The Fragility of Jailbreak Robustness Across Operational States

arXiv:2608.30748 · cs.CR, cs.CL · Submitted 2026-08-31 · Read on arXiv

cs.CR, cs.CL

Submitted: 2026-08-31

Updated: 2026-08-31

Code: https://github.com/patrickrchao/JailbreakingLLMshttps:

Terminology

• Robustness — 110× in this paper · explained in 5 episodes
• Alignment — 13× in this paper · explained in 1 episode
• Attack Success Rate — 9× in this paper
• AUROC — 8× in this paper · explained in 2 episodes
• Generalization — 4× in this paper · explained in 13 episodes
• State Sensitivity Indicator — 4× in this paper
• Alignment Methods — 3× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Cooperation — 2× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Personalization — 2× in this paper · explained in 2 episodes
• Accountability — 1× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Adversarial Prompting — 1× in this paper · explained in 1 episode
• Attack Success Rate (ASR) — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Korea Institute of Science and Technology — 1× in this paper
• Linear probe — 1× in this paper · explained in 2 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Representation Engineering — 1× in this paper · explained in 2 episodes

Sources

• The Llama 3 Herd of Models
• Mistral 7B
• DeepInception: Hypnotize Large Language Model to Be Jailbreaker
• AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs
• AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs
• Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• Qwen2.5 Technical Report
• The Better Angels of Machine Personality: How Personality Relates to LLM Safety
• BERTScore: Evaluating Text Generation with BERT
• Enhancing Jailbreak Attacks on LLMs via Persona Prompts
• Representation Engineering: A Top-Down Approach to AI Transparency
• Universal and Transferable Adversarial Attacks on Aligned Language Models

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs