2,077+ academic papers on AI security, attacks, and defenses
Showing 261–280 of 715 papers
Clear filtersAdeyemi Adeseye, Aisvarya Adeseye
Loop vulnerabilities are one major risky construct in software development. They can easily lead to infinite loops or executions, exhaust resources,...
Mohammad Shamim Ahsan, Peng Liu
In the network security domain, due to practical issues -- including imbalanced data and heterogeneous legitimate network traffic -- adversarial...
Zhihao Dou, Dongfei Cui, Weida Wang +7 more
Split Learning (SL) offers a framework for collaborative model training that respects data privacy by allowing participants to share the same dataset...
Jiani Liu, Yixin He, Lanlan Fan +5 more
Navigation agents powered by large language models (LLMs) convert natural language instructions into executable plans and actions. Compared to...
Fan Huang, Haewoon Kwak, Jisun An
Large Language Models (LLMs) are increasingly employed in various question-answering tasks. However, recent studies showcase that LLMs are...
Jiayi Yuan, Jonathan Nöther, Natasha Jaques +1 more
While recent automated red-teaming methods show promise for systematically exposing model vulnerabilities, most existing approaches rely on...
Bingxin Xu, Yuzhang Shang, Binghui Wang +1 more
Vision-Language-Action (VLA) models are increasingly deployed in safety-critical robotic applications, yet their security vulnerabilities remain...
Asen Dotsinski, Panagiotis Eustratiadis
As open-weight large language models (LLMs) increase in capabilities, safeguarding them against malicious prompts and understanding possible attack...
Yow-Fu Liou, Yu-Chien Tang, Yu-Hsiang Liu +1 more
Benchmarking large language models (LLMs) is critical for understanding their capabilities, limitations, and robustness. In addition to interface...
Diego Gosmar, Deborah A. Dahl
Prompt injection remains a central obstacle to the safe deployment of large language models, particularly in multi-agent settings where intermediate...
Xiaolei Zhang, Xiaojun Jia, Liquan Chen +1 more
Introducing reasoning models into Retrieval-Augmented Generation (RAG) systems enhances task performance through step-by-step reasoning, logical...
Jesus-German Ortiz-Barajas, Jonathan Tonglet, Vivek Gupta +1 more
Multimodal large language models (MLLMs) are increasingly used to automate chart generation from data tables, enabling efficient data analysis and...
Nay Myat Min, Long H. Pham, Hongyu Zhang +1 more
Single-pass hallucination detectors rely on internal telemetry (e.g., uncertainty, hidden-state geometry, and attention) of large language models,...
Chutian Huang, Dake Cao, Jiacheng Ji +3 more
Background: While Large Language Models (LLMs) have achieved widespread adoption, malicious prompt engineering specifically "jailbreak attacks" poses...
Zhixin Xie, Xurui Song, Jun Luo
The demand of customized large language models (LLMs) has led to commercial LLMs offering black-box fine-tuning APIs, yet this convenience introduces...
Anirudh Sekar, Mrinal Agarwal, Rachel Sharma +4 more
Prompt injection attacks have become an increasing vulnerability for LLM applications, where adversarial prompts exploit indirect input channels such...
Aiman Al Masoud, Marco Arazzi, Antonino Nocera
Retrieval-Augmented Generation (RAG) has attracted significant attention due to its ability to combine the generative capabilities of Large Language...
Yipu Dou, Wang Yang
Large language model (LLM) safety evaluation is moving from content moderation to action security as modern systems gain persistent state, tool...
Haoze Guo, Ziqi Wei
Retrieval-augmented generation (RAG) systems put more and more emphasis on grounding their responses in user-generated content found on the Web,...
Chetan Pathade, Vinod Dhimam, Sheheryar Ahmad +1 more
Serverless computing has achieved widespread adoption, with over 70% of AWS organizations using serverless solutions [1]. Meanwhile, machine learning...
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