Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM
September 18, 2023 ยท Declared Dead ยท ๐ Annual Meeting of the Association for Computational Linguistics
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Bochuan Cao, Yuanpu Cao, Lu Lin, Jinghui Chen
arXiv ID
2309.14348
Category
cs.CL: Computation & Language
Cross-listed
cs.AI,
cs.CR,
cs.LG
Citations
209
Venue
Annual Meeting of the Association for Computational Linguistics
Last Checked
3 months ago
Abstract
Recently, Large Language Models (LLMs) have made significant advancements and are now widely used across various domains. Unfortunately, there has been a rising concern that LLMs can be misused to generate harmful or malicious content. Though a line of research has focused on aligning LLMs with human values and preventing them from producing inappropriate content, such alignments are usually vulnerable and can be bypassed by alignment-breaking attacks via adversarially optimized or handcrafted jailbreaking prompts. In this work, we introduce a Robustly Aligned LLM (RA-LLM) to defend against potential alignment-breaking attacks. RA-LLM can be directly constructed upon an existing aligned LLM with a robust alignment checking function, without requiring any expensive retraining or fine-tuning process of the original LLM. Furthermore, we also provide a theoretical analysis for RA-LLM to verify its effectiveness in defending against alignment-breaking attacks. Through real-world experiments on open-source large language models, we demonstrate that RA-LLM can successfully defend against both state-of-the-art adversarial prompts and popular handcrafted jailbreaking prompts by reducing their attack success rates from nearly 100% to around 10% or less.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Computation & Language
๐
๐
Old Age
๐
๐
Old Age
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
R.I.P.
๐ป
Ghosted
Language Models are Few-Shot Learners
R.I.P.
๐ป
Ghosted
RoBERTa: A Robustly Optimized BERT Pretraining Approach
R.I.P.
๐ป
Ghosted
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
R.I.P.
๐ป
Ghosted
Deep contextualized word representations
Died the same way โ ๐ป Ghosted
R.I.P.
๐ป
Ghosted
PyTorch: An Imperative Style, High-Performance Deep Learning Library
R.I.P.
๐ป
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
๐ป
Ghosted
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
R.I.P.
๐ป
Ghosted