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 961–980 of 1,450 papers
Clear filtersIvan K. Tung, Yu Xiang Shi, Alex Chien +2 more
Creating attack paths for cyber defence exercises requires substantial expert effort. Existing automation requires vulnerability graphs or exploit...
Miao Lin, Feng Yu, Rui Ning +6 more
Deep neural networks are highly susceptible to backdoor attacks, yet most defense methods to date rely on balanced data, overlooking the pervasive...
Tanusree Debi, Wentian Zhu
Large language model (LLM) based agents are increasingly used to automate financial transactions, yet their reliance on contextual reasoning exposes...
Naen Xu, Jinghuai Zhang, Ping He +6 more
Large language models (LLMs) have been widely integrated into critical automated workflows, including contract review and job application processes....
Aarush Noheria, Yuguang Yao
Vision-language models (VLMs) have become central to tasks such as visual question answering, image captioning, and text-to-image generation....
Chanwoo Park, Chanwoo Kim
Evasion attacks pose significant threats to AI systems, exploiting vulnerabilities in machine learning models to bypass detection mechanisms. The...
Javier Carnerero-Cano, Luis Muñoz-González, Phillippa Spencer +1 more
Regression models are widely used in industrial processes, engineering, and in natural and physical sciences, yet their robustness to poisoning has...
Pedro H. Barcha Correia, Ryan W. Achjian, Diego E. G. Caetano de Oliveira +5 more
The rapid advancement and widespread adoption of generative artificial intelligence (GenAI) and large language models (LLMs) has been accompanied by...
Xiaogeng Liu, Xinyan Wang, Yechao Zhang +5 more
Large reasoning models (LRMs) extend large language models with explicit multi-step reasoning traces, but this capability introduces a new class of...
Ningyuan He, Ronghong Huang, Qianqian Tang +3 more
In-context learning (ICL) has become a powerful, data-efficient paradigm for text classification using large language models. However, its robustness...
Xingwei Lin, Wenhao Lin, Sicong Cao +4 more
Multi-turn jailbreak attacks have emerged as a critical threat to Large Language Models (LLMs), bypassing safety mechanisms by progressively...
Yuetian Chen, Kaiyuan Zhang, Yuntao Du +5 more
Diffusion Language Models (DLMs) represent a promising alternative to autoregressive language models, using bidirectional masked token prediction....
Md Tasnim Jawad, Mingyan Xiao, Yanzhao Wu
With the widespread adoption of Large Language Models (LLMs) and increasingly stringent privacy regulations, protecting data privacy in LLMs has...
Haonan Zhang, Dongxia Wang, Yi Liu +2 more
Safety-aligned LLMs suffer from two failure modes: jailbreak (answering harmful inputs) and over-refusal (declining benign queries). Existing vector...
Nirhoshan Sivaroopan, Kanchana Thilakarathna, Albert Zomaya +6 more
Sponge attacks increasingly threaten LLM systems by inducing excessive computation and DoS. Existing defenses either rely on statistical filters that...
Harsh Chaudhari, Ethan Rathbun, Hanna Foerster +5 more
Chain-of-Thought (CoT) reasoning has emerged as a powerful technique for enhancing large language models' capabilities by generating intermediate...
Zihan Wu, Jie Xu, Yun Peng +2 more
Large Language Models (LLMs) struggle to automate real-world vulnerability detection due to two key limitations: the heterogeneity of vulnerability...
Gabriel Lee Jun Rong, Christos Korgialas, Dion Jia Xu Ho +3 more
Existing automated attack suites operate as static ensembles with fixed sequences, lacking strategic adaptation and semantic awareness. This paper...
Alexandra Chouldechova, A. Feder Cooper, Solon Barocas +3 more
We argue that conclusions drawn about relative system safety or attack method efficacy via AI red teaming are often not supported by evidence...
Thomas Heverin
Prompt injection evaluations typically treat refusal as a stable, binary indicator of safety. This study challenges that paradigm by modeling refusal...
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