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 652 papers
Clear filtersDavid Schmotz, Derck Prinzhorn, Luca Beurer-Kellner +3 more
A central concern in AI safety is that agents may treat oversight as an obstacle when it conflicts with completing their goals. We study instrumental...
Luciano Maldonado
Large language models increasingly operate as persistent assistants in user-facing, shared-session, and tool-augmented settings. When users disclose...
Saim Rehman, Muhammad Shafique
Deployment-oriented compression is attractive for resource-constrained brain--computer interfaces (BCIs), but whether it changes adversarial...
Qingyu Wu, Zeyu Feng, Yongda Yu +2 more
Prompt injection can degrade benign task performance without eliciting harmful content. Yet many attack objectives depend on task labels or...
Manit Baser, Aditya Nawal, Dinil Mon Divakaran +1 more
Open-weight LLMs give downstream users control over the inference stack, but this flexibility can undermine post-release guarantees that sensitive...
Spencer King, Zhilu Zhang, Mikhail Kuznetsov +3 more
LLM agents are deployed into infrastructure that grants them broad host authority, yet existing agent-security benchmarks and defenses operate almost...
Mingyuan Li, Yanna Jiang, Guangsheng Yu +4 more
Privacy-sensitive organizations may run large language models (LLMs) in restricted or air-gapped environments while exporting selected diagnostic...
Saeedeh Lohrasbi, Mohammad Mamun, Ahmed Yehia +2 more
Multi-stage LLM-based cyber agents may complete attack workflows while remaining brittle, costly, or reliant on incorrect interpretations of...
Jian Xu
Agentic video-generation systems close a loop between a generator and a verifier: an LLM plans shots, calls a text-to-video model, and a multimodal...
Xin Shen, San-Zhuo Xi, Yali Du +1 more
Recent advances in large language models (LLMs) have made them widely used for code-related tasks. Identifier names are statistically informative in...
Vansh Wahi
A higher evaluation score does not always mean a better language model system. When optimization exploits an evaluator's mistakes, measured progress...
Dahlia Shehata, Ming Li
Large language models (LLMs) exhibit a parametric vulnerability to adversarial swarm consensus. To mitigate this sycophancy, we introduce Contrastive...
Volkan Dağlı, Zerrin Dağlı, Dağhan Dağlı
Deploying Large Language Models for runtime operational triage incurs prohibitive latency (>100-500 ms), high VRAM requirements (>4-8 GB), and...
Jiling Zhou, Aisvarya Adeseye, Antti Hakkala +2 more
Large Language Models (LLMs) are increasingly used in cybersecurity, where accurate analysis often requires multi-step and context-dependent...
Kaiyuan Zhang, Yuke Peng, Ke Jiang +1 more
Large language model (LLM) agents increasingly execute long-horizon workflows through external tools, allowing untrusted outputs to influence...
Kaiyuan Zhang, Yuke Peng, Ke Jiang +1 more
Large language model (LLM) agents increasingly execute long-horizon workflows through external tools, allowing untrusted outputs to influence...
Akihisha Fujiyama, Niwase Shamim
AI is increasingly used to automate computer security testing, and the tools must decide for themselves whether an attack succeeded. A finding that a...
Muhammad Abdullah Sohail
The Model Context Protocol (MCP) has emerged as the dominant interface for connecting autonomous agents to external data sources and execution...
Elia Nikolaou, Magnus Wiik Eckhoff, Robert Flood +3 more
LLM-based agents generate and execute multi-step plans that invoke external tools which can access private data or execute commands. In this setting,...
Hasnain Irshad, Anam Mughees, Neelam Mughees +2 more
Agentic browsers can execute security-sensitive actions under a user's authenticated session, making indirect prompt injection and deceptive...
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