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 2701–2720 of 3,023 papers
Xiuyuan Chen, Tao Sun, Dexin Su +38 more
Current benchmarks for AI clinician systems, often based on multiple-choice exams or manual rubrics, fail to capture the depth, robustness, and...
Jonghyun Park, Minhyuk Seo, Jonghyun Choi
One of the key challenges of modern AI models is ensuring that they provide helpful responses to benign queries while refusing malicious ones. But...
Ivan Dubrovsky, Anastasia Orlova, Illarion Iov +3 more
Benchmarking outcomes increasingly govern trust, selection, and deployment of LLMs, yet these evaluations remain vulnerable to semantically...
Avihay Cohen
Large Language Model (LLM) based agents integrated into web browsers (often called agentic AI browsers) offer powerful automation of web tasks....
Xin Zhao, Xiaojun Chen, Bingshan Liu +3 more
Large language models (LLMs) with Mixture-of-Experts (MoE) architectures achieve impressive performance and efficiency by dynamically routing inputs...
Yisen Wang, Yichuan Mo, Hongjun Wang +2 more
Despite the rapid progress of neural networks, they remain highly vulnerable to adversarial examples, for which adversarial training (AT) is...
Karthik Avinash, Nikhil Pareek, Rishav Hada
The increasing deployment of Large Language Models (LLMs) across enterprise and mission-critical domains has underscored the urgent need for robust...
Yuan Feng, Haoyu Guo, JunLin Lv +2 more
Large language models have revolutionized natural language processing, yet their deployment remains hampered by the substantial memory and runtime...
Baogang Song, Dongdong Zhao, Jianwen Xiang +2 more
Backdoor attacks pose a persistent security risk to deep neural networks (DNNs) due to their stealth and durability. While recent research has...
Jiarui Li, Yuhan Chai, Lei Du +3 more
Rule-based network intrusion detection systems play a crucial role in the real-time detection of Web attacks. However, most existing works primarily...
Juan Ren, Mark Dras, Usman Naseem
Large Vision-Language Models (LVLMs) unlock powerful multimodal reasoning but also expand the attack surface, particularly through adversarial inputs...
Ruoyu Sun, Da Song, Jiayang Song +2 more
As Large Language Models (LLMs) continue to revolutionize Natural Language Processing (NLP) applications, critical concerns about their...
João A. Leite, Arnav Arora, Silvia Gargova +5 more
Large Language Models (LLMs) can generate human-like disinformation, yet their ability to personalise such content across languages and demographics...
Tuan T. Nguyen, John Le, Thai T. Vu +2 more
Large language models (LLMs) achieve impressive performance across diverse tasks yet remain vulnerable to jailbreak attacks that bypass safety...
Ruben Belo, Marta Guimaraes, Claudia Soares
Large Language Models are susceptible to jailbreak attacks that bypass built-in safety guardrails (e.g., by tricking the model with adversarial...
Siyuan Li, Aodu Wulianghai, Xi Lin +4 more
With the increasing integration of large language models (LLMs) into open-domain writing, detecting machine-generated text has become a critical task...
Masoud Makrehchi
Artificial Intelligence (AI) has emerged as both a continuation of historical technological revolutions and a potential rupture with them. This paper...
Francesco Giarrusso, Olga E. Sorokoletova, Vincenzo Suriani +1 more
Jailbreaking techniques pose a significant threat to the safety of Large Language Models (LLMs). Existing defenses typically focus on single-turn...
Daniel Pulido-Cortázar, Daniel Gibert, Felip Manyà
Over the last decade, machine learning has been extensively applied to identify malicious Android applications. However, such approaches remain...
Sifan Li, Hongkai Chen, Yujun Cai +4 more
Vision Language Models (VLMs) have achieved impressive progress in multimodal reasoning; yet, they remain vulnerable to hallucinations, where outputs...
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