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 161–180 of 562 papers
Clear filtersBoyang Li, Bingyu Shen, Weihao Hong +6 more
Quantized large language models are increasingly deployed on edge devices for their low latency and energy efficiency. However, model quantization...
Shuze Liu, Kaixiang Zhao, Runyang Xu +4 more
Large language models (LLMs) deployed through text-only APIs face model extraction risks, as adversaries can collect their responses to train...
Ayan Javeed Shaikh, Arunesh Sinha, Nathaniel D. Bastian +1 more
Autonomous red team agents increasingly stress-test AI-enabled cyber defenses by planning strategy and executing multistage attacks. Reinforcement...
Zhen Liang, Hai Huang, Wentao Chen
Large language models have achieved remarkable capabilities across diverse domains, yet their safety alignment remains vulnerable to jailbreak...
Eunmin Lee, Jungwoo Kim, Jong-Seok Lee
Vision-language models (VLMs) are increasingly used for AI-generated image (AIGI) detection, providing natural-language explanations for authenticity...
Zezhong Wang, Xueyang Tang, Rui Lian +2 more
As Large Language Model (LLM) agents are increasingly deployed in complex environments, multi-turn interaction attacks have become a significant...
Yuelin Han
Agent interaction protocols such as ACP and A2A have moved LLM-based agents toward multi-agent collaboration, introducing new security threats. A...
Wenyu Chen, Li Wang, Chuanchao Zang +5 more
Video Multimodal Large Language Models (Video-MLLMs) support reasoning over video inputs, yet remain vulnerable to jailbreak attacks that elicit...
Alexandra Souly, Kai Fronsdal, Abby D'Cruz +2 more
This technical report presents an alignment evaluation developed and performed by the UK AI Security Institute for assessing whether advanced AI...
Yelyzaveta, Husieva, Lauren Alvarez
Large language models (LLMs) remain vulnerable to adversarial attacks that circumvent safety alignment to elicit harmful outputs. It remains unclear...
Ying Song, Xiaowei Jia, Balaji Palanisamy
As Graph Neural Networks (GNNs) are widely deployed as Machine Learning-as-a-Service (MLaaS) APIs, model stealing attacks have emerged as a critical...
Rui Wen, Jiayang Liu, Zeyu Yang +2 more
When a prompt injection attack succeeds, a Large Language Model (LLM) abandons its assigned system role to comply with an adversarial instruction....
Sabrina Kaniewski, Tim Krämer, Julius Bächle +3 more
Retrieval-Augmented Generation (RAG) is increasingly used to enhance Large Language Model (LLM)-based software vulnerability detection by grounding...
Longzhu He, Zelang Wen, Xinfeng Li +2 more
Driven by the rapid advancement of large language models (LLMs), LLM-based multi-agent systems (MAS) have emerged as a powerful paradigm for...
Jesson Wang, Shawn Li, Wei Yang +4 more
Manipulating next-token probabilities during generation can bypass the safety alignment of large language models. Existing approaches, however, rely...
Omar Sheta, Rinku Deuja, Hadi Masoudi +1 more
Safety-aligned language models are commonly deployed as multi-turn assistants, which lets adversaries spread unsafe intent across several user turns...
Zonghao Ying, Xiangfan Wu, Bo Yang +5 more
Indirect prompt injection embeds malicious instructions within external content retrieved by LLM-based agents, altering target behavior without user...
Zonghua Gu, Zeyu Gao, Amin Saremi +1 more
Adversarial machine learning has focused mainly on integrity, but availability is an increasingly consequential complement. Latency attacks (also...
Michael Lee, Zhipeng Wei, Yue Dong +1 more
Agentic systems are now being widely used to orchestrate tools and reason over long contexts. However, the improving capabilities of the large...
Sujin Chen, Lijun Li, Xuhong Wang +1 more
While LLM-based attackers exhibit growing proficiency in vulnerability exploitation, most existing cybersecurity benchmarks suffer from single-stage...
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