CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning (2026.acl-long)
Copied to clipboard
| Challenge: | Fine-tuning-as-a-service exposes models to harmful fine-tuneing attacks . however, inherent general adaptability of LLMs allows them to bypass selective unlearning by rapidly relearning or repurposing their general capabilities for harmful tasks. |
| Approach: | They propose a paradigm shift that inducing model collapse instead of selective removal by relearning or repurposing general capabilities for harmful tasks. |
| Outcome: | The proposed model collapse mechanism neutralizes the very general capabilities that attackers exploit, tackling the core issue unaddressed by selective unlearning. |
Similar Papers
SDD: Self-Degraded Defense against Malicious Fine-tuning (2025.acl-long)
Copied to clipboard
| Challenge: | Open-source Large Language Models (LLMs) employ safety alignment methods to resist harmful instructions, but malicious fine-tuning can easily bypass these safeguards. |
| Approach: | They propose a framework to prevent malicious fine-tuning of large language models on harmful data by using alignment methods that encourage them to produce irrelevant responses to harmful prompts. |
| Outcome: | The proposed framework reduces the general capability of the LLM when malicious fine-tuning fails, rendering it incapable of following harmful instructions. |
Multitask-Bench: Unveiling and Mitigating Safety Gaps in LLMs Fine-tuning (2025.coling-main)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have led to their adoption across a wide range of tasks, ranging from code generation to machine translation and sentiment analysis. |
| Approach: | They propose to fine-tune LLMs on benign (non-harmful) data to ensure safe outputs. |
| Outcome: | The proposed model reduces attack success rates across a range of tasks without compromising its usefulness. |
Making Harmful Behaviors Unlearnable for Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are often customized by fine-tuning for the requirements of different domains. |
| Approach: | They propose a controllable training framework to make undesired behaviors unlearnable during the fine-tuning process. |
| Outcome: | The proposed framework makes undesired behaviors unlearnable during the fine-tuning process while preserving the ability to learn other information. |
Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Fine-tuning large language models for downstream tasks often leads to catastrophic forgetting, notably degrading the safety of original alignments. |
| Approach: | They propose to merge the weights of pre- and post-fine-tuned models to improve safety while enhancing performance. |
| Outcome: | Experiments across different downstream tasks and models validate the method’s practicality and effectiveness. |
Dissecting Fine-Tuning Unlearning in Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning-based unlearning are ineffective at completely erasing model-embedded knowledge, but their true effectiveness remains unclear. |
| Approach: | They propose to use activation patching and parameter restoration experiments to examine the limitations of fine-tuning-based unlearning methods for erasing harmful, sensitive, or copyrighted information within large language models. |
| Outcome: | The proposed methods alter the model’s knowledge retrieval process rather than genuinely erasing the problematic knowledge embedded in the model parameters. |
Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models achieve effective safety alignment at the time of release, but fine-tuning often compromises safety mechanisms. |
| Approach: | They propose a method that performs safety realignment for large language models . they identify unsafe delta parameters from the fine-tuned models and recalibrate the retained parameters . |
| Outcome: | The proposed method improves safety performance on safety benchmarks and jailbreak attacks while maintaining their performance on downstream tasks. |
LM-Cocktail: Resilient Tuning of Language Models via Model Merging (2024.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models are continually fine-tuned to better support downstream applications. however, this operation may result in significant performance degeneration on general perspectives. |
| Approach: | They propose a method which enables pre-trained language models to stay resilient in general perspectives. |
| Outcome: | The proposed model achieves strong empirical performance in the whole scope of general tasks while preserving a superior capacity in its targeted domain. |
Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are vulnerable to jailbreak attacks that exploit weaknesses in traditional safety alignment. |
| Approach: | They propose a framework that trains models to engage in explicit safe reasoning before response . they propose RATIONAL, which allows models to reject harmful prompts while providing meaningful and context-aware responses. |
| Outcome: | The proposed framework fine-tunes models to reason about query intent, ethics, and potential harm. |
Revisiting Catastrophic Forgetting in Large Language Model Tuning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Catastrophic Forgetting (CF) compromises the effectiveness of large language models during fine-tuning, yet the underlying causes of CF remain largely unexplored. |
| Approach: | They propose a method to flatten the model loss landscape to mitigate CF by flattening the loss landscape. |
| Outcome: | The proposed method complements existing anti-forgetting strategies, further enhancing the resistance of LLMs to CF. |
Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks (2025.findings-naacl)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models have sparked concerns about their safety. |
| Approach: | They propose a method to identify safety-related information in the model parameter space . they propose to use a few adversarially chosen examples to fine-tune LLMs . |
| Outcome: | The proposed method can break safety alignment in multilingual LLMs using a few examples . it also shows that the proposed method jailbreaks LLM models adapted to new languages . |