Most adversarial threats in artificial intelligence (AI) target the computational behavior of models rather than the humans who rely on them. Yet modern AI systems increasingly operate within human decision loops, where users interpret and act on model recommendations. Large Language Models (LLMs) generate fluent natural-language explanations that shape how users perceive and trust AI outputs, revealing a new attack surface at the cognitive layer: the communication channel between AI and its users. We introduce adversarial explanation attacks (AEAs), where an attacker manipulates the framing of LLM-generated explanations to modulate human trust in incorrect outputs. We formalize this behavioral threat through the trust miscalibration gap, a metric that captures the difference in human trust between benign and adversarial explanations. Using this metric as a lens, we highlight a behavioral risk where persuasive explanation framing can preserve user trust even when the underlying AI prediction is wrong. To characterize this threat, we conducted a human study with over 200 participants, systematically varying four dimensions of explanation framing: reasoning mode, evidence type, communication style, and presentation format. Our findings show that users report nearly identical trust for adversarial and benign explanations, with adversarial explanations preserving the vast majority of benign trust despite being incorrect. The most vulnerable cases arise when AEAs closely resemble expert communication, combining authoritative evidence, neutral tone, and domain-appropriate reasoning. Vulnerability is highest on hard tasks, in fact-driven domains, and among participants who are less formally educated, younger, or highly trusting of AI.
LLMs can persuade only psychologically susceptible humans on societal issues, via trust in AI and emotional appeals, amid logical fallacies
organization= CogNosco Lab, Department of Psychology；Cognitive Science, University of Trento , city= Rovereto , country= Italy；organization= Institute of Information Science；Technologies ``Alessandro Faedo", National Research Council , country= Italy；organization= Thomas Lord Department of Computer Science, University of Southern California , city= Los Angeles , state= California , country= USA；organization= Department of Sociology；Social Research, University of Trento , city= Trento , country= Italy；organization= Centre for Behavioural；Implementation Sciences in Medicine (BISI), National University of Singapore , city= Singapore , country= Singapore
Large Language Models as 'Hidden Persuaders': Fake Product Reviews are Indistinguishable to Humans and Machines
N/LAB, Nottingham University Business School, University of Nottingham, UK（N/LAB，诺丁汉大学商学院，诺丁汉大学，英国）；Haydn Green Institute for Entrepreneurship and Innovation, University of Nottingham, UK（创业与创新研究院，诺丁汉大学，英国）；Strategic Innovation Ltd, UK（战略创新有限公司，英国）
CurateGPT: A flexible language-model assisted biocuration tool
Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）；Queen Mary University of London（伦敦玛丽女王大学）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；European Bioinformatics Institute (EMBL-EBI)（欧洲生物信息研究所（欧洲分子生物学实验室-欧洲生物信息研究所））；Berlin Institute of Health - Charité, Universitätsmedizin（柏林健康研究所-夏里特医科大学）
An Experimental Comparison of Cognitive Forcing Functions for Execution Plans in AI-Assisted Writing: Effects On Trust, Overreliance, and Perceived Critical Thinking
Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）；Microsoft Research（微软研究院）
Measuring Perceived Trust in XAI-Assisted Decision-Making by Eliciting a Mental Model
Eindhoven University of Technology（埃因霍温理工大学）；Eindhoven Artificial Intelligence Systems Institute（埃因霍温人工智能系统研究所）；Ca’ Foscari University of Venice（威尼斯大学）
Can agents whose sole duty is to keep humans alive be hijacked to kill? Delayed multi-turn derived-action trap attacks in simulated high-stakes environments
Exploring the Role of Explainability in AI-Assisted Embryo Selection
Barcelona Supercomputing Center（巴塞罗那超级计算中心）；Hospital Clínic de Barcelona（巴塞罗那诊所医院）；Universitat Politécnica de Catalunya - Barcelona TECH（加泰罗尼亚理工大学-巴塞罗那TECH）
Towards Blockchain-Assisted Privacy-Aware Data Sharing For Edge Intelligence: A Smart Healthcare Perspective
Data61, CSIRO（联邦科学与工业研究组织数据61研究所）；Victoria University（维多利亚大学）；University of Electronic Science and Technology of China（电子科技大学）；University of Technology Sydney（悉尼科技大学）；CNPIEC KEXIN LTD（中国图书进出口科信有限公司）；Xidian University（西安电子科技大学）
