2,529+ academic papers on AI security, attacks, and defenses
Showing 701–720 of 729 papers
Clear filtersYao Tong, Haonan Wang, Siquan Li +2 more
Fingerprinting Large Language Models (LLMs) is essential for provenance verification and model attribution. Existing methods typically extract...
Joel Dyer, Daniel Jarne Ornia, Nicholas Bishop +2 more
Evaluating the safety of frontier AI systems is an increasingly important concern, helping to measure the capabilities of such models and identify...
Yixu Wang, Xin Wang, Yang Yao +4 more
The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However,...
Simin Chen, Yixin He, Suman Jana +1 more
LLM-based agents are increasingly deployed for software maintenance tasks such as automated program repair (APR). APR agents automatically fetch...
Ruolin Chen, Yinqian Sun, Jihang Wang +3 more
Embodied agents powered by large language models (LLMs) inherit advanced planning capabilities; however, their direct interaction with the physical...
Xiang Zhang, Kun Wei, Xu Yang +3 more
As Large Language Models (LLMs) become increasingly prevalent, their security vulnerabilities have already drawn attention. Machine unlearning is...
Jiacheng Shi, Hongfei Du, Y. Alicia Hong +1 more
Speech emotion recognition (SER) with audio-language models (ALMs) remains vulnerable to distribution shifts at test time, leading to performance...
Aryan Yazdan Parast, Parsa Hosseini, Hesam Asadollahzadeh +4 more
Object hallucination in Multimodal Large Language Models (MLLMs) is a persistent failure mode that causes the model to perceive objects absent in the...
Adrian Arnaiz-Rodriguez, Miguel Baidal, Erik Derner +5 more
Large language model-powered chatbots have transformed how people seek information, especially in high-stakes contexts like mental health. Despite...
Su Kara, Fazle Faisal, Suman Nath
Recent advances in browser-based LLM agents have shown promise for automating tasks ranging from simple form filling to hotel booking or online...
Yihan Wu, Ruibo Chen, Georgios Milis +1 more
As large language models become increasingly capable and widely deployed, verifying the provenance of machine-generated content is critical to...
Alireza Lotfi, Charalampos Katsis, Elisa Bertino
Software vulnerabilities remain a critical security challenge, providing entry points for attackers into enterprise networks. Despite advances in...
Meet Udeshi, Venkata Sai Charan Putrevu, Prashanth Krishnamurthy +4 more
Security of software supply chains is necessary to ensure that software updates do not contain maliciously injected code or introduce vulnerabilities...
Shuyi Lin, Tian Lu, Zikai Wang +3 more
OpenAI's GPT-OSS family provides open-weight language models with explicit chain-of-thought (CoT) reasoning and a Harmony prompt format. We summarize...
Nayeong Kim, Seong Joon Oh, Suha Kwak
Parameter-efficient fine-tuning (PEFT) of vision-language models (VLMs) excels in various vision tasks thanks to the rich knowledge and...
Jianshuo Dong, Sheng Guo, Hao Wang +6 more
Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information. However, this also introduces a new...
Sihan Hu, Xiansheng Cai, Yuan Huang +5 more
Training large language models with Reinforcement Learning with Verifiable Rewards (RLVR) exhibits a set of distinctive and puzzling behaviors that...
Sherif Saad, Kevin Shi, Mohammed Mamun +1 more
Automated machine learning (AutoML) has emerged as a promising paradigm for automating machine learning (ML) pipeline design, broadening AI adoption....
Xiaotian Zou
Multimodal Large Language Models (MLLMs) have transformed text-to-image workflows, allowing designers to create novel visual concepts with...
Antreas Ioannou, Andreas Shiamishis, Nora Hollenstein +1 more
In an era dominated by Large Language Models (LLMs), understanding their capabilities and limitations, especially in high-stakes fields like law, is...
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