2,077+ academic papers on AI security, attacks, and defenses
Showing 181–200 of 226 papers
Clear filtersMd. Mehedi Hasan, Ziaur Rahman, Rafid Mostafiz +1 more
This paper presents a real-time modular defense system named Sentra-Guard. The system detects and mitigates jailbreak and prompt injection attacks...
Adetayo Adebimpe, Helmut Neukirchen, Thomas Welsh
Honeypots are decoy systems used for gathering valuable threat intelligence or diverting attackers away from production systems. Maximising attacker...
Li An, Yujian Liu, Yepeng Liu +3 more
Watermarking has emerged as a promising solution for tracing and authenticating text generated by large language models (LLMs). A common approach to...
Alyssa Gerhart, Balaji Iyangar
Adversarial attacks pose a severe risk to AI systems used in healthcare, capable of misleading models into dangerous misclassifications that can...
Xin Lian, Kenneth D. Forbus
Despite the broad applicability of large language models (LLMs), their reliance on probabilistic inference makes them vulnerable to errors such as...
Zhonghao Zhan, Amir Al Sadi, Krinos Li +1 more
In this work, we study security of Model Context Protocol (MCP) agent toolchains and their applications in smart homes. We introduce AegisMCP, a...
Thomas Wang, Haowen Li
As large language models (LLMs) are increasingly integrated into real-world applications, ensuring their safety, robustness, and privacy compliance...
Sidhant Narula, Javad Rafiei Asl, Mohammad Ghasemigol +2 more
Large Language Models (LLMs) remain vulnerable to multi-turn jailbreak attacks. We introduce HarmNet, a modular framework comprising ThoughtNet, a...
Zijie Xu, Minfeng Qi, Shiqing Wu +4 more
Multi-agent systems powered by large language models are advancing rapidly, yet the tension between mutual trust and security remains underexplored....
Qilin Liao, Anamika Lochab, Ruqi Zhang
Vision-Language Models (VLMs) extend large language models with visual reasoning, but their multimodal design also introduces new, underexplored...
Rishi Jha, Harold Triedman, Justin Wagle +1 more
Control-flow hijacking attacks manipulate orchestration mechanisms in multi-agent systems into performing unsafe actions that compromise the system...
Yue Liu, Zhenchang Xing, Shidong Pan +1 more
In recent years, the AI wave has grown rapidly in software development. Even novice developers can now design and generate complex...
Xiaofan Li, Xing Gao
The Model Context Protocol (MCP) is an emerging open standard that enables AI-powered applications to interact with external tools through structured...
Kate Glazko, Jennifer Mankoff
Generative AI risks such as bias and lack of representation impact people who do not interact directly with GAI systems, but whose content does:...
Shiwen Ou, Yuwei Li, Lu Yu +6 more
Deep learning (DL) frameworks serve as the backbone for a wide range of artificial intelligence applications. However, bugs within DL frameworks can...
ChenYu Wu, Yi Wang, Yang Liao
Large language models (LLMs) are increasingly vulnerable to multi-turn jailbreak attacks, where adversaries iteratively elicit harmful behaviors that...
Zixuan Liu, Yi Zhao, Zhuotao Liu +4 more
Machine Learning (ML)-based malicious traffic detection is a promising security paradigm. It outperforms rule-based traditional detection by...
Edoardo Allegrini, Ananth Shreekumar, Z. Berkay Celik
Agentic AI systems, which leverage multiple autonomous agents and Large Language Models (LLMs), are increasingly used to address complex, multi-step...
Yisen Wang, Yichuan Mo, Hongjun Wang +2 more
Despite the rapid progress of neural networks, they remain highly vulnerable to adversarial examples, for which adversarial training (AT) is...
Karthik Avinash, Nikhil Pareek, Rishav Hada
The increasing deployment of Large Language Models (LLMs) across enterprise and mission-critical domains has underscored the urgent need for robust...
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