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 1–20 of 609 papers
Clear filtersTiansheng Huang, Ananth Balashankar, Virat Shejwalkar +2 more
We expose a safety vulnerability on nascent agentic reinforcement-learning-as-a-service. Specifically, with a cost as low as \$20, we show that...
Weimin Fu, Minghao Shao, Zeng Wang +7 more
LLM agents apply approval settings, such as whether to ask before a consequential tool call, through instructions in their system prompt, and...
Vicenç Torra, Maria Bras-Amorós
Multi-agent systems provide a convenient framework for the massive deployment of agents based on Large Language Models (LLMs). It provides a sound...
Mohammed Qaiss, Peter Horvath, Michal Shagam +5 more
Can power-analysis techniques reveal secret weights of machine-learning models? Multiple recent works demonstrate proof-of-concept attacks that can...
Jingfen Qiao, Rui Li, Shuaiqun Pan +3 more
LLM agents increasingly retrieve third-party skills from public registries and follow their procedures to complete user tasks. This reliance allows...
Enhao Huang, Chunshu Xia, Yiming Li +5 more
Agent skills package reusable workflows and task-specific procedures into deployable natural-language artifacts for LLM agents. Their scale and...
Doron Shavit
LLM agents that call tools are exposed to indirect prompt injection: instructions hidden in tool outputs can steer an agent into calls the user never...
Julian Kunkel, Ali Doosthosseini
Chat remains the default surface for many large language model (LLM) tasks, even as agentic tools such as OpenCode excel at coding and automation....
Howard Halim, Eyasu Getahun Chekole, Jianying Zhou
Behavioral biometrics have emerged as a promising complement to traditional physiological biometrics by leveraging dynamic human characteristics....
Andrei Alexandru Drăghici, Sediola Ruko, Briland Hitaj +1 more
Nowadays, large language models produce text at scale, and much of it is redistributed across platforms. A moderator who finds a suspicious comment,...
Xiaobo Chen, Genliang Zhu, Ziyuan Wang +1 more
Enterprise AI agents increasingly split a user's request across subagents and merge their results, and each handoff can summarize away, alter or...
Yangguang Lin, Quan Fang, Xiaoyan Liu +1 more
Video Large Language Models (Video-LLMs) have achieved strong performance on many video understanding tasks, yet remain vulnerable to temporal...
Binhao Ma, Weikang Ding, Hanqing Guo +5 more
Speech watermarking is becoming a key defense for digital copyright and content authentication. Existing attacks treat evasion as a removal problem:...
Datta Manikanta Sri Hari Danduri, Connor Everett Glosner, Aravind Machiry
Securing bootloaders is critical to establishing the trusted computing base of modern systems. TianoCore's edk2, the de facto UEFI-based bootloader,...
Xu Zhang, Zhichao Lu
As large language model (LLM) agents take on more complex tasks with greater autonomy, security has become a major obstacle to their broader...
Mingchen Li, Ren-Yi Huang, Dumindu Samaraweera +2 more
Edge deployment of Large Language Models requires optimization techniques that reduce memory, computation, and energy costs. However, preserving task...
Ezra Edelman, Benjamin Edelman, Surbhi Goel +1 more
Despite growing capabilities, LLMs remain susceptible to prompt injections: malicious inputs that can manipulate or hijack models. In particular, it...
Yubo Cui, Xianchao Guan, Zheng Zhang
Vision-language models (VLMs) exhibit strong zero-shot generalization but remain vulnerable to adversarial attacks. Existing adversarial fine-tuning...
Abdelkader Metales, Miriam Grabenheinrich
Continual learning methods for large language models increasingly decide what to learn by surprise, keeping the inputs the model finds least...
Zihou Ren, Byungchul Tak, Long Wang
Large language model (LLM) agents often receive access to more files, accounts, and services than a task requires. Prompt injection turns this excess...
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