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 523 papers
Clear filtersJeremy Qin, David Schmotz, Derck Prinzhorn +3 more
Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct what happened. These analyses...
Sheng Liu, Panos Papadimitratos
Federated learning (FL) can improve world model (WM)-based autonomous driving (AD) without centralizing raw private vehicle data, but it also turns...
Yanming Xiu
Video see-through extended reality (VST XR) systems commonly use headset screenshots or captured frames as proxies for the user's first-person visual...
Daiki Chiba, Hiroki Nakano, Takashi Koide
Short claims such as not-phishing or official can change how a large language model (LLM) judges a domain name, without explicit prompt-injection...
Haoyang Li, Yaxin Xiao, Linyan Dai +5 more
Multimodal training relies on image-text corpora collected from external sources, creating opportunities for attackers to poison the data. Stealthy...
Harsh Verma
Blockchain and artificial intelligence (AI) are converging into a single infrastructural layer for securing data sharing, model integrity, and...
Jasem Khelifi, Issam Oukhay, Ali Ouni +2 more
Agentic workflows shift software development from prompting AI agents for individual tasks to defining recurring work that agents execute...
Tianhao Chen, Yuhan Wei, Weifei Jin +3 more
Multi-passage corpus poisoning often repeats one target claim across similar documents, creating correlated lexical and semantic patterns that...
Christopher Burger, Christina Trotter, Joseph Carlisle +1 more
The rapidly advancing capabilities of vision-language models (VLMs) present a systemic challenge to academic integrity. VLMs now allow students to...
Abdullahil Kafi, Alvi Ataur Khalil
Retrieval augmented generation (RAG) systems have emerged as the dominant architecture for grounding large language model (LLM) outputs in verifiable...
Frank E. Bobe, Gregory D. Vetaw, Darshan W. Bryner +2 more
Activation steering modifies LLM behavior at inference time, but identifying where and how strongly to steer remains manual. We introduce Deep Noir,...
Leilei Chen, Lan Zhang, Chen Tang +5 more
In pay-per-token LLM services, the more a model says, the more users pay. Dishonest providers can covertly manipulate generation to inflate output...
Qi Rong Sua, Junhao Dong, Nguyen Duc Thai +3 more
Multi-agent trading systems built on large language models (LLMs) are beginning to appear in quantitative finance, yet their robustness to...
Matteo Golinelli, Idilio Drago, Matteo Boffa +2 more
AI agents for security inspect web pages, source code, logs, configuration files, and command outputs. These environments may contain deceptive...
Tanzim Hossain Safin, Sharif Noor Zisad, Swakkhar Shatabda +1 more
Multi-agent LLM systems increasingly automate tasks involving agents with different levels of privilege, creating a security risk in which a...
Deepak Akkil, Tamer Abuelsaad, Karthik Vikram +5 more
As AI agents move from bounded tasks to persistent deployments, failures can propagate through memory, tools, other agents, and environmental state...
Vincent Karpf, Joseph Reth, Eike Gerhardt +5 more
Long-horizon scientific discovery requires agents to alternate between exploration, disciplined execution, and critical reassessment as evidence...
Danny Wood, James Stringer
The difficulty of training large language models (LLMs), together with their ubiquity, raises the threat of stegomalware, where malicious payloads...
Fares Trad, Simin Chen, Hung Viet Pham +2 more
Software agents with Large Language Models (LLMs) are designed for Automated Program Repair (APR) tasks, raising the possibility that, in the near...
Saranraj S, Saranya M S, Alex David S +1 more
Robust aggregation methods for federated learning quietly rest on a fragile assumption: that whoever shows up in a given round is a fair sample of...
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