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 641–660 of 759 papers
Clear filtersXingwei 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...
Yizhong Ding
Webshells remain a primary foothold for attackers to compromise servers, particularly within PHP ecosystems. However, existing detection mechanisms...
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...
Yangyang Guo, Ziwei Xu, Si Liu +2 more
This study reveals a previously unexplored vulnerability in the safety alignment of Large Language Models (LLMs). Existing aligned LLMs predominantly...
Sen Nie, Jie Zhang, Zhuo Wang +2 more
Vision-language models (VLMs) such as CLIP have demonstrated remarkable zero-shot generalization, yet remain highly vulnerable to adversarial...
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...
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...
Narek Maloyan, Dmitry Namiot
The proliferation of agentic AI coding assistants, including Claude Code, GitHub Copilot, Cursor, and emerging skill-based architectures, has...
Chen Ling, Kai Hu, Hangcheng Liu +3 more
Large Vision-Language Models (LVLMs) are increasingly deployed in real-world intelligent systems for perception and reasoning in open physical...
Mohammad Zare, Pirooz Shamsinejadbabaki
Membership inference attacks (MIAs) pose a serious threat to the privacy of machine learning models by allowing adversaries to determine whether a...
Jiankai Jin, Xiangzheng Zhang, Zhao Liu +2 more
Machine learning systems can produce personalized outputs that allow an adversary to infer sensitive input attributes at inference time. We introduce...
David Condrey
Recent proposals advocate using keystroke timing signals, specifically the coefficient of variation ($δ$) of inter-keystroke intervals, to...
Andy Zhu, Rongzhe Wei, Yupu Gu +1 more
Machine unlearning (MU) for large language models has become critical for AI safety, yet existing methods fail to generalize to Mixture-of-Experts...
Xing Su, Hao Wu, Hanzhong Liang +4 more
Blockchain systems are increasingly targeted by on-chain attacks that exploit contract vulnerabilities to extract value rapidly and stealthily,...
Jivnesh Sandhan, Fei Cheng, Tushar Sandhan +1 more
Large Language Models (LLMs) are increasingly deployed in domains such as education, mental health and customer support, where stable and consistent...
Song Xia, Meiwen Ding, Chenqi Kong +2 more
Multimodal large language models (MLLMs) exhibit strong capabilities across diverse applications, yet remain vulnerable to adversarial perturbations...
Fengheng Chu, Jiahao Chen, Yuhong Wang +4 more
While Large Language Models (LLMs) are aligned to mitigate risks, their safety guardrails remain fragile against jailbreak attacks. This reveals...
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