2,077+ academic papers on AI security, attacks, and defenses
Showing 341–360 of 603 papers
Clear filtersAink Acrie Soe Thein, Nikolaos Pitropakis, Pavlos Papadopoulos +2 more
With the adoption of multiple digital devices in everyday life, the cyber-attack surface has increased. Adversaries are continuously exploring new...
Xinye Cao, Yihan Lin, Guoshun Nan +9 more
Zero-Touch Networks (ZTNs) represent a transformative paradigm toward fully automated and intelligent network management, providing the scalability...
Futa Waseda, Shojiro Yamabe, Daiki Shiono +2 more
Large vision-language models (LVLMs) are vulnerable to typographic attacks, where misleading text within an image overrides visual understanding....
Bethel Hall, Owen Ungaro, William Eiers
Access control policies are vital for securing modern cloud computing, where organizations must manage access to sensitive data across thousands of...
Anantaa Kotal, Anupam Joshi
The widespread use of big data across sectors has raised major privacy concerns, especially when sensitive information is shared or analyzed....
Shuyue Hu, Haoyang Yan, Yiqun Zhang +3 more
Foundation models (FMs) are increasingly assuming the role of the ''brain'' of AI agents. While recent efforts have begun to equip FMs with native...
Manos Plitsis, Giorgos Bouritsas, Vassilis Katsouros +1 more
Text-to-image (TTI) diffusion models have achieved remarkable visual quality, yet they have been repeatedly shown to exhibit social biases across...
Gary Ackerman, Zachary Kallenborn, Anna Wetzel +7 more
The potential for rapidly-evolving frontier artificial intelligence (AI) models, especially large language models (LLMs), to facilitate bioterrorism...
Md Nazmul Haque, Elizabeth Lin, Lawrence Arkoh +2 more
Large Language Models for code (LLMs4Code) are increasingly used to generate software artifacts, including library and package recommendations in...
Lukas Johannes Möller
The escalating sophistication and variety of cyber threats have rendered static honeypots inadequate, necessitating adaptive, intelligence-driven...
Jordan Taylor, Sid Black, Dillon Bowen +10 more
Future AI systems could conceal their capabilities ('sandbagging') during evaluations, potentially misleading developers and auditors. We...
Sangha Park, Seungryong Yoo, Jisoo Mok +1 more
Although Multimodal Large Language Models (MLLMs) have advanced substantially, they remain vulnerable to object hallucination caused by language...
Alisha Ukani, Hamed Haddadi, Ali Shahin Shamsabadi +1 more
This paper presents a systematic evaluation of the privacy behaviors and attributes of eight recent, popular browser agents. Browser agents are...
JV Roig
We investigate how large language models (LLMs) fail when operating as autonomous agents with tool-use capabilities. Using the Kamiwaza Agentic Merit...
Qiwei Tian, Chenhao Lin, Zhengyu Zhao +1 more
To address the trade-off between robustness and performance for robust VLM, we observe that function words could incur vulnerability of VLMs against...
Xiaojun Jia, Jie Liao, Qi Guo +11 more
Recent advances in multi-modal large language models (MLLMs) have enabled unified perception-reasoning capabilities, yet these systems remain highly...
Cheng Cheng, Jinqiu Yang
Code-focused Large Language Models (LLMs), such as CodeX and Star-Coder, have demonstrated remarkable capabilities in enhancing developer...
Caleb Gross
Security research is fundamentally a problem of resource constraint and consequent prioritization. There is simply too much attack surface and too...
Xiuyuan Chen, Jian Zhao, Yuxiang He +10 more
While the deployment of large language models (LLMs) in high-value industries continues to expand, the systematic assessment of their safety against...
Ashish Hooda, Mihai Christodorescu, Chuangang Ren +3 more
Machine learning (ML) models for code clone detection determine whether two pieces of code are semantically equivalent, which in turn is a key...
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