Mani Malek +2 more
Large language models (LLMs) remain vulnerable to jailbreak prompts that are fluent and semantically coherent, and therefore difficult to detect with...
Charles Ye, Jasmine Cui, Dylan Hadfield-Menell
Language models remain vulnerable to prompt injection attacks despite extensive safety training. We trace this failure to role confusion: models...
Charles Ye, Jasmine Cui, Dylan Hadfield-Menell
Language models remain vulnerable to prompt injection attacks despite extensive safety training. We trace this failure to role confusion: models...
Sieun Kim, Yeeun Jo, Sungmin Na +5 more
Red-teaming, where adversarial prompts are crafted to expose harmful behaviors and assess risks, offers a dynamic approach to surfacing underlying...
Shenyang Chen, Liuwan Zhu
Standard evaluations of backdoor attacks on text-to-image (T2I) models primarily measure trigger activation and visual fidelity. We challenge this...
Zafir Shamsi, Nikhil Chekuru, Zachary Guzman +1 more
Large Language Models (LLMs) are increasingly integrated into high-stakes applications, making robust safety guarantees a central practical and...
Diego Soi, Silvia Lucia Sanna, Lorenzo Pisu +2 more
In recent years, stealthy Android malware has increasingly adopted sophisticated techniques to bypass automatic detection mechanisms and harden...
Jingkai Guo, Chaitali Chakrabarti, Deliang Fan
Large language models (LLMs) are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model...
Manuel Wirth
As Large Language Models (LLMs) are increasingly integrated into automated decision-making pipelines, specifically within Human Resources (HR), the...
Wyatt Benno, Alberto Centelles, Antoine Douchet +1 more
We present Jolt Atlas, a zero-knowledge machine learning (zkML) framework that extends the Jolt proving system to model inference. Unlike zkVMs...
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 3,023+ 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