2,077+ academic papers on AI security, attacks, and defenses
Showing 81–100 of 224 papers
Clear filtersLige Huang, Zicheng Liu, Jie Zhang +3 more
The dual offensive and defensive utility of Large Language Models (LLMs) highlights a critical gap in AI security: the lack of unified frameworks for...
Nirhoshan Sivaroopan, Kanchana Thilakarathna, Albert Zomaya +6 more
Sponge attacks increasingly threaten LLM systems by inducing excessive computation and DoS. Existing defenses either rely on statistical filters that...
Satyapriya Krishna, Matteo Memelli, Tong Wang +5 more
Amazon published its Frontier Model Safety Framework (FMSF) as part of the Paris AI summit, following which we presented a report on Amazon's Premier...
Dongrui Liu, Qihan Ren, Chen Qian +40 more
The rise of AI agents introduces complex safety and security challenges arising from autonomous tool use and environmental interactions. Current...
Qi Li, Xinchao Wang
Enabling large language models (LLMs) to solve complex reasoning tasks is a key step toward artificial general intelligence. Recent work augments...
Narek Maloyan, Dmitry Namiot
The Model Context Protocol (MCP) has emerged as a de facto standard for integrating Large Language Models with external tools, yet no formal security...
Inderjeet Singh, Eleonore Vissol-Gaudin, Andikan Otung +1 more
Fine-tuning Large Language Models (LLMs) for specialized domains is constrained by a fundamental challenge: the need for diverse,...
Wenbo Guo, Shiwen Song, Jiaxun Guo +5 more
Open-source ecosystems such as NPM and PyPI are increasingly targeted by supply chain attacks, yet existing detection methods either depend on...
Jiazhu Xie, Bowen Li, Heyu Fu +3 more
Large Language Model (LLM)-based question-answering systems offer significant potential for automating customer support and internal knowledge access...
Yijin Zhou, Xiaoya Lu, Dongrui Liu +2 more
The rapid advancement of Large Language Model (LLM)-based Multi-Agent Systems (MAS) has introduced significant security vulnerabilities, where...
Adeyemi Adeseye, Aisvarya Adeseye
Loop vulnerabilities are one major risky construct in software development. They can easily lead to infinite loops or executions, exhaust resources,...
Daisuke Miyamoto, Takuji Iimura, Narushige Michishita
With the spread of generative AI in recent years, attacks known as Whaling have become a serious threat. Whaling is a form of social engineering that...
Hossein Naderi, Alireza Shojaei, Lifu Huang +3 more
Robots are expected to play a major role in the future construction industry but face challenges due to high costs and difficulty adapting to dynamic...
HyeYoung Lee
This paper proposes a multi-agent artificial intelligence system that generates response-oriented media content in real time based on audio-derived...
Roy Betser, Shamik Bose, Amit Giloni +3 more
AI agents are autonomous systems that combine LLMs with external tools to solve complex tasks. While such tools extend capability, improper tool...
Zimo Ji, Daoyuan Wu, Wenyuan Jiang +5 more
Large Language Model (LLM)-based agent systems are increasingly deployed for complex real-world tasks but remain vulnerable to natural language-based...
Kaiyu Zhou, Yongsen Zheng, Yicheng He +5 more
The agent--tool interaction loop is a critical attack surface for modern Large Language Model (LLM) agents. Existing denial-of-service (DoS) attacks...
Xinrui Zhang, Pincan Zhao, Jason Jaskolka +2 more
Machine Learning (ML) has emerged as a pivotal technology in the operation of large and complex systems, driving advancements in fields such as...
Federico Pierucci, Marcello Galisai, Marcantonio Syrnikov Bracale +6 more
As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a...
Yutao Mou, Zhangchi Xue, Lijun Li +4 more
While LLM-based agents can interact with environments via invoking external tools, their expanded capabilities also amplify security risks....
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