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.
F., and Liu, L
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 4
citation-polarity summary
verdicts
UNVERDICTED 9roles
background 4polarities
background 4representative citing papers
TokenBuncher constrains response entropy via entropy-as-reward RL and a Token Noiser to stop harmful RL fine-tuning while keeping benign performance intact.
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.
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.
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.
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 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.
A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.
Survey of harmful fine-tuning attacks on LLMs, their variants, defense strategies, mechanical analysis, and evaluation methodologies.
citing papers explorer
-
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.
-
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.