Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning (2026.acl-long)
Copied to clipboard
Yanrui Du, Fenglei Fan, Sendong Zhao, Jiawei Cao, Ming Ma, Danyang Zhao, Shuren Qi, Ting Liu, Bing Qin
| Challenge: | Instruction Fine-Tuning (IFT) has emerged as a critical technique for customizing Large Language Models (LLMs) however, recent studies have revealed that IFT can compromise the built-in security mechanisms of LLMs, posing significant security risks. |
| Approach: | They propose a method that shifts learning burden onto security-robust parameters and propose 'warm-up' phase that preferentially trains Mods_Rob to learn low-level features with minimal security risk. |
| Outcome: | The proposed method reduces security risks without sacrificing performance gains across knowledge-intensive datasets. |
Similar Papers
Revisiting Instruction Fine-tuned Model Evaluation to Guide Industrial Applications (2023.emnlp-main)
Copied to clipboard
| Challenge: | Instruction fine-tuned (IFT) models are gaining traction in industrial NLP to unlock task-specific performance gains and strengthen model alignment with industry requirements. |
| Approach: | They propose to use instruction fine-tuned (IFT) models to enhance the zero-shot capabilities of Large Language Models (LLMs) they also propose to leverage IFT models to analyze the trade-offs that emerge in industrial settings. |
| Outcome: | The proposed model is well adapted to new evaluation metric requirements, and offers practical insights for real-world LLM deployment. |
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. |
Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing safety-related methodologies for large language models are lacking . despite advances in safety alignment techniques, safeguarding LLMs during adaptation to various tasks remains a challenge. |
| Approach: | They propose a framework to quantify how different parameters affect LLM safety . they propose two targeted intervention paradigms for safety enhancement and preservation . |
| Outcome: | The proposed framework reveals safety-critical patterns across different LLM architectures. |
Safeguarding LLM Fine-tuning via Push-Pull Distributional Alignment (2026.acl-long)
Copied to clipboard
| Challenge: | Existing safety defenses for large language models fail to explicitly repel harmful patterns . Optimal transport (SOT) allows for safe fine-tuning without sacrificing safety . |
| Approach: | They propose a framework that reframes safe fine-tuning from instance-level filtering challenge to distribution-level alignment task grounded in Optimal Transport. |
| Outcome: | a new framework improves safety of large language models while maintaining competitive performance . the proposed framework reduces the risk of errors and improves model performance compared to baselines . |
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 . |
Immunization against harmful fine-tuning attacks (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models are often trained with safety guards to prevent harmful text generation. |
| Approach: | They propose a formal framework based on the training budget of an attacker to validate defenses against harmful fine-tuning attacks. |
| Outcome: | The proposed framework validates whether a model has been fine-tuned against harmful fine-uning attacks on harmful datasets. |
SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent studies show that fine-tuning can erode safety alignment, causing LLMs to respond to harmful or unethical prompts. |
| Approach: | They propose a lightweight framework that restores safety while maintaining downstream performance. |
| Outcome: | The proposed framework reduces harmful outputs compared to other defenses, with negligible impact on utility. |
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. |
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. |
Learning or Self-aligning? Rethinking Instruction Fine-tuning (2024.acl-long)
Copied to clipboard
| Challenge: | Instruction fine-tuning (IFT) is a crucial phase in building large language models (LLMs). |
| Approach: | They propose a knowledge intervention framework to decouple the potential underlying factors of IFT and enable individual analysis of different factors. |
| Outcome: | The proposed framework decouples the potential underlying factors of IFT, enabling individual analysis of different factors. |