Image de couverture de livre

Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encoding

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Joo, Seongho, Koh, Hyukhun, Jung, Kyomin
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence 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

Public Data Assisted Differentially Private In-Context Learning
par: Joo, Seongho, et autres
Publié: (2025)

Can LLMs Recognize Toxicity? A Structured Investigation Framework and Toxicity Metric
par: Koh, Hyukhun, et autres
Publié: (2024)

Conditional [MASK] Discrete Diffusion Language Model
par: Koh, Hyukhun, et autres
Publié: (2024)

Black-Box Hallucination Detection via Consistency Under the Uncertain Expression
par: Joo, Seongho, et autres
Publié: (2025)

Program Synthesis via Test-Time Transduction
par: Lee, Kang-il, et autres
Publié: (2025)

VLind-Bench: Measuring Language Priors in Large Vision-Language Models
par: Lee, Kang-il, et autres
Publié: (2024)

Casual as an Anchor: Resolving Supervision Misalignment in Formality Transfer Dataset
par: Yu, Hyojeong, et autres
Publié: (2026)

Fine-grained Gender Control in Machine Translation with Large Language Models
par: Lee, Minwoo, et autres
Publié: (2024)

MultiActor-Audiobook: Zero-Shot Audiobook Generation with Faces and Voices of Multiple Speakers
par: Park, Kyeongman, et autres
Publié: (2025)

`For Argument's Sake, Show Me How to Harm Myself!': Jailbreaking LLMs in Suicide and Self-Harm Contexts
par: Schoene, Annika M, et autres
Publié: (2025)

Confidence-Guided Stepwise Model Routing for Cost-Efficient Reasoning
par: Lee, Sangmook, et autres
Publié: (2025)

Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
par: Chan, Yik Siu, et autres
Publié: (2025)

LLMs can be easily Confused by Instructional Distractions
par: Hwang, Yerin, et autres
Publié: (2025)

Avoidance Decoding for Diverse Multi-Branch Story Generation
par: Park, Kyeongman, et autres
Publié: (2025)

LongStory: Coherent, Complete and Length Controlled Long story Generation
par: Park, Kyeongman, et autres
Publié: (2023)

Say It Differently: Linguistic Styles as Jailbreak Vectors
par: Panda, Srikant, et autres
Publié: (2025)

ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs
par: Jiang, Fengqing, et autres
Publié: (2024)

Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs
par: Li, Xiaoxia, et autres
Publié: (2024)

NeSTR: A Neuro-Symbolic Abductive Framework for Temporal Reasoning in Large Language Models
par: Liang, Feng, et autres
Publié: (2025)

What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks
par: Kirch, Nathalie, et autres
Publié: (2024)

StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation
par: Zheng, Huawei, et autres
Publié: (2026)

Uncovering the Potential Risks in Unlearning: Danger of English-only Unlearning in Multilingual LLMs
par: Hwang, Kyomin, et autres
Publié: (2025)

Soft Begging: Modular and Efficient Shielding of LLMs against Prompt Injection and Jailbreaking based on Prompt Tuning
par: Ostermann, Simon, et autres
Publié: (2024)

Generating Diverse Hypotheses for Inductive Reasoning
par: Lee, Kang-il, et autres
Publié: (2024)

FaithUn: Toward Faithful Forgetting in Language Models by Investigating the Interconnectedness of Knowledge
par: Yang, Nakyeong, et autres
Publié: (2025)

Unplug and Play Language Models: Decomposing Experts in Language Models at Inference Time
par: Yang, Nakyeong, et autres
Publié: (2024)

When Wording Steers the Evaluation: Framing Bias in LLM judges
par: Hwang, Yerin, et autres
Publié: (2026)

Uncovering the Persuasive Fingerprint of LLMs in Jailbreaking Attacks
par: Noughabi, Havva Alizadeh, et autres
Publié: (2025)

Playing Language Game with LLMs Leads to Jailbreaking
par: Peng, Yu, et autres
Publié: (2024)

Abductive Reasoning with Syllogistic Forms in Large Language Models
par: Abe, Hirohiko, et autres
Publié: (2026)

Foot-In-The-Door: A Multi-turn Jailbreak for LLMs
par: Weng, Zixuan, et autres
Publié: (2025)

Poisoned LangChain: Jailbreak LLMs by LangChain
par: Wang, Ziqiu, et autres
Publié: (2024)

From LLMs to MLLMs: Exploring the Landscape of Multimodal Jailbreaking
par: Wang, Siyuan, et autres
Publié: (2024)

Defending LLMs against Jailbreaking Attacks via Backtranslation
par: Wang, Yihan, et autres
Publié: (2024)

Jailbreaking to Jailbreak
par: Kritz, Jeremy, et autres
Publié: (2025)

Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs
par: Xing, Wenpeng, et autres
Publié: (2025)

MP2D: An Automated Topic Shift Dialogue Generation Framework Leveraging Knowledge Graphs
par: Hwang, Yerin, et autres
Publié: (2024)

Data Laundering: Artificially Boosting Benchmark Results through Knowledge Distillation
par: Mansurov, Jonibek, et autres
Publié: (2024)

From We to Me: Theory Informed Narrative Shift with Abductive Reasoning
par: Patil, Jaikrishna Manojkumar, et autres
Publié: (2026)

AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
par: Liu, Xiaogeng, et autres
Publié: (2023)