# Tamper-Resistant Safeguards for Open-Weight LLMs

arXiv: https://arxiv.org/abs/2408.00761 · HTML: https://mlsanity.com/paper/2408.00761/

## Key facts

- Cited by 138 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 45 of its 62 references that are in the map.
- First posted on arXiv 1 Aug 2024.

## Placed in

- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 30 of 45)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal](https://mlsanity.com/paper/2402.04249/) (2024)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models](https://mlsanity.com/paper/2310.04451/) (2023)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning](https://mlsanity.com/paper/2403.03218/) (2024)
- [Who's Harry Potter? Approximate Unlearning in LLMs](https://mlsanity.com/paper/2310.02238/) (2023)
- [Snapshot Ensembles: Train 1, get M for free](https://mlsanity.com/paper/1704.00109/) (2017)
- [ZeRO-Offload: Democratizing Billion-Scale Model Training](https://mlsanity.com/paper/2101.06840/) (2021)
- [Large Language Model Unlearning](https://mlsanity.com/paper/2310.10683/) (2023)
- [Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models](https://mlsanity.com/paper/2310.02949/) (2023)
- [LEACE: Perfect linear concept erasure in closed form](https://mlsanity.com/paper/2306.03819/) (2023)
- [Rethinking Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2402.08787/) (2024)
- [Fast Yet Effective Machine Unlearning](https://mlsanity.com/paper/2111.08947/) (2021)
- [Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations](https://mlsanity.com/paper/2003.02960/) (2020)

## Built on by (most cited first, 30 of 138)

- [LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet](https://mlsanity.com/paper/2408.15221/) (2024)
- [Safety Layers in Aligned Large Language Models: The Key to LLM Security](https://mlsanity.com/paper/2408.17003/) (2024)
- [An Adversarial Perspective on Machine Unlearning for AI Safety](https://mlsanity.com/paper/2409.18025/) (2024)
- [Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation](https://mlsanity.com/paper/2409.01586/) (2024)
- [Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey](https://mlsanity.com/paper/2409.18169/) (2024)
- [Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond](https://mlsanity.com/paper/2502.05374/) (2025)
- [Do Unlearning Methods Remove Information from Language Model Weights?](https://mlsanity.com/paper/2410.08827/) (2024)
- [Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning](https://mlsanity.com/paper/2408.09600/) (2024)
- [Position: LLM Unlearning Benchmarks are Weak Measures of Progress](https://mlsanity.com/paper/2410.02879/) (2024)
- [A Closer Look at Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2410.08109/) (2024)
- [On Evaluating the Durability of Safeguards for Open-Weight LLMs](https://mlsanity.com/paper/2412.07097/) (2024)
- [Improving LLM Safety Alignment with Dual-Objective Optimization](https://mlsanity.com/paper/2503.03710/) (2025)
- [Infrastructure for AI Agents](https://mlsanity.com/paper/2501.10114/) (2025)
- [Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts](https://mlsanity.com/paper/2410.12777/) (2024)
- [Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities](https://mlsanity.com/paper/2502.05209/) (2025)
- [Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbation](https://mlsanity.com/paper/2410.09760/) (2024)
- [Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization](https://mlsanity.com/paper/2410.12949/) (2024)
- [Erasing Conceptual Knowledge from Language Models](https://mlsanity.com/paper/2410.02760/) (2024)
- [Gradient Routing: Masking Gradients to Localize Computation in Neural Networks](https://mlsanity.com/paper/2410.04332/) (2024)
- [Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks](https://mlsanity.com/paper/2410.18210/) (2024)
- [Backtracking Improves Generation Safety](https://mlsanity.com/paper/2409.14586/) (2024)
- [SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging](https://mlsanity.com/paper/2503.17239/) (2025)
- [FORTRESS: Frontier Risk Evaluation for National Security and Public Safety](https://mlsanity.com/paper/2506.14922/) (2025)
- [Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety](https://mlsanity.com/paper/2505.06843/) (2025)
- [Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning](https://mlsanity.com/paper/2506.01339/) (2025)
- [Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation](https://mlsanity.com/paper/2501.18100/) (2025)
- [AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin](https://mlsanity.com/paper/2506.08473/) (2025)
- [Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models](https://mlsanity.com/paper/2506.16447/) (2025)
- [Estimating Worst-Case Frontier Risks of Open-Weight LLMs](https://mlsanity.com/paper/2508.03153/) (2025)
- [Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research](https://mlsanity.com/paper/2412.06966/) (2024)

## Abstract (arXiv)

Rapid advances in the capabilities of large language models (LLMs) have raised widespread concerns regarding their potential for malicious use. Open-weight LLMs present unique challenges, as existing safeguards lack robustness to tampering attacks that modify model weights. For example, recent works have demonstrated that refusal and unlearning safeguards can be trivially removed with a few steps of fine-tuning. These vulnerabilities necessitate new approaches for enabling the safe release of open-weight LLMs. We develop a method, called TAR, for building tamper-resistant safeguards into open-weight LLMs such that adversaries cannot remove the safeguards even after hundreds of steps of fine-tuning. In extensive evaluations and red teaming analyses, we find that our method greatly improves tamper-resistance while preserving benign capabilities. Our results demonstrate that progress on tamper-resistance is possible, opening up a promising new avenue to improve the safety and security of open-weight LLMs.