AI Threat Alert indexes 4,319+ 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 1,007 papers
Clear filtersAdel Khorramrouz, Yi-Chia Wang, Sharon Levy
Social psychology has long described how people can be persuaded to interpret a harmful act as moral. Recent research suggests that Large Language...
Sarthak Gupta, Priyanka Tembey
Several recent studies propose detecting prompt injections from a language model's internal state. However, these methods do not measure a single...
Kshitij Mishra, Salem Lahlou, Nils Lukas
Indirect prompt injection uses untrusted retrieved content, tool outputs, or agent messages to override an LLM's intended behavior. We show that...
Xi Chen, Chunyi Zhou, Rui Zeng +3 more
Federated fine-tuning of large language models (LLMs) allows multiple clients to collaboratively adapt models without sharing raw data, offering...
Kaan Kale, Sriram Vishwanath
Linear probes on a model's hidden states are used as cheap monitors for indirect prompt injection: they screen the tool outputs an agent reads and...
Yan-Lun Chen, Pin-Yu Chen, Chia-Mu Yu
Third-party skills can expose LLM agents to malicious instructions hidden by encoding. We introduce Ciphered Skill Injection (CSI), which embeds such...
Fasheng Miao, Zhaoyu Hu, Xiang Li +5 more
Large language model (LLM) agents are increasingly used for vulnerability analysis, yet existing benchmarks provide limited coverage of exploitation...
Xiang Li, Aichun Huang, Mingming Zhang +1 more
TypeSafe AI's Jev is a new kind of safety judge. It generates no text and no label: it answers questions the developer defines in advance and returns...
Maria-Ioana-Andrea Ivan, Orhan Ermis, Ruxandra F. Olimid
With recent developments in Artificial Intelligence (AI), the adoption of distributed learning paradigms such as Federated Learning (FL) has emerged....
Ali Javeri, Javad Hezareh, Radin Shahdaei +1 more
Score-based black-box adversarial attacks pose a serious threat to deployed machine learning systems by exploiting repeated model queries to craft...
Mohammad Reza Mirbagheri, Amir Mahdi Sadeghzadeh
Aligned large language models (LLMs) remain vulnerable to jailbreak prompts that circumvent their safety guardrails, making the identification of...
Seyedarmin Azizi, Erfan Baghaei Potraghloo, Massoud Pedram
A typed decision model reads a piece of text and returns a probability over caller-defined options, each with a short written definition, generating...
Luman Zhao, Minghui Xu, Yue Zhang +1 more
Large language models (LLMs) perform remarkably well on complex tasks, yet remain highly vulnerable to prompt injection attacks, where malicious...
Adam Y. J. Jones, Yu Yuan, Sergio Maffeis
Speculative decoding is a popular technique for increasing the speed and reducing the costs of large language model (LLM) inference by verifying...
Juanyang Xu, Zheng Wang, Xingyu Zhao +2 more
When the harmfulness of an LLM agent's output can be quantified, a natural jailbreaking objective is to maximize expected harmfulness over admissible...
Zitong Yao, Jiangrong Wu, Yixi Lin +3 more
Large language model (LLM) agents interact with external resources to complete complex user tasks, exposing them to indirect prompt injection (IPI),...
Xiaoyi Pang, Haoyue Feng, Quanxin Shou +3 more
Vision-Language-Action models (VLAs) are increasingly deployed in safety-critical physical environments, yet their adversarial robustness remains...
Yupu Wang, Zhengyuan Jiang, Reachal Wang +1 more
Modern agentic coding frameworks increasingly rely on community-shared rule files (e.g., AGENTS.md or .cursorrules) to guide autonomous code...
Xunlei Qian, Yingqian Cui, Yuping Lin +2 more
Jailbreak defenses for large language models are usually calibrated on a fixed set of known attack methods. However, new attack methods keep...
Pengfei He, Deep Mitra, Vishesh Sharma +4 more
LLM agents retrieve untrusted content and act through tools, creating indirect prompt-injection risks that can cause unauthorized actions or...
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 4,319+ 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