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 121–140 of 927 papers
Clear filtersJieyu Li, Jingya Li, Sheng Li +2 more
Agent harnesses, the prompt and tool code around a base model, leak. Claude Code's 512,000 lines were mirrored within hours of a packaging error. A...
Ferry Afit Kurniawan, Kazushi Okamoto, Koki Karube +2 more
Cyber threat intelligence (CTI) relies on the timely identification of emerging threats, enabling organizations and security analysts to support...
Junhoo Lee, Baekseung Kim, Seungyeon Kim +1 more
Traditional backdoor attacks inject artificial trigger patterns into training data, causing models to misclassify triggered inputs while maintaining...
Ravan Nazaraliyev, Yicheng Zhang, Nael Abu-Ghazaleh
NVIDIA's Grace Hopper (GH200) superchip represents a new generation of heterogeneous computing, tightly integrating a 72-core Arm-based CPU with a...
Giovana Kerche Bonás, Thales Sales Almeida, Marcelo da Silva Reis +2 more
Recent literature shows that unsafe tool calls can often accompany textual refusals in language models. To investigate this hidden vulnerability, we...
Shaoyuan Xie, Zihan Zhang, Jingxuan Wang +6 more
Vision-Language-Action (VLA) models are gaining attention in autonomous driving, inheriting commonsense priors from large language models (LLMs) and...
Alicia Colmenero-Fernández
Mid-2026 reporting on autonomous AI evaluation incidents claimed that frontier large language model (LLM) agents escaped server containment through...
Jiahong Qian
Audits of large language model (LLM) extraction from full-length documents report severe unreliability, leaving two questions open: what the failures...
Tianshi Wang, Jingsong Wang, Fengling Li +3 more
Representation-based safety defenses for vision-language models (VLMs) often learn to separate harmful from benign inputs, but separation alone does...
Wei-Liang Liu, Cheng-Yen Tsai
Model signing authenticates the full-precision weights W an LLM is released with, yet users run a quantized artifact Q whose producing transformation...
Chenxu Wang, Xiaoyu Wen, Han Qi +4 more
Large language model (LLM) agents accomplish complex tasks through multi-turn interactions with external tools. However, malicious content embedded...
Min-Young Yu
Runtime policy verifiers can prevent agents from executing disallowed actions, but their decisions are typically used only for enforcement and...
Yifan Lan, Zhongye Liu, Yurui Chang +4 more
Emerging decision models such as JEV provide typed interfaces that map task instructions and observations directly to choices, judgments, and scores....
Chengtao Jian, Kai Yang
Direct Preference Optimization (DPO) has become a widely adopted approach for aligning vision-language models (VLMs), yet the security of multimodal...
Inderjeet Singh
Finite safety assessments cannot exclude an adversary that preserves unattacked behavior until certification and activates afterward. We characterize...
Dominik Seip, Bartol Markovinović, Matthias Hein
The safety of LLM-based agents currently rests on alignment training and safety classifiers, neither of which can rule out that a sophisticated...
Kristoffer Hempel, Nils Loose, Lorenzo Cavallaro +1 more
Large language model (LLM) agents are becoming an integral part of the software development lifecycle, and the capabilities granted to them allow an...
Paweł Batorski, Przemysław Spurek, Paul Swoboda
Multi-bit watermarking embeds a message, typically an account identifier, into LLM output so that harmful text can be traced to its origin. We show...
Qikun Cai, Tao Huang, Chen Hou
LLM agents now act as delegated communication intermediaries: they read private context, draft messages, and send externally visible emails on behalf...
Wenbin Chen, Jiexin Wang, Guanting Wu +2 more
The code generation capabilities of large language models (LLMs) can equally be misused to implement harmful functionality, underscoring the need 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 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