Copertina

From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhang, Zhexin, Yang, Junxiao, Lu, Yida, Ke, Pei, Cui, Shiyao, Zheng, Chujie, Wang, Hongning, Huang, Minlie
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Cryptography and Security Computation and Language Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints
di: Yang, Junxiao, et al.
Pubblicazione: (2025)

Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
di: Zhang, Zhexin, et al.
Pubblicazione: (2023)

Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs
di: Liu, Fan, et al.
Pubblicazione: (2024)

Reliable Model Watermarking: Defending Against Theft without Compromising on Evasion
di: Zhu, Hongyu, et al.
Pubblicazione: (2024)

Knowledge-to-Jailbreak: Investigating Knowledge-driven Jailbreaking Attacks for Large Language Models
di: Tu, Shangqing, et al.
Pubblicazione: (2024)

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

JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering
di: Chen, Renmiao, et al.
Pubblicazione: (2025)

Prefix Guidance: A Steering Wheel for Large Language Models to Defend Against Jailbreak Attacks
di: Zhao, Jiawei, et al.
Pubblicazione: (2024)

The Ripple Effect: On Unforeseen Complications of Backdoor Attacks
di: Zhang, Rui, et al.
Pubblicazione: (2025)

Defending Large Language Models Against Jailbreak Exploits with Responsible AI Considerations
di: Wong, Ryan, et al.
Pubblicazione: (2025)

DELMAN: Dynamic Defense Against Large Language Model Jailbreaking with Model Editing
di: Wang, Yi, et al.
Pubblicazione: (2025)

Defending Against Neural Network Model Inversion Attacks via Data Poisoning
di: Zhou, Shuai, et al.
Pubblicazione: (2024)

HSF: Defending against Jailbreak Attacks with Hidden State Filtering
di: Qian, Cheng, et al.
Pubblicazione: (2024)

Towards Robust Multimodal Large Language Models Against Jailbreak Attacks
di: Yin, Ziyi, et al.
Pubblicazione: (2025)

Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs
di: Zhong, Yinan, et al.
Pubblicazione: (2025)

Defending Against Attack on the Cloned: In-Band Active Man-in-the-Middle Detection for the Signal Protocol
di: Teng, Wil Liam, et al.
Pubblicazione: (2024)

No Free Lunch for Defending Against Prefilling Attack by In-Context Learning
di: Xue, Zhiyu, et al.
Pubblicazione: (2024)

Defending Against Beta Poisoning Attacks in Machine Learning Models
di: Gulciftci, Nilufer, et al.
Pubblicazione: (2025)

LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper
di: Wu, Daoyuan, et al.
Pubblicazione: (2024)

Too Private to Tell: Practical Token Theft Attacks on Apple Intelligence
di: Zhou, Haoling, et al.
Pubblicazione: (2026)

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

Voice Jailbreak Attacks Against GPT-4o
di: Shen, Xinyue, et al.
Pubblicazione: (2024)

RePD: Defending Jailbreak Attack through a Retrieval-based Prompt Decomposition Process
di: Wang, Peiran, et al.
Pubblicazione: (2024)

Defending LLM Watermarking Against Spoofing Attacks with Contrastive Representation Learning
di: An, Li, et al.
Pubblicazione: (2025)

CleanStack: A New Dual-Stack for Defending Against Stack-Based Memory Corruption Attacks
di: Chong, Lei
Pubblicazione: (2025)

AutoJailbreak: Exploring Jailbreak Attacks and Defenses through a Dependency Lens
di: Lu, Lin, et al.
Pubblicazione: (2024)

Defending Against Prompt Injection with DataFilter
di: Wang, Yizhu, et al.
Pubblicazione: (2025)

Defending Against Indirect Prompt Injection Attacks With Spotlighting
di: Hines, Keegan, et al.
Pubblicazione: (2024)

SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner
di: Wang, Xunguang, et al.
Pubblicazione: (2024)

Beyond Surface-Level Patterns: An Essence-Driven Defense Framework Against Jailbreak Attacks in LLMs
di: Xiang, Shiyu, et al.
Pubblicazione: (2025)

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
di: Xu, Zhangchen, et al.
Pubblicazione: (2024)

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem
di: Mao, Yanxu, et al.
Pubblicazione: (2025)

Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks
di: Jin, Haotian, et al.
Pubblicazione: (2025)

Defending Against Sophisticated Poisoning Attacks with RL-based Aggregation in Federated Learning
di: Wang, Yujing, et al.
Pubblicazione: (2024)

Defending Large Language Models Against Attacks With Residual Stream Activation Analysis
di: Kawasaki, Amelia, et al.
Pubblicazione: (2024)

HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learning
di: Qiu, Pengyu, et al.
Pubblicazione: (2022)

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

Untargeted Jailbreak Attack
di: Huang, Xinzhe, et al.
Pubblicazione: (2025)

Tit-for-Tat: Safeguarding Large Vision-Language Models Against Jailbreak Attacks via Adversarial Defense
di: Hao, Shuyang, et al.
Pubblicazione: (2025)

Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence
di: Fu, Shaopeng, et al.
Pubblicazione: (2025)