Image de couverture de livre

Friend or Foe: How LLMs' Safety Mind Gets Fooled by Intent Shift Attack

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ding, Peng, Kuang, Jun, Sun, Wen, Wang, Zongyu, Cao, Xuezhi, Cai, Xunliang, Chen, Jiajun, Huang, Shujian
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement
par: Ding, Peng, et autres
Publié: (2025)

A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily
par: Ding, Peng, et autres
Publié: (2023)

Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs
par: Ding, Peng, et autres
Publié: (2024)

Friend or Foe
par: Cherendichenko, Oleksandr, et autres
Publié: (2025)

Alcohol: Friend or Foe?
par: Ricardo A. González
Publié: (2011)

LLMs in Cybersecurity: Friend or Foe in the Human Decision Loop?
par: Pekaric, Irdin, et autres
Publié: (2025)

SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models
par: Ding, Peng, et autres
Publié: (2025)

Chemifriction and Superlubricity: Friends or Foes?
par: Ying, Penghua, et autres
Publié: (2024)

Meeseeks: A Feedback-Driven, Iterative Self-Correction Benchmark evaluating LLMs' Instruction Following Capability
par: wang, Jiaming, et autres
Publié: (2025)

LARY: A Latent Action Representation Yielding Benchmark for Generalizable Vision-to-Action Alignment
par: Nie, Dujun, et autres
Publié: (2026)

Fooling SHAP with Output Shuffling Attacks
par: Yuan, Jun, et autres
Publié: (2024)

Friend or Foe Inside? Exploring In-Process Isolation to Maintain Memory Safety for Unsafe Rust
par: Gülmez, Merve, et autres
Publié: (2023)

Movable Antennas Meet Intelligent Reflecting Surface: Friends or Foes?
par: Wei, Xin, et autres
Publié: (2025)

Knowledge Graphs and Critical Infrastructures: Friends or Foes?
par: José Miguel Blanco, et autres
Publié: (2026)

AI Code Generators for Security: Friend or Foe?
par: Natella, Roberto, et autres
Publié: (2024)

Audio and Video Cassettes; Friend or Foe of the Librarian?
par: Poulos, Arthur
Publié: (1972)

Conflict in the Large Academic Library: Friend or Foe?
par: Pettas, William, et autres
Publié: (1992)

Tissue Resident Memory Cells: Friend or Foe?
par: Chidimma F. Chude, et autres
Publié: (2025)

Local ancestry in Apoe3: Friend or Foe?
par: Sofia Moura, et autres
Publié: (2024)

Defects of Metal Halide Perovskites in Photocatalytic Energy Conversion: Friend or Foe?
par: Chunhua Wang, et autres
Publié: (2024)

StyleFool: Fooling Video Classification Systems via Style Transfer
par: Cao, Yuxin, et autres
Publié: (2022)

Friend or Foe? Navigating and Re-configuring "Snipers' Alley"
par: Dwyer, Andrew C, et autres
Publié: (2025)

Friend or Foe? Harnessing Controllable Overfitting for Anomaly Detection
par: Qian, Long, et autres
Publié: (2024)

Friend or Foe: Delegating to an AI Whose Alignment is Unknown
par: Fudenberg, Drew, et autres
Publié: (2025)

Valganciclovir and Risk for Neutropenia: When the Friend Becomes the Foe
par: Nadya Nalli, et autres
Publié: (2024)

Fat‐Free Mass: Friend or Foe to Metabolic Health?
par: Christopher J. Oliver, et autres
Publié: (2025)

The Role of ROS and Its Sources in Tumorigenesis: Friend or Foe?
par: Qin Jiang, et autres
Publié: (2025)

Classroom Management and Novice Language Teachers: Friend or Foe?
par: Ana Clara Sánchez Solarte
Publié: (2019)

Making Mathematical Reasoning Adaptive
par: Lai, Zhejian, et autres
Publié: (2025)

Machine Learning and Artificial Intelligence in PK‐PD Modeling: Fad, Friend, or Foe?
par: Zhonghui Huang, et autres
Publié: (2024)

MUSE: MCTS-Driven Red Teaming Framework for Enhanced Multi-Turn Dialogue Safety in Large Language Models
par: Yan, Siyu, et autres
Publié: (2025)

Friend or Foe: Unraveling the Ties Between Deepfakes, Pornography, and Women
par: Fihsani, Marsya Diandra, et autres
Publié: (2025)

Platelets During Myelin Repair in Multiple Sclerosis: Friend or Foe?
par: Francisco J. Rivera, et autres
Publié: (2025)

Mutual Coupling in Dynamic Metasurface Antennas: Foe, but also Friend
par: Prod'homme, Hugo, et autres
Publié: (2024)

Navigating the Paradox of IL‐22: Friend or Foe in Hepatic Health?
par: Jianqi Qin, et autres
Publié: (2025)

JAK Inhibitors and Cardiovascular Disease in Psoriatic Arthritis: Friends or Foe?
par: Jenny Lin‐Hong Shi, et autres
Publié: (2024)

Natural Killer Cells in Alzheimer's Disease: From Foe to Friend
par: Milos Kostic, et autres
Publié: (2025)

Alleviating Distribution Shift in Synthetic Data for Machine Translation Quality Estimation
par: Geng, Xiang, et autres
Publié: (2025)

Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks
par: Qraitem, Maan, et autres
Publié: (2024)

Turning Foe into Friend: Bridging Neutrophil Biological Characteristics and Neutrophil‐Based Oncolytic Nanotherapeutics
par: Sitong Chen, et autres
Publié: (2026)