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 621–640 of 748 papers
Clear filtersPavlos Ntais
Large language models (LLMs) remain vulnerable to sophisticated prompt engineering attacks that exploit contextual framing to bypass safety...
Havva Alizadeh Noughabi, Julien Serbanescu, Fattane Zarrinkalam +1 more
Despite recent advances, Large Language Models remain vulnerable to jailbreak attacks that bypass alignment safeguards and elicit harmful outputs....
Kieu Dang, Phung Lai, NhatHai Phan +3 more
Large language models (LLMs) demonstrate remarkable capabilities across various tasks. However, their deployment introduces significant risks related...
Mahavir Dabas, Tran Huynh, Nikhil Reddy Billa +8 more
Large language models remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs. Defending against novel...
Xingwei Zhong, Kar Wai Fok, Vrizlynn L. L. Thing
Multimodal large language models (MLLMs) comprise of both visual and textual modalities to process vision language tasks. However, MLLMs are...
Mingrui Liu, Sixiao Zhang, Cheng Long +1 more
As Large Language Models (LLMs) become integral to computing infrastructure, safety alignment serves as the primary security control preventing the...
Yukun Jiang, Mingjie Li, Michael Backes +1 more
Despite their superior performance on a wide range of domains, large language models (LLMs) remain vulnerable to misuse for generating harmful...
Nguyen Linh Bao Nguyen, Alsharif Abuadbba, Kristen Moore +1 more
The rapid advancement of generative models has enabled the creation of increasingly stealthy synthetic voices, commonly referred to as audio...
Zheng-Xin Yong, Stephen H. Bach
We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaking....
Wei Shao, Yuhao Wang, Rongguang He +2 more
Existing defence mechanisms have demonstrated significant effectiveness in mitigating rule-based Denial-of-Service (DoS) attacks, leveraging...
Chiyu Chen, Xinhao Song, Yunkai Chai +7 more
Vision-Language Models (VLMs) are increasingly deployed as autonomous agents to navigate mobile graphical user interfaces (GUIs). Operating in...
Divyanshu Kumar, Shreyas Jena, Nitin Aravind Birur +3 more
Multimodal large language models (MLLMs) have achieved remarkable progress, yet remain critically vulnerable to adversarial attacks that exploit...
Mohamed ElShehaby, Ashraf Matrawy
Adversarial attacks pose significant challenges to Machine Learning (ML) systems and especially Deep Neural Networks (DNNs) by subtly manipulating...
Ariana Yi, Ce Zhou, Liyang Xiao +1 more
As object detection models are increasingly deployed in cyber-physical systems such as autonomous vehicles (AVs) and surveillance platforms, ensuring...
Jia Deng, Jin Li, Zhenhua Zhao +1 more
Vision-Language Models (VLMs), such as CLIP, have demonstrated remarkable zero-shot generalizability across diverse downstream tasks. However, recent...
R. Can Aygun, Yehuda Afek, Anat Bremler-Barr +1 more
With the goal of improving the security of Internet protocols, we seek faster, semi-automatic methods to discover new vulnerabilities in protocols...
Yizhu Wang, Sizhe Chen, Raghad Alkhudair +2 more
When large language model (LLM) agents are increasingly deployed to automate tasks and interact with untrusted external data, prompt injection...
Sanskar Amgain, Daniel Lobo, Atri Chatterjee +2 more
The growing use of third-party hardware accelerators (e.g., FPGAs, ASICs) for deep neural networks (DNNs) introduces new security vulnerabilities....
Zheng Zhang, Jiarui He, Yuchen Cai +4 more
As large language model (LLM) agents increasingly automate complex web tasks, they boost productivity while simultaneously introducing new security...
Isaac Wu, Michael Maslowski
As large language models (LLMs) become integrated into various sensitive applications, prompt injection, the use of prompting to induce harmful...
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