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 281–300 of 1,175 papers
Clear filtersAbhijit Talluri
Adversarial robustness evaluation underpins every claim of trustworthy ML deployment, yet the field suffers from fragmented protocols and undetected...
Nandakrishna Giri, Asmitha K. A., Serena Nicolazzo +2 more
Machine learning-based static malware detectors remain vulnerable to adversarial evasion techniques, such as metamorphic engine mutations. To address...
Pranav Pallerla, Wilson Naik Bhukya, Bharath Vemula +1 more
Retrieval-augmented generation (RAG) systems are increasingly deployed in sensitive domains such as healthcare and law, where they rely on private,...
MinJae Jung, YongTaek Lim, Chaeyun Kim +3 more
While Large Language Models (LLMs) are widely used, they remain susceptible to jailbreak prompts that can elicit harmful or inappropriate responses....
Hanrui Luo, Shreyank N Gowda
Detecting jailbreak behaviour in large language models remains challenging, particularly when strongly aligned models produce harmful outputs only...
Ruixuan Liu, David Evans, Li Xiong
Indistinguishability properties such as differential privacy bounds or low empirically measured membership inference are widely treated as proxies to...
Md Rysul Kabir, Zoran Tiganj
Open-weight language models can be rendered unsafe through several distinct interventions, but the resulting models may differ substantially in...
Thamilvendhan Munirathinam
Current open-source prompt-injection detectors converge on two architectural choices: regular-expression pattern matching and fine-tuned transformer...
Wentao Zhang, Yan Zhuang, ZhuHang Zheng +3 more
Existing jamming attacks on Retrieval-Augmented Generation (RAG) systems typically induce explicit refusals or denial-of-service behaviors, which are...
Jin Zhao, Marta Knežević, Tanja Käser
Large Language Models (LLMs) are increasingly used in education, yet their default helpfulness often conflicts with pedagogical principles. Prior...
Jianming Tong, Hanshen Xiao, Krishna Kumar Nair +5 more
Multi-user virtual reality enables immersive interaction. However, rendering avatars for numerous participants on each headset incurs prohibitive...
Haochun Tang, Yuliang Yan, Jiahua Lu +2 more
Cost-aware routing dynamically dispatches user queries to models of varying capability to balance performance and inference cost. However, the...
Xuanli He, Bilgehan Sel, Faizan Ali +3 more
Large Language Models (LLMs) are increasingly exposed to adaptive jailbreaking, particularly in high-stakes Chemical, Biological, Radiological, and...
Meng Chen, Kun Wang, Li Lu +2 more
Modern Large audio-language models (LALMs) power intelligent voice interactions by tightly integrating audio and text. This integration, however,...
Firas Ben Hmida, Philemon Hailemariam, Kashif Ali Khan +1 more
Deep neural networks (DNNs) remain largely opaque at inference time, limiting our ability to detect and diagnose malicious input manipulations such...
Fortunatus Aabangbio Wulnye, Justice Owusu Agyemang, Kwame Opuni-Boachie Obour Agyekum +3 more
Ensuring the reliability of machine learning-based intrusion detection systems remains a critical challenge in Internet of Things (IoT) environments,...
Pavel Chizhov, Egor Bogomolov, Ivan P. Yamshchikov
Efficiency and safety of Large Language Models (LLMs), among other factors, rely on the quality of tokenization. A good tokenizer not only improves...
Andrii Vakhnovskyi
The United States designates Food and Agriculture as one of sixteen critical infrastructure sectors, yet no mandatory cybersecurity requirements...
Yingying Zhao, Chengyin Hu, Qike Zhang +7 more
Vision-Language Models (VLMs) have shown remarkable performance, yet their security remains insufficiently understood. Existing adversarial studies...
Shaopeng Fu, Di Wang
Adversarial training (AT) is an effective defense for large language models (LLMs) against jailbreak attacks, but performing AT on LLMs is costly. To...
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