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 981–1000 of 1,175 papers
Clear filtersMyeongseob Ko, Nikhil Reddy Billa, Adam Nguyen +3 more
The memorization of training data in large language models (LLMs) poses significant privacy and copyright concerns. Existing data extraction methods,...
Zesen Liu, Zhixiang Zhang, Yuchong Xie +1 more
LLM-powered agents often use prompt compression to reduce inference costs, but this introduces a new security risk. Compression modules, which are...
Bin Wang, YiLu Zhong, MiDi Wan +4 more
Large language models (LLMs) have become indispensable for automated code generation, yet the quality and security of their outputs remain a critical...
Jiaxiang Liu, Jiawei Du, Xiao Liu +2 more
Pre-trained vision-language models (VLMs) such as CLIP have demonstrated strong zero-shot capabilities across diverse domains, yet remain highly...
Dongyi Liu, Jiangtong Li, Dawei Cheng +1 more
Graph Neural Networks(GNNs) are vulnerable to backdoor attacks, where adversaries implant malicious triggers to manipulate model predictions....
Devon A. Kelly, Christiana Chamon
Wide-bandgap (WBG) technologies offer unprecedented improvements in power system efficiency, size, and performance, but also introduce unique sensor...
Anum Paracha, Junaid Arshad, Mohamed Ben Farah +1 more
Data poisoning attacks are a potential threat to machine learning (ML) models, aiming to manipulate training datasets to disrupt their performance....
Pavlos Ntais
Large language models (LLMs) remain vulnerable to sophisticated prompt engineering attacks that exploit contextual framing to bypass safety...
Sarah Ball, Niki Hasrati, Alexander Robey +4 more
Discrete optimization-based jailbreaking attacks on large language models aim to generate short, nonsensical suffixes that, when appended onto input...
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....
Soham Hans, Stacy Marsella, Sophia Hirschmann +1 more
Understanding adversarial behavior in cybersecurity has traditionally relied on high-level intelligence reports and manual interpretation of attack...
Austin Jia, Avaneesh Ramesh, Zain Shamsi +2 more
Retrieval-Augmented Generation (RAG) has emerged as the dominant architectural pattern to operationalize Large Language Model (LLM) usage in Cyber...
Antônio H. Ribeiro, David Vävinggren, Dave Zachariah +2 more
Adversarial training has emerged as a key technique to enhance model robustness against adversarial input perturbations. Many of the existing methods...
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