2,077+ academic papers on AI security, attacks, and defenses
Showing 201–220 of 603 papers
Clear filtersYuxiang Wang, Hongyu Liu, Dekun Chen +2 more
As Speech Language Models (SLMs) transition from personal devices to shared, multi-user environments such as smart homes, a new challenge emerges:...
Chi Zhang, Wenxuan Ding, Jiale Liu +3 more
Vision-Language Models (VLMs) have shown strong multimodal reasoning capabilities on Visual-Question-Answering (VQA) benchmarks. However, their...
Zahra Hashemi, Zhiqiang Zhong, Jun Pang +1 more
The rapid evolution of large language models (LLMs) has fuelled enthusiasm about their role in advancing scientific discovery, with studies exploring...
Mohamed Amine Ferrag, Abderrahmane Lakas, Merouane Debbah
Autonomous unmanned aerial vehicle (UAV) systems are increasingly deployed in safety-critical, networked environments where they must operate...
Geunsik Lim
As climate-related hazards intensify, conventional early warning systems (EWS) disseminate alerts rapidly but often fail to trigger timely protective...
Krittin Pachtrachai, Petmongkon Pornpichitsuwan, Wachiravit Modecrua +1 more
Building reliable conversational AI assistants for customer-facing industries remains challenging due to noisy conversational data, fragmented...
Dezhang Kong, Zhuxi Wu, Shiqi Liu +8 more
LLM-based web agents have become increasingly popular for their utility in daily life and work. However, they exhibit critical vulnerabilities when...
Thomas Heverin
Prompt injection evaluations typically treat refusal as a stable, binary indicator of safety. This study challenges that paradigm by modeling refusal...
Xiaohui Hu, Wun Yu Chan, Yuejie Shi +5 more
Smart contract security is paramount, but identifying intricate business logic vulnerabilities remains a persistent challenge because existing...
Zelong Zheng, Jiayuan Zhou, Xing Hu +2 more
Software vulnerability management has become increasingly critical as modern systems scale in size and complexity. However, existing automated...
Alireza Salemi, Hamed Zamani
Personalization is crucial for aligning Large Language Model (LLM) outputs with individual user preferences and background knowledge....
Marton Szep, Jorge Marin Ruiz, Georgios Kaissis +4 more
Fine-tuning Large Language Models (LLMs) on sensitive datasets carries a substantial risk of unintended memorization and leakage of Personally...
Massimiliano Pronesti, Anya Belz, Yufang Hou
Recent work on reinforcement learning with verifiable rewards (RLVR) has shown that large language models (LLMs) can be substantially improved using...
Dongshen Peng, Yi Wang, Austin Schoeffler +2 more
Large language models (LLMs) show promise in clinical decision support yet risk acquiescing to patient pressure for inappropriate care. We introduce...
Khoa Nguyen, Khiem Ton, NhatHai Phan +6 more
Although boosting software development performance, large language model (LLM)-powered code generation introduces intellectual property and data...
Andres Karjus, Kais Allkivi, Silvia Maine +3 more
Large language models (LLMs) enable rapid and consistent automated evaluation of open-ended exam responses, including dimensions of content and...
Akriti Vij, Benjamin Chua, Darshini Ramiah +43 more
As frontier AI models are deployed globally, it is essential that their behaviour remains safe and reliable across diverse linguistic and cultural...
Kristen Moore, Diksha Goel, Cody James Christopher +5 more
Realistic network traffic simulation is critical for evaluating intrusion detection systems, stress-testing network protocols, and constructing...
Anmol Goel, Cornelius Emde, Sangdoo Yun +2 more
We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle...
Xiaonan Jing, Gongqing Wu, Xingrui Zhuo +2 more
Open-domain Relational Triplet Extraction (ORTE) is the foundation for mining structured knowledge without predefined schemas. Despite the impressive...
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