Image de couverture de livre

Adaptive Probe-based Steering for Robust LLM Jailbreaking

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Junxi, Dong, Junhao, Xie, Xiaohua
Format:	Preprint
Publié:	2026
Sujets:	Cryptography and Security Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Exploring Adversarial Attacks against Latent Diffusion Model from the Perspective of Adversarial Transferability
par: Chen, Junxi, et autres
Publié: (2024)

Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreaking
par: Chen, Junxi, et autres
Publié: (2025)

Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks
par: Hu, Hanjiang, et autres
Publié: (2025)

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
par: Chao, Patrick, et autres
Publié: (2024)

TrojanPraise: Jailbreak LLMs via Benign Fine-Tuning
par: Xie, Zhixin, et autres
Publié: (2026)

TRYLOCK: Defense-in-Depth Against LLM Jailbreaks via Layered Preference and Representation Engineering
par: Thornton, Scott
Publié: (2026)

The Art of the Jailbreak: Formulating Jailbreak Attacks for LLM Security Beyond Binary Scoring
par: Hossain, Ismail, et autres
Publié: (2026)

CARE: Ensemble Adversarial Robustness Evaluation Against Adaptive Attackers for Security Applications
par: Zhang, Hangsheng, et autres
Publié: (2024)

The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
par: Nasr, Milad, et autres
Publié: (2025)

Sparse Autoencoders are Capable LLM Jailbreak Mitigators
par: Assogba, Yannick, et autres
Publié: (2026)

LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet
par: Li, Nathaniel, et autres
Publié: (2024)

TokenProber: Jailbreaking Text-to-image Models via Fine-grained Word Impact Analysis
par: Wang, Longtian, et autres
Publié: (2025)

Understanding and Enhancing the Transferability of Jailbreaking Attacks
par: Lin, Runqi, et autres
Publié: (2025)

Adaptive Meta-learning-based Adversarial Training for Robust Automatic Modulation Classification
par: Bamdad, Amirmohammad, et autres
Publié: (2025)

Security-by-Design for LLM-Based Code Generation: Leveraging Internal Representations for Concept-Driven Steering Mechanisms
par: Wendlinger, Maximilian, et autres
Publié: (2026)

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks
par: Andriushchenko, Maksym, et autres
Publié: (2024)

Jailbreak Attack Initializations as Extractors of Compliance Directions
par: Levi, Amit, et autres
Publié: (2025)

ASTRA: An Automated Framework for Strategy Discovery, Retrieval, and Evolution for Jailbreaking LLMs
par: Liu, Xu, et autres
Publié: (2025)

Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models
par: Dong, Yingkai, et autres
Publié: (2024)

Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks
par: Wang, Zi, et autres
Publié: (2024)

"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
par: Shen, Xinyue, et autres
Publié: (2023)

Voice Jailbreak Attacks Against GPT-4o
par: Shen, Xinyue, et autres
Publié: (2024)

Jailbreaking Large Language Models in Infinitely Many Ways
par: Goldstein, Oliver, et autres
Publié: (2025)

DeepInception: Hypnotize Large Language Model to Be Jailbreaker
par: Li, Xuan, et autres
Publié: (2023)

JULI: Jailbreak Large Language Models by Self-Introspection
par: Wang, Jesson, et autres
Publié: (2025)

Defending Jailbreak Prompts via In-Context Adversarial Game
par: Zhou, Yujun, et autres
Publié: (2024)

Is The Watermarking Of LLM-Generated Code Robust?
par: Suresh, Tarun, et autres
Publié: (2024)

Toward Principled LLM Safety Testing: Solving the Jailbreak Oracle Problem
par: Lin, Shuyi, et autres
Publié: (2025)

AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
par: Zeng, Yifan, et autres
Publié: (2024)

Systematic Scaling Analysis of Jailbreak Attacks in Large Language Models
par: Wang, Xiangwen, et autres
Publié: (2026)

Knowledge-Driven Multi-Turn Jailbreaking on Large Language Models
par: Li, Songze, et autres
Publié: (2026)

LLMStinger: Jailbreaking LLMs using RL fine-tuned LLMs
par: Jha, Piyush, et autres
Publié: (2024)

Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation
par: Chen, Luoyu, et autres
Publié: (2026)

Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challenges
par: Dong, Junhao, et autres
Publié: (2023)

The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
par: Nikolić, Kristina, et autres
Publié: (2025)

T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models
par: Liang, Siyuan, et autres
Publié: (2025)

MetaCipher: A Time-Persistent and Universal Multi-Agent Framework for Cipher-Based Jailbreak Attacks for LLMs
par: Chen, Boyuan, et autres
Publié: (2025)

LMEraser: Large Model Unlearning through Adaptive Prompt Tuning
par: Xu, Jie, et autres
Publié: (2024)

Odysseus: Jailbreaking Commercial Multimodal LLM-integrated Systems via Dual Steganography
par: Li, Songze, et autres
Publié: (2025)

SafeSteer: Adaptive Subspace Steering for Efficient Jailbreak Defense in Vision-Language Models
par: Zeng, Xiyu, et autres
Publié: (2025)