Cover Image

You Can't Eat Your Cake and Have It Too: The Performance Degradation of LLMs with Jailbreak Defense

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mai, Wuyuao, Hong, Geng, Chen, Pei, Pan, Xudong, Liu, Baojun, Zhang, Yuan, Duan, Haixin, Yang, Min
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Shell or Nothing: Real-World Benchmarks and Memory-Activated Agents for Automated Penetration Testing
by: Mai, Wuyuao, et al.
Published: (2025)

Have Your Cake and Eat It Too: Toward Efficient and Accurate Split Federated Learning
by: Yan, Dengke, et al.
Published: (2023)

Revealing the Black Box of Device Search Engine: Scanning Assets, Strategies, and Ethical Consideration
by: Wu, Mengying, et al.
Published: (2024)

You Can't Trust Your Tag Neither: Privacy Leaks and Potential Legal Violations within the Google Tag Manager
by: Mertens, Gilles, et al.
Published: (2023)

You Can't Steal Nothing: Mitigating Prompt Leakages in LLMs via System Vectors
by: Cao, Bochuan, et al.
Published: (2025)

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

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

You Can Run But You Can't Hide: Runtime Protection Against Malicious Package Updates For Node.js
by: Ohm, Marc, et al.
Published: (2023)

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

Invisible Threats from Model Context Protocol: Generating Stealthy Injection Payload via Tree-based Adaptive Search
by: Shen, Yulin, et al.
Published: (2026)

Evolving Security in LLMs: A Study of Jailbreak Attacks and Defenses
by: Shang, Zhengchun, et al.
Published: (2025)

Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses
by: Zheng, Xiaosen, et al.
Published: (2024)

PRISON: Unmasking the Criminal Potential of Large Language Models
by: Wu, Xinyi, et al.
Published: (2025)

Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking Attacks
by: Liu, Xiaoqun, et al.
Published: (2024)

Beyond Jailbreak: Unveiling Risks in LLM Applications Arising from Blurred Capability Boundaries
by: Zhang, Yunyi, et al.
Published: (2025)

If You Can't Beat Them, Eat Them – Stinging Nettle
by: NA
Published: (1989)

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

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

When Bots Take the Bait: Exposing and Mitigating the Emerging Social Engineering Attack in Web Automation Agent
by: Wu, Xinyi, et al.
Published: (2026)

Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications
by: Jiang, Changyue, et al.
Published: (2024)

MCPZoo: A Large-Scale Dataset of Runnable Model Context Protocol Servers for AI Agent
by: Wu, Mengying, et al.
Published: (2025)

Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs
by: Hu, Xiaomeng, et al.
Published: (2025)

ShieldLearner: A New Paradigm for Jailbreak Attack Defense in LLMs
by: Ni, Ziyi, et al.
Published: (2025)

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations
by: Li, Xiaohu, et al.
Published: (2025)

Bidirectional Intention Inference Enhances LLMs' Defense Against Multi-Turn Jailbreak Attacks
by: Tong, Haibo, et al.
Published: (2025)

Injecting Universal Jailbreak Backdoors into LLMs in Minutes
by: Chen, Zhuowei, et al.
Published: (2025)

Enhanced MLLM Black-Box Jailbreaking Attacks and Defenses
by: Zhong, Xingwei, et al.
Published: (2025)

BELT: Old-School Backdoor Attacks can Evade the State-of-the-Art Defense with Backdoor Exclusivity Lifting
by: Qiu, Huming, et al.
Published: (2023)

Image-to-Text Logic Jailbreak: Your Imagination can Help You Do Anything
by: Zou, Xiaotian, et al.
Published: (2024)

A Causal Perspective for Enhancing Jailbreak Attack and Defense
by: Pan, Licheng, et al.
Published: (2026)

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

Your LLM Agent Can Leak Your Data: Data Exfiltration via Backdoored Tool Use
by: Zhang, Wuyang, et al.
Published: (2026)

Revisiting JBShield: Breaking and Rebuilding Representation-Level Jailbreak Defenses
by: Derya, Kemal, et al.
Published: (2026)

TrapSuffix: Proactive Defense Against Adversarial Suffixes in Jailbreaking
by: Du, Mengyao, et al.
Published: (2026)

The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
by: Nikolić, Kristina, et al.
Published: (2025)

A Simple and Efficient Jailbreak Method Exploiting LLMs' Helpfulness
by: Luo, Xuan, et al.
Published: (2025)

How Real is Your Jailbreak? Fine-grained Jailbreak Evaluation with Anchored Reference
by: Liu, Songyang, et al.
Published: (2026)

Unveiling the Resilience of LLM-Enhanced Search Engines against Black-Hat SEO Manipulation
by: Chen, Pei, et al.
Published: (2026)

Jailbreaking Generative AI: Multivector Phishing Threats and Transformer based Defenses
by: Mishra, Rina, et al.
Published: (2025)

Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing
by: Lin, Zheng, et al.
Published: (2026)