2,589+ academic papers on AI security, attacks, and defenses
Showing 1001–1020 of 1,930 papers
Clear filtersHerman Errico
As artificial intelligence systems evolve from passive assistants into autonomous agents capable of executing consequential actions, the security...
Pei-Chi Pan, Yingbin Liang, Sen Lin
Large Language Models (LLMs) demonstrate transformative potential, yet their reasoning remains inconsistent and unreliable. Reinforcement learning...
Chaeyun Kim, YongTaek Lim, Kihyun Kim +2 more
Existing red-teaming benchmarks, when adapted to new languages via direct translation, fail to capture socio-technical vulnerabilities rooted in...
Georgios Syros, Evan Rose, Brian Grinstead +4 more
Large language model (LLM) based web agents are increasingly deployed to automate complex online tasks by directly interacting with web sites and...
Kotekar Annapoorna Prabhu, Andrew Gan, Zahra Ghodsi
Machine learning relies on randomness as a fundamental component in various steps such as data sampling, data augmentation, weight initialization,...
Ashwin Sreevatsa, Sebastian Prasanna, Cody Rushing
The AI Control research agenda aims to develop control protocols: safety techniques that prevent untrusted AI systems from taking harmful actions...
Yuting Ning, Jaylen Jones, Zhehao Zhang +5 more
Computer-use agents (CUAs) have made tremendous progress in the past year, yet they still frequently produce misaligned actions that deviate from the...
Yu Yan, Sheng Sun, Shengjia Cheng +3 more
Vision-Language Models (VLMs) with multimodal reasoning capabilities are high-value attack targets, given their potential for handling complex...
Suraj Ranganath, Atharv Ramesh
AI-text detectors face a critical robustness challenge: adversarial paraphrasing attacks that preserve semantics while evading detection. We...
Suraj Ranganath, Atharv Ramesh
AI-text detectors face a critical robustness challenge: adversarial paraphrasing attacks that preserve semantics while evading detection. We...
Oliver Daniels, Perusha Moodley, Benjamin M. Marlin +1 more
Alignment audits aim to robustly identify hidden goals from strategic, situationally aware misaligned models. Despite this threat model, existing...
Yu Fu, Haz Sameen Shahgir, Huanli Gong +3 more
Large language models (LLMs) increasingly combine long-context processing with advanced reasoning, enabling them to retrieve and synthesize...
Jona te Lintelo, Lichao Wu, Stjepan Picek
The rapid adoption of Mixture-of-Experts (MoE) architectures marks a major shift in the deployment of Large Language Models (LLMs). MoE LLMs improve...
Shae McFadden, Myles Foley, Elizabeth Bates +5 more
Deep Reinforcement Learning (DRL) has achieved remarkable success in domains requiring sequential decision-making, motivating its application to...
Yanzhang Fu, Zizheng Guo, Jizhou Luo
Score-based query attacks pose a serious threat to deep learning models by crafting adversarial examples (AEs) using only black-box access to model...
Scott Thornton
Hybrid Retrieval-Augmented Generation (RAG) pipelines combine vector similarity search with knowledge graph expansion for multi-hop reasoning. We...
Yukun Jiang, Hai Huang, Mingjie Li +3 more
By introducing routers to selectively activate experts in Transformer layers, the mixture-of-experts (MoE) architecture significantly reduces...
Ahmed Salem, Andrew Paverd, Sahar Abdelnabi
Large language models (LLMs) are commonly treated as stateless: once an interaction ends, no information is assumed to persist unless it is...
Igor Santos-Grueiro
Safety evaluation for advanced AI systems assumes that behavior observed under evaluation predicts behavior in deployment. This assumption weakens...
Pouria Arefijamal, Mahdi Ahmadlou, Bardia Safaei +1 more
Federated learning (FL) is a decentralized learning paradigm widely adopted in resource-constrained Internet of Things (IoT) environments. These...
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