REVIEW 5 cited by
Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Jailbreaking attacks can enable Large Language Models (LLMs) to bypass the safeguard and generate harmful content. Existing jailbreaking defense methods have failed to address the fundamental issue that harmful knowledge resides within the model, leading to potential jailbreak risks for LLMs. In this paper, we propose a novel defense method called Eraser, which mainly includes three goals: unlearning harmful knowledge, retaining general knowledge, and maintaining safety alignment. The intuition is that if an LLM forgets the specific knowledge required to answer a harmful question, it will no longer have the ability to answer harmful questions. The training of Erase does not actually require the model's own harmful knowledge, and it can benefit from unlearning general answers related to harmful queries, which means it does not need assistance from the red team. The experimental results show that Eraser can significantly reduce the jailbreaking success rate for various attacks without compromising the general capabilities of the model. Our codes are available at https://github.com/ZeroNLP/Eraser.
Forward citations
Cited by 5 Pith papers
-
SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses
A systemization of LLM jailbreak security that adds linked taxonomies, an evaluation platform, and JailbreakDB, while its main attack–defense comparison results remain deferred.
-
SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks
SafeLLM detects unsafe outputs, traces them to specific feedforward-network components, and applies constrained optimization to unlearn harmful generation while preserving general capability.
-
Automating Evaluation of Diffusion Model Unlearning with (Vision-) Language Model World Knowledge
A new evaluation tool uses (vision-)language model world knowledge to rank nearby concepts and craft adversarial prompts, showing that diffusion unlearning is incomplete and that semantic similarity correlates with co...
-
SEPS: A Separability Measure for Robust Unlearning in LLMs
SEPS measures separation of forget and retain queries in mixed prompts, and Mixed Prompt training makes unlearned LLMs much better at this separation.
-
A Survey on Generative Model Unlearning: Fundamentals, Taxonomy, Evaluation, and Future Direction
A survey and framework that categorizes generative model unlearning by point-wise versus concept-wise objectives, parameter-based versus non-parametric methods, and completeness/utility/efficiency evaluation.
Discussion (0). Continue with ORCID to comment.