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 161–180 of 388 papers
Clear filtersGuoxin Shi, Haoyu Wang, Zaihui Yang +2 more
Adversarial behavior plays a central role in aligning large language models with human values. However, existing alignment methods largely rely on...
Martin Odersky, Yaoyu Zhao, Yichen Xu +2 more
AI agents that interact with the real world through tool calls pose fundamental safety challenges: agents might leak private information, cause...
Jingyuan Xie, Wenjie Wang, Ji Wu +1 more
Supervised fine-tuning (SFT) is essential for the development of medical large language models (LLMs), yet prior poisoning studies have mainly...
Qianxun Xu, Chenxi Song, Yujun Cai +1 more
Recent advances in text-to-video diffusion models have enabled high-fidelity and temporally coherent videos synthesis. However, current models are...
Qianxun Xu, Chenxi Song, Yujun Cai +1 more
Recent advances in text-to-video diffusion models have enabled high-fidelity and temporally coherent videos synthesis. However, current models are...
Idan Habler, Vineeth Sai Narajala, Stav Koren +2 more
Retrieval-Augmented Generation (RAG) systems are essential to contemporary AI applications, allowing large language models to obtain external...
Bruce W. Lee, Chen Yueh-Han, Tomek Korbak
Frontier AI agents may pursue hidden goals while concealing their pursuit from oversight. Alignment training aims to prevent such behavior by...
Sarthak Munshi, Manish Bhatt, Vineeth Sai Narajala +4 more
While prior work has focused on projecting adversarial examples back onto the manifold of natural data to restore safety, we argue that a...
Inderjeet Singh, Vikas Pahuja, Aishvariya Priya Rathina Sabapathy +8 more
Current stateless defences for multimodal agentic RAG fail to detect adversarial strategies that distribute malicious semantics across retrieval,...
Zac Garby, Andrew D. Gordon, David Sands
A conversation with a large language model (LLM) is a sequence of prompts and responses, with each response generated from the preceding...
Natalie Shapira, Chris Wendler, Avery Yen +35 more
We report an exploratory red-teaming study of autonomous language-model-powered agents deployed in a live laboratory environment with persistent...
Xunzhuo Liu, Huamin Chen, Samzong Lu +27 more
As large language models (LLMs) diversify across modalities, capabilities, and cost profiles, the problem of intelligent request routing -- selecting...
Kaiwen Wang, Xiaolin Chang, Yuehan Dong +1 more
Secure comparison is a fundamental primitive in multi-party computation, supporting privacy-preserving applications such as machine learning and data...
Diego Soi, Silvia Lucia Sanna, Lorenzo Pisu +2 more
In recent years, stealthy Android malware has increasingly adopted sophisticated techniques to bypass automatic detection mechanisms and harden...
Justin Albrethsen, Yash Datta, Kunal Kumar +1 more
While Large Language Model (LLM) capabilities have scaled, safety guardrails remain largely stateless, treating multi-turn dialogues as a series of...
Nils Palumbo, Sarthak Choudhary, Jihye Choi +2 more
LLM-based agents are increasingly being deployed in contexts requiring complex authorization policies: customer service protocols, approval...
Yuval Felendler, Parth A. Gandhi, Idan Habler +2 more
Model Context Protocols (MCPs) provide a unified platform for agent systems to discover, select, and orchestrate tools across heterogeneous execution...
Varun Pratap Bhardwaj
We present SuperLocalMemory, a local-first memory system for multi-agent AI that defends against OWASP ASI06 memory poisoning through architectural...
Chengzhi Hu, Jonas Dornbusch, David Lüdke +2 more
Adversarial training for LLMs is one of the most promising methods to reliably improve robustness against adversaries. However, despite significant...
Yohan Lee, Jisoo Jang, Seoyeon Choi +2 more
Tool-using LLM agents increasingly coordinate real workloads by selecting and chaining third-party tools based on text-visible metadata such as tool...
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