2,077+ academic papers on AI security, attacks, and defenses
Showing 61–79 of 79 papers
Clear filtersKaiwen Zhou, Ahmed Elgohary, A S M Iftekhar +1 more
The ability of LLM agents to plan and invoke tools exposes them to new safety risks, making a comprehensive red-teaming system crucial for...
Euodia Dodd, Nataša Krčo, Igor Shilov +1 more
Membership inference attacks (MIAs) have emerged as the standard tool for evaluating the privacy risks of AI models. However, state-of-the-art...
Osama Al Haddad, Muhammad Ikram, Ejaz Ahmed +1 more
Security analysts face increasing pressure to triage large and complex vulnerability backlogs. Large Language Models (LLMs) offer a potential aid by...
Pranshav Gajjar, Molham Khoja, Abiodun Ganiyu +4 more
The impending adoption of Open Radio Access Network (O-RAN) is fueling innovation in the RAN towards data-driven operation. Unlike traditional RAN...
Chengquan Guo, Yuzhou Nie, Chulin Xie +3 more
As large language models (LLMs) are increasingly used for code generation, concerns over the security risks have grown substantially. Early research...
Bin Liu, Yanjie Zhao, Guoai Xu +1 more
Large language model (LLM) agents have demonstrated remarkable capabilities in software engineering and cybersecurity tasks, including code...
Trilok Padhi, Pinxian Lu, Abdulkadir Erol +5 more
Large Language Model (LLM) agents are powering a growing share of interactive web applications, yet remain vulnerable to misuse and harm. Prior...
Ivan Dubrovsky, Anastasia Orlova, Illarion Iov +3 more
Benchmarking outcomes increasingly govern trust, selection, and deployment of LLMs, yet these evaluations remain vulnerable to semantically...
Dongsen Zhang, Zekun Li, Xu Luo +3 more
The Model Context Protocol (MCP) standardizes how large language model (LLM) agents discover, describe, and call external tools. While MCP unlocks...
Haoran Ou, Kangjie Chen, Xingshuo Han +4 more
Large Language Models (LLMs) have been augmented with web search to overcome the limitations of the static knowledge boundary by accessing up-to-date...
Rishika Bhagwatkar, Kevin Kasa, Abhay Puri +5 more
AI agents are vulnerable to indirect prompt injection attacks, where malicious instructions embedded in external content or tool outputs cause...
Rishika Bhagwatkar, Kevin Kasa, Abhay Puri +5 more
AI agents are vulnerable to indirect prompt injection attacks, where malicious instructions embedded in external content or tool outputs cause...
Chengquan Guo, Chulin Xie, Yu Yang +6 more
Code agents have gained widespread adoption due to their strong code generation capabilities and integration with code interpreters, enabling dynamic...
Yinuo Liu, Ruohan Xu, Xilong Wang +2 more
Multiple prompt injection attacks have been proposed against web agents. At the same time, various methods have been developed to detect general...
Haoran Xi, Minghao Shao, Brendan Dolan-Gavitt +2 more
Large language models show promise for vulnerability discovery, yet prevailing methods inspect code in isolation, struggle with long contexts, and...
Simin Chen, Yixin He, Suman Jana +1 more
LLM-based agents are increasingly deployed for software maintenance tasks such as automated program repair (APR). APR agents automatically fetch...
Alireza Lotfi, Charalampos Katsis, Elisa Bertino
Software vulnerabilities remain a critical security challenge, providing entry points for attackers into enterprise networks. Despite advances in...
Jianshuo Dong, Sheng Guo, Hao Wang +6 more
Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information. However, this also introduces a new...
Wenkai Guo, Xuefeng Liu, Haolin Wang +3 more
Fine-tuning large language models (LLMs) with local data is a widely adopted approach for organizations seeking to adapt LLMs to their specific...
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