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 41–60 of 748 papers
Clear filtersLiangsheng Liu, Si Chen, Jiamin Wu +5 more
Vision-Language Models (VLMs), such as CLIP, have shown strong zero-shot generalization but remain highly vulnerable to adversarial perturbations,...
Abzal Aidakhmetov, Donato Crisostomi, Tommaso Mencattini +3 more
Activation steering has become a popular way to control Large Language Model (LLM) behavior without fine-tuning. Since the technique is...
Shuze Liu, Qianwen Guo, Yushun Dong
Large language models (LLMs) are increasingly deployed through hosted APIs, making model extraction a practical threat to model ownership and service...
Seungwon Jeong, Jiwoo Jeong, Hyeonjin Kim +2 more
As large language models (LLMs) are widely deployed, identifying their vulnerability through jailbreak attacks becomes increasingly critical....
Paulo Ricardo Ferreira Neves, Edson Rodrigues da Cruz Filho, Paulo Henrique Eleuterio Falsetti +7 more
Large Language Models (LLMs) have transformed natural language processing, but they remain vulnerable to Prompt Injection (PI) and Jailbreak (JB)...
Alexandre Cristovão Maiorano
Security teams routinely simulate attacks against their own systems to check whether their monitoring would catch a real intruder. These...
Choongwon Kang, Seungjong Sun, Hyunmin Jun +1 more
As multimodal large language models (MLLMs) have advanced to process video inputs, concerns have emerged about their potential for malicious misuse....
Yani Wang, Yilong Yang, Yang Liu +3 more
Multimodal Large Language Models (MLLMs) have recently demonstrated remarkable capabilities in content synthesis and autonomous reasoning. Previous...
Rakshit Naidu
Machine learning models trained on sensitive data can inadvertently leak population-level information about their training distributions -- a threat...
Yoshinari Fujinuma, Varun Gangal, Traian Rebedea +4 more
Large language model (LLM) agents increasingly rely on reusable skills i.e. documents describing task-specific procedures. However, this introduces a...
Boxuan Wang, Zhuoyun Li, Xiaowei Huang +1 more
Large language models (LLMs) excel in reasoning and knowledge-intensive tasks but remain vulnerable to prompt-level adversarial attacks that preserve...
Yuyang Gong, Miaokun Chen, Jiawei Liu +5 more
Retrieval-Augmented Generation (RAG) systems are widely deployed and increasingly influential, but their reliance on external corpora exposes new...
Travis Lelle
We show that LoRA adapters, the dominant distribution format for fine-tuned LLMs, can be reliably backdoored through training data poisoning while...
Galip Tolga Erdem
Large language models (LLMs) can autonomously conduct multi-stage cyber attacks, but the consistency of their offensive behavior under repeated...
Hongtao Wang, Se Yang, Yu Chen +1 more
Large language model (LLM) agents increasingly leverage long term memory to support persistent and autonomous task execution. However, this...
Ihor Stepanov, Aleksandr Smechov
Real-time safety filtering for large language model (LLM) applications requires classifiers that can detect unsafe prompts, toxic language, jailbreak...
Junyoung Park, Sunghwan Park, Seongyong Ju +1 more
Attack Success Rate (ASR) evaluates each jailbreak with a single yes/no label at the end of generation, telling us whether a failure happened but not...
Mohan Zhang, Yuqi Jia, Zhen Tan +4 more
LLMs are vulnerable to prompt injection attacks. However, this vulnerability has been primarily demonstrated conceptually in academic studies or...
Ziyang You, Huilong He, Xiaoke Yang +1 more
Cryptographic watermarking is a leading defense for attributing text generated by large language models (LLMs). Existing schemes, including KGW,...
Matteo Gioele Collu, Riccardo Conte, Alberto Giaretta +4 more
In this paper, we investigate whether refusal behavior can be predicted from LLM intermediate activations before decoding using linear probes trained...
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