Cover Image

Bypassing the Safety Training of Open-Source LLMs with Priming Attacks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Vega, Jason, Chaudhary, Isha, Xu, Changming, Singh, Gagandeep
Format:	Preprint
Published:	2023
Subjects:	Cryptography and Security Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Cross-Input Certified Training for Universal Perturbations
by: Xu, Changming, et al.
Published: (2024)

How Catastrophic is Your LLM? Certifying Risk in Conversation
by: Wang, Chengxiao, et al.
Published: (2025)

MANATEE: Inference-Time Lightweight Diffusion Based Safety Defense for LLMs
by: Kan, Chun Yan Ryan, et al.
Published: (2026)

Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation
by: Huang, Tiansheng, et al.
Published: (2025)

Quantitative Certification of Agentic Tool Selection
by: Yeon, Jehyeok, et al.
Published: (2025)

Matching Ranks Over Probability Yields Truly Deep Safety Alignment
by: Vega, Jason, et al.
Published: (2025)

Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learning
by: Xu, Yinglun, et al.
Published: (2024)

Certifying Knowledge Comprehension in LLMs
by: Chaudhary, Isha, et al.
Published: (2024)

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
by: Hubinger, Evan, et al.
Published: (2024)

Using Hallucinations to Bypass GPT4's Filter
by: Lemkin, Benjamin
Published: (2024)

Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
by: Mehrotra, Anay, et al.
Published: (2023)

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

Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarking
by: Xu, Yijie, et al.
Published: (2025)

Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks
by: Struppek, Lukas, et al.
Published: (2026)

No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
by: Kazdan, Joshua, et al.
Published: (2025)

JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs
by: Chu, Junjie, et al.
Published: (2024)

Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment
by: Shao, Zedian, et al.
Published: (2024)

Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks
by: Poppi, Samuele, et al.
Published: (2024)

Exposing LLM Safety Gaps Through Mathematical Encoding:New Attacks and Systematic Analysis
by: Zhang, Haoyu, et al.
Published: (2026)

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
by: Wang, Kun, et al.
Published: (2025)

LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models
by: Lin, Shi, et al.
Published: (2024)

Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?
by: Liang, Zi, et al.
Published: (2025)

Toward a Safer Web: Multilingual Multi-Agent LLMs for Mitigating Adversarial Misinformation Attacks
by: Aldahoul, Nouar, et al.
Published: (2025)

Special Characters Attack: Toward Scalable Training Data Extraction From Large Language Models
by: Bai, Yang, et al.
Published: (2024)

Advancing Jailbreak Strategies: A Hybrid Approach to Exploiting LLM Vulnerabilities and Bypassing Modern Defenses
by: Ahmed, Mohamed, et al.
Published: (2025)

SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
by: Jin, Chang, et al.
Published: (2026)

IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs
by: Guo, Chuan, et al.
Published: (2026)

Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking
by: Fang, Zhicheng, et al.
Published: (2026)

Safety Alignment Can Be Not Superficial With Explicit Safety Signals
by: Li, Jianwei, et al.
Published: (2025)

On the Role of Attention Heads in Large Language Model Safety
by: Zhou, Zhenhong, et al.
Published: (2024)

Jailbreak Attacks and Defenses Against Large Language Models: A Survey
by: Yi, Sibo, et al.
Published: (2024)

EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage
by: Liao, Zeyi, et al.
Published: (2024)

Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy
by: Wu, Tong, et al.
Published: (2024)

Weight space Detection of Backdoors in LoRA Adapters
by: Merenciano, David Puertolas, et al.
Published: (2026)

Lifelong Safety Alignment for Language Models
by: Wang, Haoyu, et al.
Published: (2025)

Formalizing and Benchmarking Prompt Injection Attacks and Defenses
by: Liu, Yupei, et al.
Published: (2023)

Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
by: Xu, Xiaoyu, et al.
Published: (2025)

Certifying LLM Safety against Adversarial Prompting
by: Kumar, Aounon, et al.
Published: (2023)

An Adversarial Perspective on Machine Unlearning for AI Safety
by: Łucki, Jakub, et al.
Published: (2024)

The Resurgence of GCG Adversarial Attacks on Large Language Models
by: Tan, Yuting, et al.
Published: (2025)