2,529+ academic papers on AI security, attacks, and defenses
Showing 261–280 of 345 papers
Clear filtersJoonHo Lee, HyeonMin Cho, Jaewoong Yun +3 more
We present SGuard-v1, a lightweight safety guardrail for Large Language Models (LLMs), which comprises two specialized models to detect harmful...
Jie Chen, Liangmin Wang
Fuzzing is a widely used technique for detecting vulnerabilities in smart contracts, which generates transaction sequences to explore the execution...
Thong Bach, Dung Nguyen, Thao Minh Le +1 more
Large language models exhibit systematic vulnerabilities to adversarial attacks despite extensive safety alignment. We provide a mechanistic analysis...
Ruoxi Cheng, Haoxuan Ma, Teng Ma +1 more
Large Vision-Language Models (LVLMs) exhibit powerful reasoning capabilities but suffer sophisticated jailbreak vulnerabilities. Fundamentally,...
Biagio Boi, Christian Esposito
Smart contracts have emerged as key components within decentralized environments, enabling the automation of transactions through self-executing...
Jialin Wu, Kecen Li, Zhicong Huang +3 more
Many machine learning models are fine-tuned from large language models (LLMs) to achieve high performance in specialized domains like code...
Daniyal Ganiuly, Nurzhau Bolatbek
The increasing virtualization of fifth generation (5G) networks expands the attack surface of the user plane, making spoofing a persistent threat to...
Huzaifa Arif, Keerthiram Murugesan, Ching-Yun Ko +3 more
We propose patching for large language models (LLMs) like software versions, a lightweight and modular approach for addressing safety...
Binayak Kara, Ujjwal Sahua, Ciza Thomas +1 more
Securing Dew-Enabled Edge-of-Things (EoT) networks against sophisticated intrusions is a critical challenge. This paper presents HybridGuard, a...
Tyler Slater
Context: The integration of Large Language Models (LLMs) into core software systems is accelerating. However, existing software architecture patterns...
Haonan Shi, Guoli Wang, Tu Ouyang +1 more
Small language models (SLMs) are increasingly deployed on edge devices, making their safety alignment crucial yet challenging. Current shallow...
Dev Patel, Gabrielle Gervacio, Diekola Raimi +5 more
Large Language Models require substantial computational resources for inference, posing deployment challenges. While dynamic pruning offers superior...
Oshando Johnson, Alexandra Fomina, Ranjith Krishnamurthy +3 more
The prevalence of security vulnerabilities has prompted companies to adopt static application security testing (SAST) tools for vulnerability...
Hao Zhu, Jia Li, Cuiyun Gao +7 more
Large language models (LLMs) have achieved remarkable progress in code understanding tasks. However, they demonstrate limited performance in...
Mohammad Atif Quamar, Mohammad Areeb, Mikhail Kuznetsov +2 more
Aligning large language models (LLMs) with human values is crucial for safe deployment. Inference-time techniques offer granular control over...
Bryce-Allen Bagley, Navin Khoshnan
The complexity of human cognition has meant that psychology makes more use of theory and conceptual models than perhaps any other biomedical field....
Xiumei Deng, Zehui Xiong, Binbin Chen +3 more
Large language models (LLMs) are proliferating rapidly at the edge, delivering intelligent capabilities across diverse application scenarios....
Ahmad Tahmasivand, Noureldin Zahran, Saba Al-Sayouri +2 more
This paper presents LM-Fix, a lightweight detection and rapid recovery framework for faults in large language models (LLMs). Existing integrity...
Ayşe Selin Okatan, Mustafa İlhan Akbaş, Laxima Niure Kandel +1 more
We analyze subliminal transfer in Transformer models, where a teacher embeds hidden traits that can be linearly decoded by a student without...
Yifan Xia, Guorui Chen, Wenqian Yu +3 more
Large language models (LLMs) excel in diverse applications but face dual challenges: generating harmful content under jailbreak attacks and...
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