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 581–600 of 759 papers
Clear filtersLeo Schwinn, Moritz Ladenburger, Tim Beyer +3 more
Automated \enquote{LLM-as-a-Judge} frameworks have become the de facto standard for scalable evaluation across natural language processing. For...
Joachim Schaeffer, Arjun Khandelwal, Tyler Tracy
Future AI deployments will likely be monitored for malicious behaviour. The ability of these AIs to subvert monitors by adversarially selecting...
Jaehyun Kwak, Nam Cao, Boryeong Cho +3 more
Adversarial attacks against Large Vision-Language Models (LVLMs) are crucial for exposing safety vulnerabilities in modern multimodal systems. Recent...
Yanshu Wang, Shuaishuai Yang, Jingjing He +1 more
Large Language Models (LLMs) face increasing threats from jailbreak attacks that bypass safety alignment. While prompt-based defenses such as...
Youngji Roh, Hyunjin Cho, Jaehyung Kim
Large Language Models (LLMs) exhibit highly anisotropic internal representations, often characterized by massive activations, a phenomenon where a...
Zeming Wei, Qiaosheng Zhang, Xia Hu +1 more
Large Reasoning Models (LRMs) have achieved tremendous success with their chain-of-thought (CoT) reasoning, yet also face safety issues similar to...
Derin Gezgin, Amartya Das, Shinhae Kim +3 more
Recently Large Language Models (LLMs) have been used in security vulnerability detection tasks including generating proof-of-concept (PoC) exploits....
Hoang Long Do, Nasrin Sohrabi, Muneeb Ul Hassan
Large language models (LLMs) have been widely adopted in modern software development lifecycles, where they are increasingly used to automate and...
Shutong Fan, Lan Zhang, Xiaoyong Yuan
Most adversarial threats in artificial intelligence target the computational behavior of models rather than the humans who rely on them. Yet modern...
Xilong Wang, Yinuo Liu, Zhun Wang +2 more
Prompt injection attacks manipulate webpage content to cause web agents to execute attacker-specified tasks instead of the user's intended ones....
Andrew Draganov, Tolga H. Dur, Anandmayi Bhongade +1 more
We present a data poisoning attack -- Phantom Transfer -- with the property that, even if you know precisely how the poison was placed into an...
Chen Xiong, Zhiyuan He, Pin-Yu Chen +2 more
Activation steering is a practical post-training model alignment technique to enhance the utility of Large Language Models (LLMs). Prior to deploying...
Mengxuan Wang, Yuxin Chen, Gang Xu +3 more
Vision language models (VLMs) extend the reasoning capabilities of large language models (LLMs) to cross-modal settings, yet remain highly vulnerable...
Hicham Eddoubi, Umar Faruk Abdullahi, Fadi Hassan
Large Language Models (LLMs) have seen widespread adoption across multiple domains, creating an urgent need for robust safety alignment mechanisms....
Matthew P. Lad, Louisa Conwill, Megan Levis Scheirer
With the rapid growth of Large Language Models (LLMs), criticism of their societal impact has also grown. Work in Responsible AI (RAI) has focused on...
Blake Bullwinkel, Giorgio Severi, Keegan Hines +3 more
Detecting whether a model has been poisoned is a longstanding problem in AI security. In this work, we present a practical scanner for identifying...
Xiaozuo Shen, Yifei Cai, Rui Ning +2 more
The widespread adoption of Vision Transformers (ViTs) elevates supply-chain risk on third-party model hubs, where an adversary can implant backdoors...
Nirab Hossain, Pablo Moriano
Modern vehicles rely on electronic control units (ECUs) interconnected through the Controller Area Network (CAN), making in-vehicle communication a...
Patrick Cooper, Alireza Nadali, Ashutosh Trivedi +1 more
Large language models (LLMs) are known to exhibit brittle behavior under adversarial prompts and jailbreak attacks, even after extensive alignment...
Samuel Nellessen, Tal Kachman
The evolution of large language models into autonomous agents introduces adversarial failures that exploit legitimate tool privileges, transforming...
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