TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering
This work addresses the problem of inconsistent safety evaluations for LLMs, which is critical for developers and users to minimize risks from unsafe modifications, though it is incremental in providing a standardized benchmarking tool.
The paper tackles the lack of a standard approach to evaluate tamper resistance in large language models (LLMs) by introducing TamperBench, a unified framework that systematically assesses safety under fine-tuning and tampering, yielding insights such as jailbreak-tuning being the most severe attack and Triplet as a leading defense.
As increasingly capable open-weight large language models (LLMs) are deployed, improving their tamper resistance against unsafe modifications, whether accidental or intentional, becomes critical to minimize risks. However, there is no standard approach to evaluate tamper resistance. Varied data sets, metrics, and tampering configurations make it difficult to compare safety, utility, and robustness across different models and defenses. To this end, we introduce TamperBench, the first unified framework to systematically evaluate the tamper resistance of LLMs. TamperBench (i) curates a repository of state-of-the-art weight-space fine-tuning attacks and latent-space representation attacks; (ii) enables realistic adversarial evaluation through systematic hyperparameter sweeps per attack-model pair; and (iii) provides both safety and utility evaluations. TamperBench requires minimal additional code to specify any fine-tuning configuration, alignment-stage defense method, and metric suite while ensuring end-to-end reproducibility. We use TamperBench to evaluate 21 open-weight LLMs, including defense-augmented variants, across nine tampering threats using standardized safety and capability metrics with hyperparameter sweeps per model-attack pair. This yields novel insights, including effects of post-training on tamper resistance, that jailbreak-tuning is typically the most severe attack, and that Triplet emerges as a leading alignment-stage defense. Code is available at: https://github.com/criticalml-uw/TamperBench