REVIEW 11 cited by
Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
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
Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation
read the original abstract
Harmful fine-tuning attack poses serious safety concerns for large language models' fine-tuning-as-a-service. While existing defenses have been proposed to mitigate the issue, their performances are still far away from satisfactory, and the root cause of the problem has not been fully recovered. To this end, we in this paper show that harmful perturbation over the model weights could be a probable cause of alignment-broken. In order to attenuate the negative impact of harmful perturbation, we propose an alignment-stage solution, dubbed Booster. Technically, along with the original alignment loss, we append a loss regularizer in the alignment stage's optimization. The regularizer ensures that the model's harmful loss reduction after the simulated harmful perturbation is attenuated, thereby mitigating the subsequent fine-tuning risk. Empirical results show that Booster can effectively reduce the harmful score of the fine-tuned models while maintaining the performance of downstream tasks. Our code is available at https://github.com/git-disl/Booster.
Forward citations
Cited by 11 Pith papers
-
Emergent Misalignment Recruits a Pre-existing Persona Subspace
Fine-tuning on narrow bad data recruits a low-rank persona subspace already present in a frozen instruction-tuned model; holding that subspace out of activations prevents broad misalignment, and injecting it into the ...
-
One Step to the Side: Why Defenses Against Malicious Finetuning Fail Under Adaptive Adversaries
A unified adaptive attack exploits the common weakness across 15 defenses against malicious fine-tuning, showing they only obscure rather than remove harmful model capabilities.
-
Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning
TokenBuncher constrains response entropy via entropy-as-reward RL and a Token Noiser to stop harmful RL fine-tuning while keeping benign performance intact.
-
HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models
A hypernetwork maps layer-wise activation fingerprints of a fine-tuned LLM to a Safe Side Network that routes harmful prompts to refusal without editing model weights.
-
Information Extraction of Nested Complex Structure of Quantum Cascade Lasers via Large Language Models
JSON schema constraints improve LLM extraction of nested quantum cascade laser structures to 83.4% F1, delivering up to 24.1% gains for smaller models.
-
AlignCultura: Towards Culturally Aligned Large Language Models?
Align-Cultura introduces the CULTURAX dataset and shows that culturally fine-tuned LLMs improve joint HHH scores by 4-6%, cut cultural failures by 18%, and gain 10-12% efficiency with minimal leakage.
-
Preventing Safety Drift in Large Language Models via Coupled Weight and Activation Constraints
Coupled constraints on weight updates in a safety subspace and regularization of SAE-identified safety features preserve LLM refusal behaviors during fine-tuning better than weight-only or activation-only methods.
-
Secure LLM Fine-Tuning via Safety-Aware Probing
SAP locates safety-correlated directions via contrastive signals and perturbs hidden-state propagation with a lightweight probe to preserve safety while fine-tuning LLMs for task performance.
-
SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance-Diversity Data Selection
SPARD defends LLMs from harmful fine-tuning attacks via alternating safety projections and relevance-diversity DPP data selection, reporting lowest attack success rates on GSM8K and OpenBookQA while keeping task accuracy.
-
Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.
-
Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey
Survey of harmful fine-tuning attacks on LLMs, their variants, defense strategies, mechanical analysis, and evaluation methodologies.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.