Papers › Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning

Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning

19 Jan 2024arXiv:2401.10862archive 2025-07-28

Adib Hasan, Ileana Rugina, Alex Wang

This paper investigates the impact of model compression on the way Large Language Models (LLMs) process prompts, particularly concerning jailbreak resistance. We show that moderate WANDA pruning can enhance resistance to jailbreaking attacks without fine-tuning, while maintaining performance on standard benchmarks. To systematically evaluate this safety enhancement, we introduce a dataset of 225 harmful tasks across five categories. Our analysis of LLaMA-2 Chat, Vicuna 1.3, and Mistral Instruct v0.2 reveals that pruning benefits correlate with initial model safety levels. We interpret these results by examining changes in attention patterns and perplexity shifts, demonstrating that pruned models exhibit sharper attention and increased sensitivity to artificial jailbreak constructs. We extend our evaluation to the AdvBench harmful behavior tasks and the GCG attack method. We find that LLaMA-2 is much safer on AdvBench prompts than on our dataset when evaluated with manual jailbreak attempts, and that pruning is effective against both automated attacks and manual jailbreaking on Advbench.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

crystaleye42/eval-safety officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Simple and Effective Pruning Approach for Large Language Models (arXiv:2306.11695; that paper's own run record: 9 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Model Compression

Datasets

Introduced by this paper, per the archive.

HarmfulTasks

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

FocusPruning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections