Cover Image

Activation Surgery: Jailbreaking White-box LLMs without Touching the Prompt

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jenny, Maël, Dentan, Jérémie, Vanier, Sonia, Krajecki, Michaël
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Predicting memorization within Large Language Models fine-tuned for classification
by: Dentan, Jérémie, et al.
Published: (2024)

Reconstructing training data from document understanding models
by: Dentan, Jérémie, et al.
Published: (2024)

RL-JACK: Reinforcement Learning-powered Black-box Jailbreaking Attack against LLMs
by: Chen, Xuan, et al.
Published: (2024)

PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage
by: Nakka, Krishna Kanth, et al.
Published: (2025)

Analysis of LLMs Against Prompt Injection and Jailbreak Attacks
by: Jaiswal, Piyush, et al.
Published: (2026)

Enhancing Jailbreak Attacks on LLMs via Persona Prompts
by: Zhang, Zheng, et al.
Published: (2025)

Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks
by: Xiong, Chen, et al.
Published: (2024)

Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts
by: Zhang, Chiyu, et al.
Published: (2025)

Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
by: Chen, Yunhao, et al.
Published: (2025)

PolyJailbreak: Cross-Modal Jailbreaking Attacks on Black-Box Multimodal LLMs
by: Wang, Xinkai, et al.
Published: (2025)

Touch to Pair: Secure and Usable IoT Pairing without Information Loss
by: Wu, Chuxiong, et al.
Published: (2024)

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs
by: Li, Hongyi, et al.
Published: (2024)

One Model Transfer to All: On Robust Jailbreak Prompts Generation against LLMs
by: Li, Linbao, et al.
Published: (2025)

White-box Membership Inference Attacks against Diffusion Models
by: Pang, Yan, et al.
Published: (2023)

Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy
by: Jeong, Joonhyun, et al.
Published: (2025)

GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis
by: Xie, Yueqi, et al.
Published: (2024)

Efficient and Stealthy Jailbreak Attacks via Adversarial Prompt Distillation from LLMs to SLMs
by: Li, Xiang, et al.
Published: (2025)

The Midas Touch: Triggering the Capability of LLMs for RM-API Misuse Detection
by: Yang, Yi, et al.
Published: (2024)

Guess or Recall? Training CNNs to Classify and Localize Memorization in LLMs
by: Dentan, Jérémie, et al.
Published: (2025)

Jailbreaking LLMs & VLMs: Mechanisms, Evaluation, and Unified Defense
by: Chen, Zejian, et al.
Published: (2026)

MacPrompt: Maraconic-guided Jailbreak against Text-to-Image Models
by: Ye, Xi, et al.
Published: (2026)

Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models
by: Hu, Xiaomeng, et al.
Published: (2024)

Involuntary Jailbreak: On Self-Prompting Attacks
by: Guo, Yangyang, et al.
Published: (2025)

Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs
by: Pathade, Chetan
Published: (2025)

TASO: Jailbreak LLMs via Alternative Template and Suffix Optimization
by: Wang, Yanting, et al.
Published: (2025)

Ellipsoid Control: A White-list Jailbreak Defense via Benign Latent Modeling
by: Chen, Luoyu, et al.
Published: (2026)

Beyond Fixed and Dynamic Prompts: Embedded Jailbreak Templates for Advancing LLM Security
by: Kim, Hajun, et al.
Published: (2025)

What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks
by: Kirch, Nathalie, et al.
Published: (2024)

The Trojan Example: Jailbreaking LLMs through Template Filling and Unsafety Reasoning
by: Liu, Mingrui, et al.
Published: (2025)

Mitigating Jailbreaks with Intent-Aware LLMs
by: Yeo, Wei Jie, et al.
Published: (2025)

Attack via Overfitting: 10-shot Benign Fine-tuning to Jailbreak LLMs
by: Xie, Zhixin, et al.
Published: (2025)

Soft Begging: Modular and Efficient Shielding of LLMs against Prompt Injection and Jailbreaking based on Prompt Tuning
by: Ostermann, Simon, et al.
Published: (2024)

Defending Jailbreak Prompts via In-Context Adversarial Game
by: Zhou, Yujun, et al.
Published: (2024)

LLMStinger: Jailbreaking LLMs using RL fine-tuned LLMs
by: Jha, Piyush, et al.
Published: (2024)

Ariadne: a Privacy-Preserving Communication Protocol
by: Fressancourt, Antoine, et al.
Published: (2024)

JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation
by: Zhang, Shenyi, et al.
Published: (2025)

FlipAttack: Jailbreak LLMs via Flipping
by: Liu, Yue, et al.
Published: (2024)

"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
by: Shen, Xinyue, et al.
Published: (2023)

Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting
by: Cretu, Ana-Maria, et al.
Published: (2023)

SEAL: Entangled White-box Watermarks on Low-Rank Adaptation
by: Oh, Giyeong, et al.
Published: (2025)