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 181–200 of 1,007 papers
Clear filtersWenyun Li, Guiping Cao, Xiangyuan Lan +1 more
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language interaction, yet their safety alignment remains...
Roshan Sood, Onat Gungor, Tajana Rosing
LLMs remain vulnerable to prompt injection attacks, where adversarial instructions embedded in user inputs or external content manipulate model...
Ling Zhou, Yihao Huang, Jingling Sun +4 more
Large vision-language models (LVLMs) have achieved remarkable progress in video understanding and reasoning. Despite extensive studies on text- and...
Md Kibria Saroare, Md Rubel Ahmed
The rapid growth of large data-center (DC) loads is creating new challenges for power-system visibility, privacy, and cyber-physical security. System...
Benedikt Kluss, Niklas Bunzel
Continual Learning (CL) enables deep learning models to iteratively learn from a stream of data without forgetting prior knowledge. Existing...
Maosen Zhang, Jianshuo Dong, Boting Lu +5 more
LLMs increasingly rely on external contexts, such as pre-defined system prompts or retrieved documents, to improve generation quality. However,...
Bilal Hussain, Xiao Tang, Qinghe Du +3 more
Deep learning-based DDoS detectors for 5G-enabled cyber-physical systems face scarce labeled attack data and unrealistic synthetic substitutes, which...
Bowen Sun, Zhengyue Zhao, Xiaogeng Liu +2 more
Most large language model services use stateless defenses, which judge only the current request, to refuse harmful tasks. Decomposition attacks...
Zhida He, Xiaoyu Wen, Han Qi +5 more
Reliable jailbreak evaluation is essential for assessing LLM safety, but most existing studies rely solely on attack success rate (ASR) without...
Mark Russinovich
Safety alignment in open-weight language models is trivially removable: abliteration projects a refusal-mediating direction out of the weights in...
Zonghao Ying, Xiangfan Wu, Huiyu Wu +4 more
We assess indirect prompt injection in DeepSeek Harness (DSH), using AI-Infra-Guard (A.I.G) to construct tests, deliver controlled taint, execute...
Zonghao Ying, Xiangfan Wu, Huiyu Wu +4 more
We assess indirect prompt injection in DeepSeek Harness (DSH), using AI-Infra-Guard (A.I.G) to construct tests, deliver controlled taint, execute...
Mingxiao Liu, Zhoumian Jiang, Jianan Ma +4 more
Autonomous AI agents tackling Long Horizon Tasks depend on marketplace skills that are certified one at a time: a scanner returns a safety verdict...
Konstantinos E. Kampourakis, Vasileios Gkioulos, Sokratis Katsikas
Digital Twins (DTs) are increasingly used to monitor and analyze Cyber Physical Systems (CPS). However, in adversarial environments, the fidelity of...
Md Habibur Rahman, Jaeho Kim
LLM agents are stateless and rely on external memory to carry context between steps. Because agents treat that memory as trustworthy, an adversary...
Riku Mochizuki, Shusuke Komatsu, Souta Noguchi +1 more
We characterize the attack surface of generative search engines (GSEs) against poisoning attacks in the political domain, from the perspectives of...
Md Wasiul Haque, Sagar Dasgupta, Mizanur Rahman +1 more
Autonomous vehicles depend on large safety-critical software stacks, where weaknesses reachable from adversarial inputs may affect steering, braking,...
Ze Yu, Hongwei Zhen, Chao Shen +1 more
The rapid growth of large language model (LLM) services is accelerating the expansion of AI data centers (AIDCs), intensifying concerns over power...
Berkay Ozcam, Irem Onen, Mehmet Fatih Amasyali +1 more
The rapid advancement of Large Language Models (LLMs) has facilitated their ubiquitous integration into various domains, leading to widespread...
Bocheng Chen, Han Zi, Roucheng Ou +5 more
In the era of large language models (LLMs), attackers often manipulate natural language to elicit unsafe or harmful outputs, creating a new natural...
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