2,529+ academic papers on AI security, attacks, and defenses
Showing 101–120 of 312 papers
Clear filtersYuval Felendler, Parth A. Gandhi, Idan Habler +2 more
Model Context Protocols (MCPs) provide a unified platform for agent systems to discover, select, and orchestrate tools across heterogeneous execution...
Varun Pratap Bhardwaj
We present SuperLocalMemory, a local-first memory system for multi-agent AI that defends against OWASP ASI06 memory poisoning through architectural...
Chengzhi Hu, Jonas Dornbusch, David Lüdke +2 more
Adversarial training for LLMs is one of the most promising methods to reliably improve robustness against adversaries. However, despite significant...
Yohan Lee, Jisoo Jang, Seoyeon Choi +2 more
Tool-using LLM agents increasingly coordinate real workloads by selecting and chaining third-party tools based on text-visible metadata such as tool...
Zhenhong Zhou, Yuanhe Zhang, Hongwei Cai +6 more
The Model Context Protocol (MCP) standardizes tool use for LLM-based agents and enable third-party servers. This openness introduces a security...
Mario Marín Caballero, Miguel Betancourt Alonso, Daniel Díaz-López +3 more
The most valuable asset of any cloud-based organization is data, which is increasingly exposed to sophisticated cyberattacks. Until recently, the...
Akshat Naik, Jay Culligan, Yarin Gal +4 more
As Large Language Model (LLM) agents become more capable, their coordinated use in the form of multi-agent systems is anticipated to emerge as a...
Yiran Gao, Kim Hammar, Tao Li
Rapidly evolving cyberattacks demand incident response systems that can autonomously learn and adapt to changing threats. Prior work has extensively...
Oguzhan Baser, Elahe Sadeghi, Eric Wang +5 more
Most large language models (LLMs) run on external clouds: users send a prompt, pay for inference, and must trust that the remote GPU executes the LLM...
Abhishek Saini, Haolin Jiang, Hang Liu
The deployment of large language models (LLMs) on third-party devices requires new ways to protect model intellectual property. While Trusted...
Zhenyu Xu, Victor S. Sheng
Protecting the intellectual property of large language models (LLMs) is a critical challenge due to the proliferation of unauthorized derivative...
Benjamin Livshits
We argue that when it comes to producing secure code with AI, the prevailing "fighting fire with fire" approach -- using probabilistic AI-based...
Zhiyu Sun, Minrui Luo, Yu Wang +2 more
Large language models (LLMs) are pretrained on corpora containing trillions of tokens and, therefore, inevitably memorize sensitive information....
Ruoyao Wen, Hao Li, Chaowei Xiao +1 more
Indirect prompt injection threatens LLM agents by embedding malicious instructions in external content, enabling unauthorized actions and data theft....
Fengpeng Li, Kemou Li, Qizhou Wang +2 more
Concept erasure helps stop diffusion models (DMs) from generating harmful content; but current methods face robustness retention trade off....
Tao Huang, Rui Wang, Xiaofei Liu +3 more
%Large vision-language models (LVLMs) have shown substantial advances in multimodal understanding and generation. However, when presented with...
Vishruti Kakkad, Paul Chung, Hanan Hibshi +1 more
An exponential growth of Machine Learning and its Generative AI applications brings with it significant security challenges, often referred to as...
Yike Sun, Haotong Yang, Zhouchen Lin +1 more
Tokenization is fundamental to how language models represent and process text, yet the behavior of widely used BPE tokenizers has received far less...
Ariel Fogel, Omer Hofman, Eilon Cohen +1 more
Open-weight language models are increasingly used in production settings, raising new security challenges. One prominent threat in this context is...
Leo Schwinn, Moritz Ladenburger, Tim Beyer +3 more
Automated \enquote{LLM-as-a-Judge} frameworks have become the de facto standard for scalable evaluation across natural language processing. For...
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