AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance–Diversity Data Selection

Shuhao Chen, Weisen Jiang, Yeqi Gong, Shengda Luo, Chengxiang Zhuo, Zang Li, James Kwok, Yu Zhang

ICML 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: LLM jailbreak and injection defense · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add trust-region radius eta_safe (ablation)SPARD · GSM8K (Qwen-2.5-7B)GSM8K accuracy: 81.92 -> 85.77Improved
add trust-region radius eta_safe (ablation)SPARD · GSM8K (Qwen-2.5-7B)average ASR (%): 5.03 -> 9.45Hurt
use Relevance-Diversity DPP instead of random selection (ablation)SPAG · GSM8K (Qwen-2.5-7B)average ASR (%): 15.85 -> 9.45Improved
use Relevance-Diversity DPP instead of max-quality selection (ablation)SPAG · GSM8K (Qwen-2.5-7B)average ASR (%): 16.51 -> 9.45Improved
add SPAG safety projection with random safe data versus Lisa (ablation)Lisa · GSM8K (Qwen-2.5-7B)average ASR (%): 19.12 -> 15.85Improved
add SPAG safety projection to DPP-selected data (ablation)standard fine-tuning · GSM8K (Qwen-2.5-7B)average ASR (%): 74.90 -> 9.45Improved
select safe data by Relevance-Diversity DPP instead of D_High-Sim with SPAG (ablation)SPAG · GSM8K (Qwen-2.5-7B)average ASR (%): 16.51 -> 9.45Improved
select safe data by DPP instead of D_Low-Sim with SPAG (ablation)SPAG · GSM8K (Qwen-2.5-7B)average ASR (%): 58.82 -> 9.45Improved
SPARD versus SFT on harmful fine-tuningQwen-2.5-7B-Instruct · GSM8Kaverage ASR (%): 87.93 -> 9.45Improved
SPARD versus SFT on harmful fine-tuningLLaMA-3.2-3B-Instruct · GSM8Kaverage ASR (%): 91.36 -> 12.09Improved
SPARD versus SafeGradQwen-2.5-7B-Instruct · OpenBookQAaverage ASR (%): 20.63 -> 14.54Improved
full fine-tuning instead of LoRA with SPARDSmolLM2-1.7B-Instruct · GSM8K (BeaverTails)ASR (%): 74.0 -> 17.4Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy