Copertina

Emergent misalignment as prompt sensitivity: A research note

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wyse, Tim, Stone, Twm, Soligo, Anna, Tan, Daniel
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security Artificial Intelligence Computation and Language Human-Computer Interaction
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

An LLM's Apology: Outsourcing Awkwardness in the Age of AI
di: Stone, Twm, et al.
Pubblicazione: (2025)

Hacc-Man: An Arcade Game for Jailbreaking LLMs
di: Valentim, Matheus, et al.
Pubblicazione: (2024)

Beyond Words: On Large Language Models Actionability in Mission-Critical Risk Analysis
di: Esposito, Matteo, et al.
Pubblicazione: (2024)

Learned, Lagged, LLM-splained: LLM Responses to End User Security Questions
di: Prakash, Vijay, et al.
Pubblicazione: (2024)

RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models
di: Wang, Jiongxiao, et al.
Pubblicazione: (2023)

NLP Privacy Risk Identification in Social Media (NLP-PRISM): A Survey
di: Goswami, Dhiman, et al.
Pubblicazione: (2026)

On the Suitability of LLM-Driven Agents for Dark Pattern Audits
di: Sun, Chen, et al.
Pubblicazione: (2026)

LLM Novice Uplift on Dual-Use, In Silico Biology Tasks
di: Zhang, Chen Bo Calvin, et al.
Pubblicazione: (2026)

Assessing LLM Response Quality in the Context of Technology-Facilitated Abuse
di: Prakash, Vijay, et al.
Pubblicazione: (2026)

A Security Risk Taxonomy for Prompt-Based Interaction With Large Language Models
di: Derner, Erik, et al.
Pubblicazione: (2023)

Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
di: Betley, Jan, et al.
Pubblicazione: (2025)

Can LLM-Generated Misinformation Be Detected?
di: Chen, Canyu, et al.
Pubblicazione: (2023)

MeAJOR Corpus: A Multi-Source Dataset for Phishing Email Detection
di: Mendes, Paulo, et al.
Pubblicazione: (2025)

BounTCHA: A CAPTCHA Utilizing Boundary Identification in Guided Generative AI-extended Videos
di: Lin, Lehao, et al.
Pubblicazione: (2025)

InjectLab: A Tactical Framework for Adversarial Threat Modeling Against Large Language Models
di: Howard, Austin
Pubblicazione: (2025)

Cyri: A Conversational AI-based Assistant for Supporting the Human User in Detecting and Responding to Phishing Attacks
di: La Torre, Antonio, et al.
Pubblicazione: (2025)

Privacy Leakage Overshadowed by Views of AI: A Study on Human Oversight of Privacy in Language Model Agent
di: Zhang, Zhiping, et al.
Pubblicazione: (2024)

PrivateXR: Defending Privacy Attacks in Extended Reality Through Explainable AI-Guided Differential Privacy
di: Kundu, Ripan Kumar, et al.
Pubblicazione: (2025)

Adversarial VR: An Open-Source Testbed for Evaluating Adversarial Robustness of VR Cybersickness Detection and Mitigation
di: Ahmed, Istiak, et al.
Pubblicazione: (2025)

"Impressively Scary:" Exploring User Perceptions and Reactions to Unraveling Machine Learning Models in Social Media Applications
di: West, Jack, et al.
Pubblicazione: (2025)

Autonomy Reshapes How Personalization Affects Privacy Concerns and Trust in LLM Agents
di: Zhang, Zhiping, et al.
Pubblicazione: (2025)

JEEVHITAA -- An End-to-End HCAI System to Support Collective Care
di: Srinivasan, Shyama Sastha Krishnamoorthy, et al.
Pubblicazione: (2025)

Human-AI Collaboration in Cloud Security: Cognitive Hierarchy-Driven Deep Reinforcement Learning
di: Aref, Zahra, et al.
Pubblicazione: (2025)

Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework
di: Dassanayake, Rishane, et al.
Pubblicazione: (2025)

From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents
di: Wu, Liangxuan, et al.
Pubblicazione: (2025)

Agentic AI and the Industrialization of Cyber Offense: Forecast, Consequences, and Defensive Priorities for Enterprises and the Mittelstand
di: Koch, Christopher
Pubblicazione: (2026)

Decision-Aware Trust Signal Alignment for SOC Alert Triage
di: Chowdhury, Israt Jahan, et al.
Pubblicazione: (2026)

Current state of LLM Risks and AI Guardrails
di: Ayyamperumal, Suriya Ganesh, et al.
Pubblicazione: (2024)

Rescriber: Smaller-LLM-Powered User-Led Data Minimization for LLM-Based Chatbots
di: Zhou, Jijie, et al.
Pubblicazione: (2024)

Empowering Users in Digital Privacy Management through Interactive LLM-Based Agents
di: Sun, Bolun, et al.
Pubblicazione: (2024)

"It's a Fair Game", or Is It? Examining How Users Navigate Disclosure Risks and Benefits When Using LLM-Based Conversational Agents
di: Zhang, Zhiping, et al.
Pubblicazione: (2023)

Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues
di: Chang, Zhiyuan, et al.
Pubblicazione: (2024)

Towards Secure AI-driven Industrial Metaverse with NFT Digital Twins
di: Prakash, Ravi, et al.
Pubblicazione: (2024)

Human-Centered Privacy Research in the Age of Large Language Models
di: Li, Tianshi, et al.
Pubblicazione: (2024)

AI-Assisted Adaptive Rendering for High-Frequency Security Telemetry in Web Interfaces
di: Rajhans, Mona
Pubblicazione: (2026)

SECURE: Benchmarking Large Language Models for Cybersecurity
di: Bhusal, Dipkamal, et al.
Pubblicazione: (2024)

Human-Centered Explainability in AI-Enhanced UI Security Interfaces: Designing Trustworthy Copilots for Cybersecurity Analysts
di: Rajhans, Mona
Pubblicazione: (2026)

Personalised Feedback Framework for Online Education Programmes Using Generative AI
di: Kuzminykh, Ievgeniia, et al.
Pubblicazione: (2024)

When Ads Become Profiles: Uncovering the Invisible Risk of Web Advertising at Scale with LLMs
di: Chen, Baiyu, et al.
Pubblicazione: (2025)

Jaco: An Offline Running Privacy-aware Voice Assistant
di: Bermuth, Daniel, et al.
Pubblicazione: (2022)