Cover Image

Online Learning Defense against Iterative Jailbreak Attacks via Prompt Optimization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kaneko, Masahiro, Talat, Zeerak, Baldwin, Timothy
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Bits Leaked per Query: Information-Theoretic Bounds on Adversarial Attacks against LLMs
by: Kaneko, Masahiro, et al.
Published: (2025)

JailNewsBench: Multi-Lingual and Regional Benchmark for Fake News Generation under Jailbreak Attacks
by: Kaneko, Masahiro, et al.
Published: (2026)

Zero-shot Sentiment Analysis in Low-Resource Languages Using a Multilingual Sentiment Lexicon
by: Koto, Fajri, et al.
Published: (2024)

Evaluating Gender Bias in Large Language Models via Chain-of-Thought Prompting
by: Kaneko, Masahiro, et al.
Published: (2024)

A Little Leak Will Sink a Great Ship: Survey of Transparency for Large Language Models from Start to Finish
by: Kaneko, Masahiro, et al.
Published: (2024)

A Capabilities Approach to Studying Bias and Harm in Language Technologies
by: Nigatu, Hellina Hailu, et al.
Published: (2024)

Balanced Multi-Factor In-Context Learning for Multilingual Large Language Models
by: Kaneko, Masahiro, et al.
Published: (2025)

The Gaps between Pre-train and Downstream Settings in Bias Evaluation and Debiasing
by: Kaneko, Masahiro, et al.
Published: (2024)

Beyond the Resumé: A Rubric-Aware Automatic Interview System for Information Elicitation
by: Stuart, Harry, et al.
Published: (2026)

Eagle: Ethical Dataset Given from Real Interactions
by: Kaneko, Masahiro, et al.
Published: (2024)

Defense against Prompt Injection Attacks via Mixture of Encodings
by: Zhang, Ruiyi, et al.
Published: (2025)

AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
by: Zeng, Yifan, et al.
Published: (2024)

Subjective $\textit{Isms}$? On the Danger of Conflating Hate and Offence in Abusive Language Detection
by: Curry, Amanda Cercas, et al.
Published: (2024)

Impoverished Language Technology: The Lack of (Social) Class in NLP
by: Curry, Amanda Cercas, et al.
Published: (2024)

Unrequited Emotions: Investigating the Gaps in Motivation and Practice in Speech Emotion Recognition Research
by: Wong, Taryn, et al.
Published: (2026)

Understanding "Democratization" in NLP and ML Research
by: Subramonian, Arjun, et al.
Published: (2024)

Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey
by: Liu, Xuannan, et al.
Published: (2024)

FedMental: Evaluating Federated Learning for Mental Health Detection from Social Media Data
by: Abdelkadir, Nuredin Ali, et al.
Published: (2026)

Unified Defense for Large Language Models against Jailbreak and Fine-Tuning Attacks in Education
by: Yi, Xin, et al.
Published: (2025)

Classist Tools: Social Class Correlates with Performance in NLP
by: Curry, Amanda Cercas, et al.
Published: (2024)

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression
by: Li, Yucheng, et al.
Published: (2025)

Paraphrasing Adversarial Attack on LLM-as-a-Reviewer
by: Kaneko, Masahiro
Published: (2026)

The Perspectivist Paradigm Shift: Assumptions and Challenges of Capturing Human Labels
by: Fleisig, Eve, et al.
Published: (2024)

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval
by: Chen, Taiye, et al.
Published: (2025)

Exploitation All the Way Down: Calling out the Root Cause of Bad Online Experiences for Users of the "Majority World"
by: Nigatu, Hellina Hailu, et al.
Published: (2024)

PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization
by: Wang, Yidan, et al.
Published: (2025)

ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs
by: Jiang, Fengqing, et al.
Published: (2024)

Defending LLMs against Jailbreaking Attacks via Backtranslation
by: Wang, Yihan, et al.
Published: (2024)

Social Bias Evaluation for Large Language Models Requires Prompt Variations
by: Hida, Rem, et al.
Published: (2024)

Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing
by: Ji, Jiabao, et al.
Published: (2024)

AttentionDefense: Leveraging System Prompt Attention for Explainable Defense Against Novel Jailbreaks
by: Siska, Charlotte, et al.
Published: (2025)

FATH: Authentication-based Test-time Defense against Indirect Prompt Injection Attacks
by: Wang, Jiongxiao, et al.
Published: (2024)

How You Prompt Matters! Even Task-Oriented Constraints in Instructions Affect LLM-Generated Text Detection
by: Koike, Ryuto, et al.
Published: (2023)

TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning
by: Sun, Bowen, et al.
Published: (2026)

Sampling-based Pseudo-Likelihood for Membership Inference Attacks
by: Kaneko, Masahiro, et al.
Published: (2024)

Code-Switching in End-to-End Automatic Speech Recognition: A Systematic Literature Review
by: Agro, Maha Tufail, et al.
Published: (2025)

Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
by: Zhou, Andy, et al.
Published: (2024)

IYKYK: Using language models to decode extremist cryptolects
by: de Kock, Christine, et al.
Published: (2025)

Exploring the Limitations of Detecting Machine-Generated Text
by: Doughman, Jad, et al.
Published: (2024)

Preventing Jailbreak Prompts as Malicious Tools for Cybercriminals: A Cyber Defense Perspective
by: Tshimula, Jean Marie, et al.
Published: (2024)