AI Threat Alert indexes 3,371+ 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 61–80 of 660 papers
Clear filtersYichi Zhang, Zhiqi Wang, Huan Zhang +1 more
Key-Value (KV) cache reduces inference latency in large language models (LLMs). Traditional prefix-based reuse has low cache hit rates across...
Li Zeng, Zeyu Ye, Meng Xie +4 more
Vision-Language Models (VLMs) are known to be vulnerable to adversarial attacks, where subtle perturbations to images or texts induce erroneous...
Qinying Wang, Yong Yang, Yuan Chen +2 more
x402 is an emerging payment protocol for Web APIs and autonomous AI agents. x402 extends HTTP 402 with a payment negotiation flow and delegates...
Yohann Sidot
We study a five-agent CI/CD pipeline (triage -> developer -> security-scan -> review -> approve/deploy), built from five distinct production LLMs...
Sibo Wang, Jie Zhang, Shiguang Shan +2 more
While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their visual inputs remain...
SangJin Park, Myungsub Choi, Jineok Kim +1 more
LLM-agent defenses are typically evaluated one session at a time. In deployment, however, attacks can be distributed across independent agents,...
Xinting Liao, Behnoosh Zamanlooy, Masoumeh Shafieinejad +4 more
Textual Collaborative Prompt Optimization (TCPO) extends Textgrad (Yuksekgonul et al., 2025) to a decentralized setting by allowing multiple clients...
Muxi Lyu, Karen Shieh, Yiwei Hou +3 more
Cross-Site Scripting (XSS) remains one of the most prevalent and damaging classes of web vulnerabilities. LLM-based coding agents offer a promising...
Chengheng Li-Chen, Kyuhee Kim
Regulatory regimes such as the EU AI Act mandate machine-readable marking of synthetic text, but existing watermark detectors rely on the generating...
Tanveer Ahmed, Seyedali Pourmoafil
Phishing emails remain one of the most persistent cybersecurity threats, and machine-learning classifiers are widely used to detect them. Most...
Daekwon Pi, Sangho Lee, Young Hun Lee +1 more
While modern vehicle security depends on effective Cyber Threat Intelligence (CTI) synthesis, current automated tools struggle with unstructured data...
Habibur Rahaman, Qipan Xu, Zafaryab Haider +3 more
Modern machine learning (ML) pipelines depend heavily on third party libraries for graph compilation and hardware acceleration. While current...
Haoyan Luo, Mateo Espinosa Zarlenga, Mateja Jamnik
Sparse autoencoders (SAEs) decompose language model activations into sparse features, but standard SAEs encode each token independently and do not...
Christos Korgialas, Gabriel Lee Jun Rong, Dion Jia Xu Ho +3 more
The reliability of deepfake detectors frequently degrades under black-box adversarial transfer, as these models often rely on fragile,...
Hamid Dashtbani, Mehdi Dousti Gandomani, AmirMahdi Sadeghzadeh
Machine learning models are increasingly adapted in various domains. However, adversarial examples pose a significant threat to the reliable...
Manuel Israel Cázares
Large language models (LLMs) exhibit a well-documented gap between latent capability and consistent activation: the router hypothesis posits that...
Soham Gadgil, David Alexander, Sai Sunku +1 more
A growing class of agentic systems maintain persistent state across sessions through memory files, behavioral preferences, and knowledge bases. While...
Taksch Dube
Advertisers delegate bidding to autobidders; users delegate tasks to language-model agents. A person describes what they want to an automated proxy...
Jarosław A. Miszczak
The potential capabilities of quantum computers motivated the development of cryptographic protocols suitable for securing communication against...
Junhui Wang, Hangtao Zhang, Zhirun Zheng +5 more
Large language models (LLMs) are increasingly deployed as purpose-specific agents to handle domain-specific tasks such as customer service and code...
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 3,371+ 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